Search

The operation and maintenance expenses of power transmission and transformation projects, as a significant power supply carrier of the nation, continue to rise as a result of the sustained and quick expansion of China's social economy and the quick growth of the country's power demand. Power grid businesses are under a lot of market pressure. To increase the level of lean management of the operation and maintenance costs of power transmission and transformation projects, power grid enterprises must significantly enhance their capacity to estimate the operation and maintenance costs of their organizations in advance. Machine learning algorithms are gradually applied to the operation and maintenance cost prediction of power transmission and transformation projects of power grid enterprises as a result of the ongoing development of big data technology, effectively increasing the accuracy of operation and maintenance cost prediction. In this paper, by analyzing the variables affecting the differential operation and maintenance cost of power transmission and transformation projects, a scientific and reasonable investment analysis model for the differential operation and maintenance cost of power transmission and transformation projects is constructed using the stochastic forest algorithm of particle swarm optimization, and the variables affecting the differential operation and maintenance cost of substations and transmission lines are obtained, which proves that the trend of the prediction model in this paper is more consistent with the actual situation. [ABSTRACT FROM AUTHOR]

It is well known that energy forecasts play an important role in guiding energy policy, economic development and technological progress. Therefore, based on the purpose of energy consumption and production forecasting, this paper proposes a novel structure adaptive discrete grey Bernoulli model, which is innovative in terms of both accumulated generating operator and model structure. In terms of accumulated generating operator, a new fractional order accumulated generating operator is proposed in this paper. The new accumulated generating operator has a different information priority by adjusting the values of the parameters. In terms of model structure, a novel discrete grey Bernoulli model is proposed in this paper. The novel model is well adapted to time series data containing nonlinear information, and can well mine and utilize the information contained in the original data. In addition, the Particle Swarm Optimization (PSO) algorithm was chosen to optimize the model parameters based on algorithm comparison experiments. This enables the model to flexibly adapt to a variety of complex data and has the ability of structure adaptive. Moreover, this paper conducts comparative experiments between the novel model and eight other forecasting algorithms for time series data. The numerical results show that the novel model has better forecasting performance for the data of China's total energy consumption, China's total electricity generation and China's total domestic electricity consumption. In addition, for the model reliability problem caused by the optimization algorithm, the stability and accuracy of the model are verified by Monte Carlo simulation and probability density visualization analysis. Finally, the proposed model predicts the future development trend of energy consumption and production in China. • A novel structural adaptive discrete grey Bernoulli model is established. • The proposed model can grasp nonlinear and fluctuant in various datasets. • The robustness analysis of the novel model is established. • Comparative study shows that the novel model is superior to other models. • Relevant suggestions are put forward according to the prediction results. [ABSTRACT FROM AUTHOR]

China has committed to peak carbon emissions by 2030 and become carbon neutral by 2060. Hebei, as a major energy province in China, has more challenging carbon peaking and carbon neutrality targets. Based on the extended STIRPAT model, this paper evaluates the time to peak carbon and post-peak carbon trend changes in Hebei province under different scenarios from 2020 to 2060. Based on the support vector machine model with particle swarm optimization, this paper evaluates the carbon neutral pathways under different scenarios in Hebei province from 2020 to 2060 in terms of forests, croplands, wetlands, grasslands and Carbon Capture, Utilization and Storage (CCUS). The results show that a monotonically flat trend without inflection point, a single-inflection-point plateau-period trend and a multi-inflection-point inverted U-wave trend occur after carbon peaks. Hebei Province can achieve carbon neutrality by 2060 under the policy scenario and the enhanced scenario, and the enhanced scenario is better. Comparing with existing studies, the innovation of this paper is to design different trends of changes after carbon peak, combining carbon absorption and carbon emission, and providing more diversified development paths for carbon neutral strategies through a more integrated perspective and multi-scenario comprehensive analysis. Therefore, In the future, Hebei Province should establish a platform for carbon emissions monitoring and carbon footprint assessment, and set up an early warning and assessment mechanism for carbon peaking, so as to prevent a rebound trend in carbon emissions after peaking. At the same time, it should introduce and develop carbon capture and conversion technologies and promote the low-carbon transformation of the industrial and energy sectors, thereby forcing the early realization of peak carbon. Pay attention to the role of forestry resources in carbon neutrality, increase carbon sink resources such as forests and wetlands, promote the development of CCUS, and enhance the implementation of the policy. [ABSTRACT FROM AUTHOR]

To promote the realization of the "dual carbon target", the implementation of rooftop distributed photovoltaic (RDPV) projects in the whole county will usher in large-scale development in China. However, comprehensive investigations into the economic benefits of RDPV projects in the whole county are still rare. This paper thus aims to evaluate the economic benefits of RDPV projects when considering multiple factors. The net present value (NPV), internal rate of return (IRR) and payback period (PBP) were used to analyze the financial feasibility of RDPV projects. The particle swarm optimization (PSO) algorithm was adopted to optimize the economic benefits of RDPV projects by calculating the different installation ratios of different building types, including industrial and commercial buildings, government buildings, public buildings, and residential buildings. A case study verified the feasibility of the optimization model of the economic benefits of RDPV projects in the whole county in China. The results revealed that the self-use ratio of power generation greatly impacted the economic benefits of RDPV projects and a single RDPV project became economically feasible when the self-use ratio of power generation was greater than 87.753%. When considering the limitations of the self-use ratio of power generation, installed capacity, and grid connection mode of different building types, compared to the single RDPV project, the economic benefits of RDPV projects on a county scale were not financially feasible based on the optimization model, which had an NPV of about −10.35 million yuan. Industrial and commercial buildings had the highest proportion of RDPV systems installed among the four building types, while residential buildings had the lowest proportion. The current results demonstrate the economic benefits of RDPV projects in the whole county, which will promote the development of RDPV projects and reduce carbon emissions in China. Therefore, this study is expected to provide investors of RDPV with recommendations for both decision-making and making scientific plans for the government. • This paper aims to evaluate economic benefits of RDPV projects in a whole county when considering multiple factors. • Self-use ratio of power generation greatly effects RDPV projects' economic benefits. • Maximizing the use of roofs can improve RDPV projects' large-scale effects. • Installing RDPV on industrial and commercial building has good economic benefits. • Investing in RDPV systems on residential buildings needs for caution. [ABSTRACT FROM AUTHOR]

The contact band on the wheel and rail is an intuitive representation of the wheel–rail contact relationship that affects the dynamic performance of rail vehicles. In this paper, a vehicle dynamics model and the Archard wear model are established in an integrated way using the actual parameters of a metro train. The mechanism of formation of double contact bands on the wheel and rail in a metro line in China is studied by analysing the geometric combination based on the measured data. The influence of double contact bands on the dynamic performance of the metro vehicle is investigated. To suppress the formation of double contact bands, an optimisation method for asymmetric rail profiles in small radius curves is proposed based on the Kriging Surrogate Model (KSM) and the Particle Swarm Optimisation (PSO) algorithm. Through numerical simulations, it is proved that the optimised rail profiles can improve the curving performance and effectively reduce wheel wear. The methodology proposed in this paper can provide useful information on the mitigation of severe double contact bands on wheel and rail. • Double contact bands were found on wheel and rail profiles in a metro line. • Formation mechanism is explained by geometric contact analysis and wear simulation. • Two-point contact on sharp curves induces double contact bands. • Asymmetric rail profiles optimisation is proposed to mitigate double contact bands. • Optimisation uses Kriging surrogate model and particle swarm algorithm. [ABSTRACT FROM AUTHOR]

• An interval sequence prediction method for power generation is proposed. • The new matrixed grey model can be applied to different interval sequences. • Parameters are estimated by combining Particle swarm optimization algorithm and Ordinary Least Square method. • The new model has higher prediction accuracy compared with four competing models. • Intervals of different types of power generation in China are predicted. Development trends of power generation sequences have nonlinearity and uncertainty. The nonlinearity can be reflected by the nonlinear grey Bernoulli model. The uncertainty can be reflected by the interval sequence. A matrixed nonlinear grey Bernoulli model based on interval sequences is proposed in this paper. In order to make the model directly applicable to interval sequence, the traditional grey Bernoulli model is linearized by power function transformation, then the parameters are matrixized, and finally the recursive prediction formula is obtained by Cramer's law. Particle swarm optimization algorithm is used to estimate the nonlinear parameter. By adjusting the parameter, the new model can be used to predict exponential, saturated and parabolic interval sequences. The new model is used to predict the intervals of China's thermal power, hydro power, nuclear power, wind power, national power generation and power generation in east China. The prediction results show that the new model has higher prediction accuracy than the competing models. Finally, the power generation of four modes and national power generation from 2022 to 2025 are predicted and analyzed. [ABSTRACT FROM AUTHOR]

• A measurement campaign on the wheel profile evolution of a metro train was conducted. • This paper converts the wheel wear model calibrating problem into an optimization problem. • The RBF-PSO method is proposed to calibrate the Archard-local model. • The calibrated wear model can roughly estimate the wheel wear of similar metro vehicles. The accuracy of physics-based wheel wear prediction approaches depends not only on the vehicle-track dynamics model but more importantly on the wear model. The currently available wear models, however, were developed for specific wheel/rail materials and under fixed operational conditions, and they need to be calibrated when used in new operational conditions. In this paper we introduce a data-driven approach into the physics-based approach to automatically calibrate the existing wear model so that it can be extended to a new operational scenario. Specifically, based on a one-year follow-up measurement data on the wheel profile evolution of a metro train commuting on a Guangdong metro line, we introduce radial basis function (RBF) and particle swarm optimization (PSO) to determine the boundary of each wear regime and the wear coefficient for each wear regime in the Archard-local model. Finally, we present a calibrated Archard-local model and then apply it to two cases. One application case shows that the calibrated model can be used for long-term wear prediction and another case shows that the calibrated model can be used to roughly estimate the wear evolution over the tread region of vehicles operating on other China metro lines. [Display omitted] [ABSTRACT FROM AUTHOR]

Abstract Global climate change is a significant environmental problem. A major trigger of climate change is the excess carbon emissions. Based on 44 scenarios in the second generation of new dry cement technology systems, this paper establishes IPSO-BP model to forecast the carbon emissions peak of China's cement industry for 2016–2050 years. The results indicate that China's cement industry only implements capacity reduction plans and the second generation of new dry cement technology systems, so that carbon emissions can reach the peak before 2030. It is up to 19 years ahead of the carbon emissions peak of the basic scenario and the carbon emissions peak is reduced by 38 Mt. Moreover, this paper analyzes the technical combination of the earliest carbon emissions and the lowest carbon emissions. As for the earliest carbon emissions technical combination, China's cement industry carbon emissions will peak at 789.95 Mt in 2021. According to the lowest carbon emissions technical combination, China's cement industry carbon emissions will peak at 742.37 Mt in 2025. Accordingly, the conclusions will be helpful for making carbon emissions reduction policies for China's cement industry. Highlights • Carbon emission levels were reviewed from industrial output and technologies. • The prediction model of carbon emissions was built with improved PSO and BPNN model. • The scenarios were set to analyze carbon emission peak in China's cement industry. • Importance of technique and capacity reduction in China's cement industry is defined. • The best carbon emission peak plan for China's cement industry is discussed. [ABSTRACT FROM AUTHOR]

Natural gas, as a clean and low-carbon energy resource, assumes a vital role in facilitating the transformation of the Chinese energy structure. Effectively forecasting its consumption holds great practical implications for the high-quality social development of China. Therefore, a hybrid model for forecasting natural gas consumption (NGC) in China is developed in this paper. Firstly, the Logarithmic Mean Divisia Index (LMDI) method is adopted to decompose the influencing factors of the NGC in China from 1994 to 2020, which revealed that the energy structure effect and the economic development effect have a positive promotion on NGC, while the energy intensity effect manifests a significant inhibition. Subsequently, based on the contribution rate of each factor, the particle swarm optimization (PSO) algorithm to optimize the long and short-term memory neural network (LSTM) model is constructed for NGC forecasting. Compared to other benchmark models, the PSO-LSTM model demonstrated a significant improvement in predictive accuracy, showcasing its valuable application in NGC prediction. Finally, the PSO-LSTM model is employed to analyze the scenario prediction of NGC development from 2021 to 2035. The forecast result indicated that the future NGC in China will show a yearly growing trend, which may lead to a serious imbalance between the supply and demand of natural gas, so the Chinese government should fully consider the energy security issue when formulating relevant policies. • The LMDI method is applied to decompose the factors of natural gas consumption. • The energy consumption structure and economic development positively promote NGC. • The energy intensity effect negatively inhibits the development of NGC. • Scenario analysis of NGC is performed by constructing a PSO-LSTM model. [ABSTRACT FROM AUTHOR]

Reducing the membrane thickness of Proton exchange membrane (PEM) electrolyzer was found to efficiently promote the hydrogen production rate. However, it can also aggravate the phenomenon of hydrogen permeation, leading to an increased hydrogen content on the anode side and posing a risk of explosions. Thus, optimal design of the membrane thickness of PEM electrolyzer systems is crucial to ensure both safe and efficient hydrogen production. In this paper, we propose two optimization problems for the membrane thicknesses, aiming at achieving a balance between the hydrogen content on the anode side and the hydrogen production rate under constant and varying power input conditions. First, the theoretical model of a PEM electrolyzer is established, and a photovoltaic-PEM electrolyzer system is considered to provide varying power input conditions. Then, the two optimization problems are formulated and resolved using the sequential quadratic programming (SQP) and particle swarm optimization (PSO) algorithms, respectively. Our results reveal that the optimal membrane thickness decreases as the constant input power increases. This suggests that high/low power inputs require thin/thick membranes. For varying power input, we collected one year of solar radiation intensity data from four different regions in China. The findings demonstrate that the selection of the optimal membrane thickness depends not only on the average solar radiation intensity but also on its seasonal variations. By applying these strategies, we effectively optimize the membrane thickness in PEM electrolyzer systems, thereby enhancing the efficiency and safety of hydrogen production. The outcomes provide valuable insights for selecting the appropriate membrane thickness in regions with varying solar radiation intensities and accounting for seasonal variations in solar radiation. • Optimizing membrane thickness balances hydrogen production and permeation. • Two optimizations address constant and varying power inputs practically. • Algorithms (SQP, PSO) efficiently optimize membrane thickness. • Solar variations guide optimal membrane selection for diverse regions. [ABSTRACT FROM AUTHOR]

Coal structure is closely related to microscopic and macroscopic properties of coal, and its accurate identification is of great significance to coalbed methane (CBM) reservoir evaluation, hydraulic fracturing performance and production efficiency prediction. The identification of coal structure based on geophysical logging data has become a popular topic as well as a challenge. The emerging Machine Learning (ML) provides convenience for this issue. Under this background, in the case of the Shanxi Formation No. 3 coal seam and the Taiyuan Formation No. 15 coal seam in Mabidong Block, Qinshui Basin, China, this paper proposed a new coal structure identification method based on geophysical logging data using Wavelet Transform (WT) and Particle Swarm Optimization Support Vector Machine (PSO-SVM) algorithms. Our results showed that the vertical resolution of logging data can be effectively improved when sym5 wavelet basis and third level decomposition were selected in wavelet decomposition, and 4.5 was selected as the weighting coefficient in wavelet reconstruction. The coal structure prediction model based on the logging data processed by WT was established by PSO-SVM algorithm, where PSO was used for parameter optimization (optimal penalty factor C and width parameter σ) and SVM with Radial Basis Function (RBF) kernel was used for model establishment. The Hold-out Cross Validation (HO CV) method was used to test the generalization ability of the prediction model, and the accuracy (ACC) of coal structure prediction in the training set and testing set was 94.26% and 88.46%, respectively. The prediction model was applied to identify the coal structure of two coring wells and the predicted coal structure class was consistent with the true coal structure class, confirming the validity of the model. The coal structure prediction results in the whole study area showed that the tectonic conditions control the coal structure. This work provides new insights for coal structure identification. • A new coal structure identification method based on geophysical logging data was proposed. • The vertical resolution of logging data was improved based on Wavelet Transform (WT). • The coal structure prediction model was established based on Particle Swarm Optimization Support Vector Machine (PSO-SVM). [ABSTRACT FROM AUTHOR]

• A hybrid prediction system is proposed to provide technical support for achieving energy sustainable development goals. • Extract original complex time series features using CEEMDAN. • Optimize Extreme Learning Machine using particle swarm optimization algorithm. • Experiments are conducted for four seasons of wind speed to verify that the model can effectively predict year-round data. • Experiments demonstrate that CEEMDAN-PSO-ELM can predict complex energy data efficiently and accurately. As environmental concerns and the energy crisis intensify, advancing the use of new energy sources such as wind and photovoltaic is an important means to achieve sustainable energy development. However, the random fluctuation characteristics and seasonality of wind and light make them difficult to predict, which brings many operational risks to grid security and power dispatch. Therefore, this paper uses the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) as the decomposition algorithm, which can effectively avoid the problems of modal confusion and noise residuals and better identify the trend, seasonality and nonlinear characteristics of the series. The Particle Swarm Optimization (PSO) algorithm is also utilized to improve the prediction accuracy and stability of the Extreme Learning Machine (ELM). Combining CEEMDAN and PSO-ELM models, a high-precision hybrid forecasting system that can effectively reduce the effects of stochastic fluctuations is proposed. In this paper, wind speed data from four different seasons at Changma wind farm in China are selected to verify the effectiveness and generalization ability of this hybrid prediction system. The results show that the improvement of ELM by PSO and CEEMDAN significantly improves the prediction accuracy of the model, and the hybrid prediction system can be applied to time series with different data characteristics and variation patterns in each season, and its prediction accuracy and model performance are significantly better than other comparative models. [ABSTRACT FROM AUTHOR]

The first-order grey model is appropriate for monotonic time series, while the grey Verhulst model is appropriate for periodic time series. The grey Verhulst model is widely used for predicting practical nonlinear time series that contain fluctuations. Despite the successful application of the grey models in practice, researchers show that grey models still have room for improvement. Moreover, recent research shows that grey models are sensitive to initial conditions. In many practical problems, the value of initial conditions is not accurate and suffers from noise or approximation errors, resulting in inaccurate prediction. To address these difficulties, an improved grey Verhulst method using particle swarm optimization is proposed in this paper. The proposed model consists of two stages. In the first stage, a second-order polynomial with unknown coefficients is used to approximate the 1- AGO. In the second stage, the initial element of the time series is modified to improve the accuracy of the prediction. The particle swarm optimization method is used to search for the unknown coefficients. It is found that PSO is a suitable optimization method for the proposed method because it is stable and generates a sequence of points that converges to a globally optimal solution. To demonstrate the efficiency and stability of the proposed method, it was applied to five practical problems, namely, gas production in China, the number of hazardous chemical accidents, CO2 emissions in Russia, the number of domestic tourists in China, and traffic flows in Canada. Numerical results show that the method is more accurate and robust than existing methods. • The proposed method needs only four elements for predicting the future elements of time series. • The paper proposes a second order polynomial for approximating 1-AGO. • The method makes more accurate prediction than existed methods. • The proposed method is applied on various practical forecasting problems successfully. [ABSTRACT FROM AUTHOR]

• Four time-delay weights structural types are designed by the grey incidence model. • The novel multivariable grey prediction model considering the time-delay periods and time-delay weights is proposed. • The accumulating impact of influencing factors on CO 2 emissions of China's transport sector is measured. CO 2 emissions from the transportation sector occupy an increasingly important proportion in China's carbon dioxide emissions. Measuring the accumulative impact of factors on carbon emissions over time is of great significance for formulating corresponding policies. This paper aims to propose a novel time-delay multivariate grey model to measure the CO 2 emissions' accumulating impact of China's transportation sector. Firstly, the grey incidence model is used to identify time lags between the input and output variables, and also analyze the structure type of time-delay weights. Then, an accumulative time-delay multivariate grey prediction model is developed. In this model, a Gaussian formula is used to discretize the convolution integral of the time response function, and the particle swarm optimization algorithm is employed to determine the optimal weight coefficients. Finally, a case for CO 2 emissions prediction is adopted to test the effectiveness and practicality of this model compared with the alternative models. The results show that the proposed model outperforms other six competing models in accordance with two measuring indices, and suggestions on emissions mitigation are proposed based on the prediction results. [ABSTRACT FROM AUTHOR]

• Analyzed the distribution principle of disturbance power in different regions, and was able to obtain the unbalanced power of the system based solely on disturbance region data. • Particle swarm optimization (PSO) and LSTM is introduced to obtain the error between the calculation result of the multi region frequency response model (RFR) model in disturbance region and the real value, Then, in order to improve the integrity and interpretability of the model, the model-based method and the data-driven method are integrated through a parallel scheme, and the final result is the superposition of the two methods. • An active load shedding control strategy based on TFSI prediction results in the disturbance region is proposed. This strategy can perform load shedding operations in the disturbance region in advance before the frequency reaches the load shedding threshold, and can quickly prevent frequency drops to achieve smaller frequency deviations. With the expansion of power grid scale, the online prediction and control of transient frequency is very important for the system security. Some known and unknown factors are ignored in traditional prediction analysis methods based on physical model, which leads to the inevitable error in calculation results. This paper proposes a model-data integration driven method for transient frequency prediction. In the model part, a multi region frequency response model was established, and the disturbance region was considered as the weak link of system frequency variation from the spatial dimension. In the data-driven part, the long short-term memory network based on particle swarm optimization is used to obtain the error between the calculated results of the model-based method and the truth value, and the model-based method and the data-driven method are integrated through the parallel mode. The final transient frequency security indicators result is the superposition of the calculated results of the two methods. Based on the TFSI prediction results, an active load shedding control strategy was constructed, which can act before the traditional load shedding frequency threshold. The performance of TFSI prediction and active load shedding control was verified on the modified New England 10-generator 39-bus system and 197-bus system in China. The TFSI prediction results show that the proposed method is more accurate and faster than other integration methods, and it is robust in both data loss and unknown scenarios. And, the constructed active load shedding control strategy has better frequency dynamics compared to traditional load shedding strategies based on fixed frequency thresholds. [ABSTRACT FROM AUTHOR]

Ensuring food quality and safety is essential after ensuring the quantity of food. Therefore, an improved adaptive particle swarm optimization algorithm (IAPSO) for optimizing the long short-term memory (LSTM) neural network (IAPSO-LSTM) is proposed to develop a food safety risk early warning model in this paper. The proposed IAPSO algorithm is verified by comparing with the traditional PSO (TPSO), the classic PSO (CPSO), the adaptive PSO (APSO) and the deterministic and adaptive PSO (DAPSO) based on five common benchmark functions in terms of the convergence speed and precision. Results show that the IAPSO algorithm has the best convergence speed and precision. Then, the analytic hierarchy process based on the sum product is used to obtain the risk value of food safety detection data, which is used as the desired output of the LSTM. And the root mean square error of the predicted risk value and the real food risk value is used as the objective function of the IAPSO algorithm to optimize the hyperparameters of the LSTM. Finally, the food safety risk early warning model based on the IAPSO-LSTM is evaluated using the composite seasoning detection data from a food testing agency in Guizhou Province, China. The proposed model effectively identifies high-risk factors affecting the risk value, with sodium cyclamate being the primary high-risk factor. The overall performance of the IAPSO-LSTM model is superior to that of the TPSO-based LSTM, the CPSO-based LSTM, the APSO-based LSTM, the DAPSO-based LSTM and the IAPSO-BP, with the prediction error of 0.474, R2 value of 0.998 and the absolute error less than 5. Moreover, the proposed model can help the relevant government departments effectively warn the potential food safety risks to ensure the food safety. [ABSTRACT FROM AUTHOR]

• Modeling artificial upwelling efficiency under crossflow. • Optimized nozzle layout improves upwelling efficiency. • Discrete particle swarm algorithm enhances carbon sequestration. • Increasing nozzles will improve performance, but raises investment cost. • Reference for engineering design of artificial upwelling. Artificial upwelling (AU) is widely recognized as a geoengineering tool to enhance oceanic fertility and stimulate the earth's capability of self-healing. Several air-lifted AU systems have been established to promote seaweed growth and facilitate carbon sequestration, for instance, in Norway and China. However, few researchers have addressed the critical issue of optimizing the layout of the underwater nozzle array (UNA), a key component of the air-lifted AU system. In this paper, we propose a novel method to optimize the layout of UNA by introducing and improving the discrete particle swarm optimization (DPSO) algorithm to guide the optimal nozzle positions. Furthermore, we develop the nutrient transport efficiency model to evaluate the performance of the AU system and apply it to investigate a typical AU system, namely the one in Aoshan Bay, China. Our results demonstrate that the proposed DPSO algorithm outperforms the conventional particle swarm optimization algorithm and the nutrient transport efficiency under the optimized UNA layouts was improved by an average of 14.5% to 35.0% compared to randomly generated layouts. These findings suggest that our optimization method could serve as a scientific reference for the engineering design of AU. [ABSTRACT FROM AUTHOR]

In this paper, a tramway's system model is established to evaluate its longitudinal dynamics performance, where the model includes multiple masses point connecting together powered by the catenary and a hybrid energy-storage system which consists of a battery pack and ultracapacitor pack. To explore an optimal or appropriate real-time power distribution among these energy sources, a dual fuzzy logic control-based energy management strategy combined with wavelet transform and multi-objective optimization is proposed. The control parameters of the dual fuzzy logic controller are adjusted using a multi-objective particle swarm optimization algorithm while considering the daily operating cost of the tramway. To verify the effectiveness and validity of the proposed model and energy management strategy, its simulation results are further compared and verified with the field experimental results of a real tramway and a real driving cycle in China. • A improved simulation model is presented for a multi-sources hybrid tramway. • A optimal strategy combined with fuzzy logic, wavelet transform and PSO is proposed. • The dual fuzzy logic controller is optimized by multi-objective PSO algorithm. • The strategy shows lower tramway daily operating cost and better energy efficiency. [ABSTRACT FROM AUTHOR]

Energy consumption is an international issue and plays an important role in the national energy security, especially for China of which the energy market is in transition. Accuracy and trustable forecasting of future energy consumption trends with nonlinear data sequences is very important for the decision makers of governments and energy companies. In this paper, a novel nonlinear grey Bernoulli model with fractional order accumulation, abbreviated as FANGBM(1,1) model, is proposed to forecast short-term renewable energy consumption of China during the 13th Five-Year Plan (2016–2020). The new model is discussed in details with the fractional accumulated generating matrix and the Bernoulli equation. Further, the Particle Swarm Optimization algorithm is used to search optimal system parameters. Based on the updated real-world data sets from 2011 to 2015, the FANGBM(1,1) model is established to forecast the total renewable energy consumption, hydroelectricity consumption, wind consumption, solar consumption, and consumption of other renewable energies, respectively. The FANGBM(1,1) model presents high accuracy in all cases and is also proved to be efficient to deal with nonlinear sequences. [ABSTRACT FROM AUTHOR]

Natural gas has been widely promoted by Chinese government as a clean energy source due to its odorless and smokeless combustion process. As an important part of urban natural gas supply, coal bed methane (CBM) accounted for 3.4% of the China's total natural gas production in 2017 and had an increase of 9.2% year-on-year compared with last year. In response to government promotion and so as to maintain the steady production of CBM, some enhancing-production approaches have been taken in CBM fields, and one of the effective approaches is the installation of compressors in gathering networks. However, due to the complexity of CBM gathering networks, the pressurization scheme lacks guidance in practice and is mainly decided by experience. To guide the practical production process, this paper proposes a mixed-integer nonlinear programming (MINLP) model to optimize the pressurization scheme. The MINLP model considers the cost of facilities and electricity and maximizes the daily net profit of CBM field companies. Then, a two-stage improved genetic algorithm-particle swarm optimization algorithm is proposed to solve this problem. Finally, the model is applied to a real CBM field with 132 production wells, 10 manifolds and 1 central processing facility (CPF) in China. The result shows that the optimal scheme can increase the total production from 3.39 × 105 m3/d to 3.73 × 105 m3/d with a growth rate of 10.0%, and the daily net profit increases 2.49 × 104CNY/d (about 3.70 × 103USD/d). • An MINLP model for optimizing the pressurization scheme in CBM fields is established. • A tailored two-stage iGA-PSO algorithm for solving the MINLP model is proposed. • A real CBM field in China is studied to validate the effectiveness of the model and algorithm. [ABSTRACT FROM AUTHOR]

• A virtual real-time electricity price optimization model based on the credit mechanism is established. • Incorporate the balancing cost of electricity and the stability cost of the grid into the cost of electricity production. • A matching degree index is proposed. Intermittence and fluctuation of renewable energy increase the cost of real-time balance of power supply and demand, which will affect the stability of the power grid. How to design the incentive mechanism to increase the flexibility of the distributed energy system and reduce the cost of real-time supply–demand balance is an urgent problem to be solved. In this study, from the perspective of the demand side actively matching the supply side, a virtual real-time electricity price optimization model based on the credit mechanism is proposed. We use the linear decreasing inertia weight particle swarm optimization algorithm to optimize the user's electricity price and realize the minimization of the total electricity cost. The influence of the virtual real-time electricity price incentive mechanism on the matching degree between the power load curve and the distributed energy output curve is also studied. Moreover, a novel index is put forward to quantitatively measure the matching degree between users' power load curve and distributed energy output curve. Taking a multi-microgrid system in a China's industrial park as the case, we have found the results that the virtual real-time electricity price optimization model can not only reduce users' total power cost by 7.8108%, but also improve the matching degree between the demand side and the supply side by 2.4643%. The new demand response incentive mechanism we have presented in this paper may promote the effective utilization of distributed energy and reduce the impact of renewable energy on power grid. [ABSTRACT FROM AUTHOR]

• Combined with the error reconstruction rate, an adaptive VMD technology is developed and used for data preprocessing. • Two mainstream deep learning methods (LSTM, DBN) are used as sub-series predictors, and the classic PSO algorithm is utilized to determine the number of neurons in the DBN network. • A novel hybrid prediction model based on the PSO-DBN nonlinear combination mechanism is proposed. Wind power forecasting plays a vital role in enhancing the efficiency of power grid operation and increasing the competitiveness of power market. In this paper, a novel hybrid forecasting model is developed by using the decomposition strategy, nonlinear weighted combination, and two deep learning models to overcome the drawbacks of the linear weighted combination and further enhance wind power forecasting accuracy and stability. Firstly, the variational mode decomposition (VMD) technique is employed to decompose the original wind power series to extract local features. Then, the long short-term memory neural networks (LSTM) and deep belief networks based on particle swarm optimization (PSO-DBN) are utilized to construct sub-series prediction models. Finally, the multiple sub-series forecasting models are integrated by a nonlinear weighted combination method based on PSO-DBN to construct a hybrid model for short-term wind power forecasting. To verify the performance of the developed forecasting model, wind speed data of 10 min from a wind farm in Shaanxi Dingbian, China are selected as case studies. The results show that the proposed method in this paper is more effective than other existing methods. [ABSTRACT FROM AUTHOR]

The coordinated control systems (CCS) in ultra-supercritical thermal power unit, like many other industrial systems, is a complex multivariable system with severe nonlinearity, strong multivariable coupling and uncertainties. In order to meet the requirements of operational stability, economy. etc in ultra-supercritical unit, it is necessary to establish its accurate mathematical model and further design the advanced controller. Against this background, a new fuzzy neural network modeling method is proposed in this paper. First of all, the incremental model is considered separately to improve the rationality of the local linear model structure. Then, the parameters in antecedent part is initialized by a kernel k -means++ algorithm, in which Xie-Beni index is used to optimize the number of fuzzy rules. Finally, supervised adaptive gradient descent algorithm and artificial immune particle swarm optimization algorithm work in stages to complete the training of the consequent part parameters. The proposed modeling method in this paper is applied to a 1000 MW unit in China and shows satisfactory accuracy. In the established model, the MSE of power output, main steam pressure and separator outlet steam temperature are 0.0099, 1.21E-4, 0.0023, respectively. Both numerical and graphical simulation results confirm the effectiveness of the presented fuzzy neural network in modeling. [ABSTRACT FROM AUTHOR]

Abstracts Amid growing and progressive reform of incremental distribution business in China, the potential confrontation of the retailers and consumers has driven the necessity to study the transaction mechanism and interest equilibrium in the incremental distribution area. In this paper, a transaction mechanism among various retailers and consumers in the regional energy market is designed. And based on the characteristics of retailers and consumers, the revenue of these market participants are formulated considering consumers' satisfaction and integrated demand response (IDR). The problem is formulated as a two-leader and two-follower Nash-Stackelberg game among them, which is built with the strategy set of energy prices and consumption patterns. The proposed game is proved the existence and uniqueness of equilibrium under classical game theory, and solved by distributed algorithm through improved particle swarm optimization algorithm with constraints. Finally, an example study of the model is presented to verify the increase of revenue under the established market transaction mechanism, where the revenue of two kinds of retailers increases by 17.8% and 10.9% respectively as well as consumers' revenue increasing by 21.7% and 12.3%. In addition, sensibility analysis of the factors like compensation prices, market share of retailers and price elasticity of consumers are carried out. Highlights • The transaction mechanism in the regional energy market is designed specifically. • The two-leader and two-follower Nash-Stackelberg game model is proposed. • A distributed optimization algorithm is proposed to determine the game equilibrium. • The reasonable compensation prices can increase the revenue of overall participants. [ABSTRACT FROM AUTHOR]

The PM 2.5 is the culprit of air pollution, and it leads to respiratory system disease when the fine particles are inhaled. Therefore, it is increasingly significant to develop an effective model for PM 2.5 forecasting and warnings that informs people to foresee the air quality. People can reduce outdoor activities and take preventive measures if they know the air quality is bad ahead of time. In addition, reliable forecasting results can remind the relevant departments to control and reduce pollutants discharge. According to our knowledge, the current hybrid forecasting techniques of PM 2.5 do not take the meteorological factors into consideration. Actually, meteorological factors affect the concentrations of air pollution, but it is unclear whether meteorological factors are helpful for improving the PM 2.5 forecasting results or not. This paper proposes a hybrid model called CEEMD-PSOGSA-SVR-GRNN, based on complementary ensemble empirical mode decomposition (CEEMD), particle swarm optimization and gravitational search algorithm (PSOGSA), support vector regression (SVR), generalized regression neural network (GRNN) and grey correlation analysis (GCA), for the daily PM 2.5 concentrations forecasting. The main steps of proposed model are described as follows: the original PM 2.5 data decomposition with CEEMD, optimal SVR selection with PSOGCA, meteorological factors selection with GCA, residual revision by GRNN and forecasting results analysis. Three cities (Chongqing, Harbin and Jinan) in China with different characteristics of climate, terrain and pollution sources are selected to verify the effectiveness of proposed model, and CEEMD-PSOGSA-SVR*, EEMD-PSOGSA-SVR, PSOGSA-SVR, CEEMD-PSO-SVR, CEEMD-GSA-SVR, CEEMD-GWO-SVR are considered to be compared models. The experimental results show that the hybrid CEEMD-PSOGSA-SVR-GRNN model outperforms other six compared models. Therefore, the proposed CEEMD-PSOGSA-SVR-GRNN model can be used to develop air quality forecasting and warnings. [ABSTRACT FROM AUTHOR]

The paper designed an information integration system for prediction of the spontaneous combustion in the coal stockpile, which is characterized by real-time data acquisition, temperature cloud field formation and parameter prediction via ZigBee wireless network and industrial laser scanner, along with the ABC-MGM(1,1) hybrid model of the moving GM(1,1) and Artificial Bee Colony (ABC) algorithm. In order to enhance the short-term prediction accuracy, a moving GM(1,1) (MGM) scheme has been provided by constantly modifying the data input; and the generation coefficient of MGM(1,1) model has been optimized by ABC algorithm. • Direct sensing and prediction method is provided to prevent spontaneous combustion. • Multilayer Zig-bee sensor network is designed to facilitate acquisition of parameters. • A novel grey prediction model is proposed based on GM(1,1) and ABC algorithm. • Better performance for hazard control is achieved in large Power plant in China. Spontaneous combustion of coal can lead to serious environmental pollution, safety hazards and huge economic losses. Hazard prevention and environmental protection requires effective monitoring network and efficient prediction methods. To acquire the real-time data of coal parameters we designed multi-layered Zig-bee based wireless sensor network. The shape of the coal pile is formed by the industrial laser scanner followed by the formation of 3D temperature point cloud field via Kriging interpolation. Afterwards, an integrated evaluation indicator Heat Loss Capacity (HLC) is proposed, which synthesizes various factors inducing spontaneous combustion. The real-time and high accurate HLC prediction is realized by using metabolic method to update the raw sequence of the GM(1,1) grey prediction model in cycle with the latest acquired sensor data. Finally, a hybrid model ABC-MGM(1,1) combining the ABC optimization algorithm with the metabolic GM(1,1) model is proposed. Experiment shows that the ABC-MGM(1,1) model has better performance in parameter optimization as well as HLC prediction, especially for short-term prediction. The proposed method has been utilized to predict spontaneous combustion of the stockpiled coal in Xutang power plant of China. The timely parameter acquisition by 25 Zig-bee nodes and effective prediction by the proposed model shows great practicability in safety and hazard prevention. [ABSTRACT FROM AUTHOR]

This paper develops an MILP model for designing multi-period natural gas transmission network to determine the connections of pipeline and the sites of compressor stations with consideration of terrains and obstacles. Equations of mass balance of network nodes, pressure drop of pipelines and pressure increase of compressors are all taken into account. A piece-wise linearization method is applied to the model. Four cases of natural gas transmission networks in Shanxi province (China) are studied. The result illustrates that the model can tackle complicated natural gas transmission network optimization problems. The developed model is of practical value for natural gas sales enterprises to minimize the construction cost and is a good designing reference for construction contractors. [ABSTRACT FROM AUTHOR]

• A LapSVM-based semi-supervised method is proposed for coal structure identification to address limited labeled-data issue. • Experiments show the LapSVM is efficient in coal structure identification using few labeled logging data. • Comparison indicates the LapSVM outperforms traditional SVM with improved classification accuracy and generalization ability. Coal structure is a critical parameter in coalbed methane (CBM) development due to its significant impacts on methane enrichment, fluid flow and hydraulic fracturing. Traditional statistical analysis and data-driven machine learning methods for coal structure identification are highly dependent on the labeled logging data and have potential limitations when labeled logging data is limited. To address this issue, this paper proposed a semi-supervised learning method based on Laplacian support vector machine (LapSVM) to identify coal structure by using few labeled logging data. By mining the structure information from abundant unlabeled data, LapSVM can improve the model performance and alleviate the over-reliance on labeled data. To evaluate and verify the effectiveness and reliability of the proposed LapSVM method in coal structure identification, datasets collected from 32 CBM wells in the southern Qinshui Basin, China, are utilized in this study. The particle swarm optimization (PSO) is adopted for parameter optimization of LapSVM models. For the LapSVM model, the addition of unlabeled data is conducive to enhance model accuracy, and unavoidably increases the computational cost at the same time. The comparison of training, testing and blind-well test results between the LapSVM and standard support vector machine (SVM) models indicates that the LapSVM outperforms traditional SVM and possesses higher accuracy and generalization in coal structure identification. It has been demonstrated that the LapSVM can be a reliable tool for coal structure identification when limited labeled logging data is available. [ABSTRACT FROM AUTHOR]

• A two-layer optimization frame to estimate and improve the net profit of BESSs in the whole life cycle. • The semi-empirical degradation model of lithium-ion batteries and economic models of BESSs are embedded into the optimization frame. • The optimization frame applies to different lithium-ion batteries. • The optimal configuration and operation varied from the types of lithium-ion batteries. Battery energy storage systems (BESSs) have been widely employed on the user-side such as buildings, residential communities, and industrial sites due to their scalability, quick response, and design flexibility. However, cell degradation is caused by the charging and discharging of batteries, which reduces the economy of BESSs. For the optimal configuration and operation of BESSs, the battery degradation process should be integrated into the optimal problem by considering the equivalent full cycles over the optimization time horizon. This paper proposes a two-layer optimization frame to estimate and improve the net profit of BESSs in the whole life cycle, the outer layer optimizes the rated capacity and power of BESSs, and the inner layer optimizes the daily operation strategy of BESSs. To this end, the semi-empirical degradation model of lithium-ion batteries and economic models of BESSs are embedded into the optimization frame. Particle swarm optimization (PSO) algorithm and fmincon toolbox of MATLAB are adopted to solve the two-layer frame to maximize the net profit of BESSs. Simulation results of the BESS for a typical industrial user in China demonstrate that the proposed frame can effectively improve the net profit of BESSs. [ABSTRACT FROM AUTHOR]

The construction of smart grid is inseparable from the appropriate deployment of utility poles. China has many poles; if they are fully utilized, can they bring more power to the smart grid? Fortunately, thanks to advances in technologies such as artificial intelligence and the Internet of Things, can we use Google Earth to recognize utility poles and optimize the deployment of power facilities? Fundamentally, Google Earth generates static images. Faced with many static images, we need further image processing for high-definition recognition of utility poles. In addition to the current chaotic distribution of poles, we also need to optimize the deployment of power facilities. However, due to the resolution of Google Earth and the aerial photography angle, many backlight phenomena are not conducive to the recognition of utility poles. Therefore, this paper proposes a backlight image enhancement algorithm based on convolutional neural networks (CNN) and constructs a novel network architecture that integrates decomposition, restoration, and adjustment to recognize poles in high-definition under backlight. Furthermore, to solve the problems of the overflow of CNN parameters and unclear training effect, particle swarm optimization (PSO), the evolutionary computing-based machine learning (ECML) is used to search CNN parameters automatically and seek the optimal solution to achieve the optimization of the overall model. The experiments prove that the CNN-based image enhancement algorithm effectively recognizes the utility poles under different illumination and backlight. At the same time, the experimental results show that the PSO-based optimization method can optimize CNN parameters obviously, and the classification accuracy is increased. • An image enhancement algorithm based on CNN for Google Earth static images is proposed for recognition of utility poles. • A novel network architecture integrating decomposition, restoration, and adjustment is constructed. • A PSO-based method is proposed to automatically tune the parameters of CNN model. [ABSTRACT FROM AUTHOR]

This paper proposes a quick response collaborative scheduling model based on Cyber-Physical Production System (CPPS) online monitoring to address the problem of quick response repair of disruption in the wheelset manufacturing of high-speed train. A Bogie Wheelset Manufacturing System-Quick response collaboration model (WS-QRC) that integrates disruption management and collaborative scheduling is established. An Enhance Neighborhood-Discrete Particle Swarm Optimization (DPSO_ENS) algorithm with extended neighborhood search structure is also designed. We take the data of a high-speed train factory in China as an example to verify the feasibility and superiority of the model and algorithm in this paper. Experimental examples have shown the supplier-led negotiation scheduling model and the improved DPSO algorithm are effective in dealing with the disruption and quick response problem during wheelset production. [ABSTRACT FROM AUTHOR]

• The modified CES function takes into account the stages of technological progress. • The improved PSO algorithm has fast convergence speed and high accuracy. • The method of calculating the contribution rate is scientific and reliable. • China's economic growth factor contribution rate is given. In the analysis of the economic growth factors, people often use the CES (constant elasticity of substitution) production function model to calculate the contribution rate of influencing factors to economic growth. However, the traditional CES production function model does not consider the period characteristic of technological progress on economic growth, so this paper puts forward a modified CES production function model. On the parameter estimation of the model, this paper presents an improved PSO (particle swarm optimization) algorithm with high precision and fast convergence. Using the modified CES production function model, this paper provides a scientific method to calculate the contribution rates of all factors influencing the economic growth. Finally, this paper performs the empirical analysis of the contribution rates of all factors influencing China's economic growth. [ABSTRACT FROM AUTHOR]

As China's environmental governance turn to a high-quality management, establishing reasonable and effective bonus-penalty mechanism is an effective means to promote coordinated emission reduction and improve regional air quality. Therefore, this paper constructs a bi-level programming model with bonus-penalty standards and emission quotas, based on the maximization of social benefits and the minimization of the gap between reward and punishment funds. Given the NP-hard problem of bi-level programming model, this work also designs a nested hierarchical particle swarm optimization (HPSO) algorithm for the above model. Subsequently, from the emission data of SO2 and macroeconomic data in the northeastern region of China from 2006 to 2015, the SO2 emission quota and bonus-penalty standards of each province are calculated. The results demonstrate that (1) the optimal emission quotas of Heilongjiang, Jilin and Liaoning province are 37.7, 30.3 and 69.3 (10,000 tons), respectively. (2) When the compensation fee of pollutant abatement is set at 521.48 yuan/ton and the standard of excess discharge levy is 2977.43 yuan/ton, the effect of pollution control in each province can be effectively improved. The empirical analysis also reveals that the proposed model has a remarkable effect on regional environmental governance. Finally, this paper puts forward some suggestions on the implementation of the bonus-penalty mechanism. • A bi-level programming model with bonus-penalty standards was developed. • This paper provides a new way to solve the same bilevel programming problem. • This paper's simulation focuses on an old industrial area. [ABSTRACT FROM AUTHOR]

The unpredictability of renewable sources of energy especially wind power causes large fluctuations in the power output. The fluctuations are smoothened by building large amounts of battery storage and/or power reserve capacity. By improving the forecasting accuracy, these reserves can be reduced. We revisit the problem of short-term wind power prediction using statistical and machine learning based modeling techniques. In prior work, we developed a fusion evaluation index to rank various forecasting models. We used eight forecasting models selected from literature and seven evaluation indexes in that study. Each evaluation index was weighted in two parts – an objective normalized weight based on maximizing deviations and a subjective (expert) weight. In this paper, we use two evolutionary optimization algorithms to optimize the objective weights of the indexes. Particle Swarm Optimization (PSO) and Differential Evolution (DE) are used to produce an optimal weight strategy for the six of the seven indexes using a training data set. The weighted objective indexes are then applied to a test dataset with promising initial results. The simulation is based on seven months of actual data from a wind farm in Shanxi province, with a sampling interval of 5 minutes. [ABSTRACT FROM AUTHOR]

• Gauss-Hermite integral based multi-point estimation method is proposed to calculate the probabilistic transient stability criterion derived through the PDSR. • To guarantee the calculation accuracy and speed at the same time, the optimal number for the sampling points is determined based on PDSR hyperplanes and improved particle swarm optimization algorithm (IPSO). • Extreme learning machine (ELM) is introduced to describe the uncertainty of practical wind power output. • Calculation accuracy of the proposed method is higher than other commonly-used point-estimation methods without much loss of computational efficiency under different wind power penetration and correlation levels. With the increasing penetration of wind power, probabilistic transient stability assessment becomes critical to deal with the uncertainties and correlations of wind power, thus improving the reliability of power system. This paper proposes an improved multi-point estimation based probabilistic transient stability assessment method. Extreme learning machine (ELM) is introduced to describe the uncertainty of practical wind power output. Gauss-Hermite integral based multi-point estimation method is proposed to calculate transient stability criterion derived through practical dynamic security region (PDSR). Optimal number of the sampling points is determined based on PDSR hyperplanes and an improved particle swarm optimization algorithm (IPSO). Test results on the New England 10-generators 39-buses system and a practical provincial power system in China show that the calculation accuracy of the proposed method is higher than that of other commonly-used point-estimation methods without much loss of computational efficiency under different wind power penetration and correlation levels. [ABSTRACT FROM AUTHOR]

• An optimization of eco-industrial structure considering economy-society-ecology. • A multi-objective optimization model meeting three dimensional objectives is built. • The hybrid ACO-PSO algorithm is applied to solve the model. • Optimized scenarios realize overall development of economic-social-ecological benefits. • The optimized scenarios with different tendencies promote different benefits. The establishment of ecological economic system has become the key to realize the transformation of China's economy from high-speed development to high-quality development. This paper considers the multiple goals of economic, social, and ecological benefits to achieve sustainable development. Firstly, it establishes an indicator system affecting economic, social, and ecological benefits to guide the construction of the subsequent model. Secondly, this study constructs a multi-objective optimization model for ecological industrial structure. According to the different emphasis of objectives, a hybrid approach based on ant colony optimization and particle swarm optimization (ACO-PSO) is implemented to solve the optimal solution set of feasible schemes. Finally, Sichuan Province is selected as the case study area, and three scenarios including economic oriented scenario, employment protection scenario and environment-friendly scenario are screened and analyzed. The results show that: (1) After reasonable optimization and adjustment of the industrial structure, it realizes the overall development of economic benefits, social benefits, and ecological benefits. The comprehensive benefits of sustainable development have been significantly improved. (2) The optimized scenarios with different tendencies promote different benefits. Decision makers can make better choices based on the diverse needs of the different development stage. [ABSTRACT FROM AUTHOR]

With the deepening of China's low-carbon energy transformation, microgrids are an essential means to promote the consumption of renewable energy. Therefore, improving the operational efficiency of microgrids is the key to promote the development of renewable energy. This paper establishes a three-layer Multi-Agent system model considering the energy storage system and power-heat load demand response based on the actual situation of China to solve the problem of microgrids energy management. In order to verify the effect of the energy storage system and demand response in microgrids, this paper designs three simulation cases, namely the underlying case, energy storage case and demand response case. In order to prove the efficiency of the proposed method, this paper applies the proposed method to solve three cases and compare the result with other meta-heuristic algorithms. The comparison results show that: (1) Multi-Agent system model can realize the collaborative optimization of 'source, grid, load, and storage.' (2) The introduction of the energy storage system and demand response in microgrids can stabilize the output of renewable energy units, promote renewable energy consumption and reduce the overall operating cost of microgrids. (3) The proposed particle swarm optimization can effectively reduce the cost and the number of iterations. • This study realizes a real-time energy management system of MG based on MAS. • This paper proves the effect of ESS and DR in MG. • This paper points out how to apply ESS and DR to MG operators. • This paper sets the stopping conditions to a chaotic process for efficiency. • Adaptive weight is added in this paper to reduce the number of iterations. [ABSTRACT FROM AUTHOR]

In this paper, a novel hybrid learning method is carried out to forecast urban air quality index (AQI). Wavelet packet decomposition (WPD) is firstly performed to decompose the original AQI data into lower-frequency subseries. Then, we improve the pigeon-inspired optimization through using the particle swarm optimization algorithm. The improved pigeon-inspired optimization (IPIO) approach is applied to optimize the initial weights and thresholds of extreme learning machine (ELM) and then the modified ELM (MELM) is employed to forecast the subseries respectively. Moreover, multidimensional scaling and K-means (MSK) clustering methods are utilized to cluster the forecasting outcomes into high frequency, medium–high frequency, medium–low frequency and low frequency subseries. Finally, MELM, as an ensemble approach, is applied to ensemble the subseries together and achieve the final results. To test the predictive precision of the proposed hybrid WPD-MELM-MSK-MELM learning method, AQI of Harbin in China is adopted to make short-term, middle-term and long-term predictions separately. Different decomposition approaches are utilized to compare with WPD, and the non-clustering hybrid model is also compared with the proposed method. The forecasting outcomes indicate that WPD is more suitable for predicting AQI and the proposed WPD-MELM-MSK-MELM learning method has better predictive performance on horizontal precision, directional precision and robustness than some existing methods and benchmark models in this paper. • A novel hybrid learning approach is presented. • Pigeon-inspired optimization is improved through using particle swarm optimization. • Extreme learning machine is modified by pigeon-inspired optimization. • Based on the multidimensional scaling and K-means clustering, the ensemble approach can enhance the predictable precision of AQI. [ABSTRACT FROM AUTHOR]

With growing attentions paid to ecological protection in recent years, the ecological operation of cascade hydropower reservoirs is becoming an increasingly significant problem in water resource system. Mathematically, the ecological operation of cascade hydropower reservoirs is a high-dimensional, nonlinear and strong spatiotemporal coupling constrained optimization problem. To overcome the premature convergence and stagnation search of traditional methods in resolving this problem, this paper develops a novel algorithm known as simplex quantum-behaved particle swarm optimization, where the probabilistic mutation operator is performed on historical best position of some individuals, and then the simplex neighborhood search strategy based on the dynamic probability identification is used to enhance the local exploration ability of the swarm. The numerical experiments of 17 classical test functions indicate that the presented method can achieve satisfactory results in both convergence speed and global search ability. The application results from China's Wu hydropower system indicate that our method has satisfying performance in reducing the ecological water shortage. Hence, this paper provides a novel effective tool for the complex ecological operation problem of cascade hydropower reservoirs. • An optimization model for hydropower system ecological operation is presented. • Simplex quantum-behaved particle swarm optimization is proposed to address it. • Nelder–Mead simplex search and mutation operator can improve swarm diversity. • SQPSO obtains satisfying results in benchmark functions and engineering cases. [ABSTRACT FROM AUTHOR]

Energy production and conversion have a significant impact on the economic development of all countries in the world. China's energy production and conversion are large. Therefore, accurate mid-to-long term China's energy production and conversion forecasting is becoming more and more important for integrating energy systems and energy strategic planning. For this purpose, a novel fractional grey sequence is proposed based on Grunwald–Letnikov fractional calculus. Furthermore, a novel self-adaptive fractional multivariable grey model is proposed based on the novel sequence. In this article, we compare several classical optimization algorithms and finally choose Particle Swarm Optimization (PSO) to compute the parameters. In addition, Monte-Carlo simulation and probability density analysis (PDA) are presented in this article to verify the model's performance. Monte-Carlo simulation reduces the randomness of the results of the model runs to a certain extent. Probability density analysis visualizes this randomness through kernel density estimation (KDE). This paper compares the new model with the existing seven grey models and predicts the total energy consumption per capita, energy conversion efficiency and total renewable energy in China, respectively. The experimental results show that the new model is superior to the other seven models in terms of stability and prediction accuracy. [ABSTRACT FROM AUTHOR]

Reliable output forecasts are critical for decision-making and planning in high-tech industries. Several endogenous and exogenous factors could influence the output dynamics, and thereby a univariate model that only incorporates historical data and single method improvement is typically insufficient to generate accurate projections. In this paper, a novel grey multivariable convolution model is designed from a collaborative optimization perspective. The core innovations of this study can be summarized as follows. Initially, a collaborative framework integrating background value optimization, data preprocessing, and model structure improvement is constructed, which overcomes the internal deficiencies of the conventional grey models. Secondly, the Particle Swarm Optimization algorithm is selected to determine the optimal values of the damping accumulation parameters to enhance the adaptability and flexibility of the proposed model. Further, for validation purposes, experiments on forecasting the output of high-tech industries considering R&D investments are conducted from the national and provincial levels, among which six competing models are involved. Moreover, Monte-Carlo Simulation, incorporated with probability density analysis and statistical analysis, is introduced to evaluate the robustness of the newly-designed model. It can be demonstrated from the empirical results that the novel model is a reliable and promising method for predicting the economic indices of the high-tech industries with enhanced forecasting capability. • The grey multivariable convolution model is proposed. • The damping accumulation technique and its properties are initially discussed. • The robustness of the novel model with diverse predicting horizons is validated. • The proposed method exhibits strong generalizability and reliability. • The proposed technique strikingly outperforms a range of prevalent benchmarks. [ABSTRACT FROM AUTHOR]

This paper establishes a mathematical model for lockage scheduling of Three Gorges-Gezhouba Dams (LSTGD) problem based on the requirement of scheduling procedure in Three Gorges-Gezhouba Dams (TG-GD) system. The lockage scheduling is separated into three sub-problems: lockage assignment (LA), timetable optimization (TO) and ship dispatch (SD) problem. We propose chaotic embedded particle swarm optimization algorithm to solve the LSTGD problem. Meanwhile, three different chaotic maps are studied and the results are compared to evaluate the effect of different maps on PSO. In addition, heuristic-adjusted strategies are proposed based on the analysis of scheduling regulation to enhance the performance of the final solution. Finally, the proposed method is tested with the real historical execution data of lockage scheduling system in Three Gorges-Gezhouba Dams. The results show that the proposed method is efficient for solving the LSTGD problem. [ABSTRACT FROM AUTHOR]

• Optimize the electricity prices based on the DR characteristics of multi-type users. • Construct a flexible power retail portfolio optimization model. • Propose a flexible electricity retail strategy with integrated DR. Since the electricity market is opening up in China, it is necessary for power retailers to participate in the market and find a way to gain benefits. In this context, this paper constructs a two-stage flexible power sales optimization model with multi-type demand response strategies. First, the demand response strategies of different types of users are analyzed. Second, two-stage optimization is conducted: In the first stage, the fuzzy K-means clustering method is used to divide a day into peaks, flats, and valleys, and then, a multi-objective time-of-use pricing model is constructed with the aims of minimizing the peak–valley load ratio and maximizing the response revenue rate of users. A flexible power retailing portfolio optimization model is built considering multiple types of users in the second stage and the model is solved by the chaotic particle swarm optimization algorithm. Finally, a case study with four scenarios is conducted, where the demand response is taken as a changeable factor. The results show that (1) the price-based demand response can shave peaks and fill valleys, whilst also reducing the electricity cost, and optimization for industrial users has the optimal effect, followed by that of commercial users and agricultural users; (2) different types of demand responses have different emphases on peak shaving and valley filling, and a combination can achieve the best effect; (3) with the demand response, an electricity retailer can effectively reduce the deviation assessment cost, and increase the revenue by flexibly allocating electricity sales, without resulting in unsatisfied users. The conclusions verify the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

• Model-based transfer learning is utilized to construct the multi-layer extreme learning machine (MLELM). • Output mapping factors of MLELM are further optimized through particle swarm optimization (PSO) with the objective of minimizing quantile evaluation indexes. • Joint distribution adaptation (JDA) is utilized to explore historical temporal variation characteristics and update weights of MLELM to accommodate variable wind power output. With the increasing penetration of wind power, probabilistic forecasting becomes critical to quantifying wind power uncertainties and guiding power system operations. This paper proposes a transfer learning based probabilistic wind power forecasting method. Model-based transfer learning is utilized to construct the multi-layer extreme learning machine (MLELM). The output mapping factors of MLELM are further optimized through the particle swarm optimization (PSO) with the objective of minimizing the quantile evaluation indexes. Joint distribution adaptation (JDA) is utilized to update the weights of MLELM to accommodate variable wind power output. Test results on the practical wind farms in China shows that the proposed method can provide more accurate quantile forecasting results with better nonlinear fitting ability compared with other quantile forecasting methods. [ABSTRACT FROM AUTHOR]

This paper proposes a hierarchical optimization energy management strategy (EMS) considering speed profile to explore energy-saving potential and achieve a reasonable power distribution for the hybrid propulsion system of a tramway composed of the catenary, a battery pack and an ultracapacitor pack. For the higher layer, a speed profile is optimized in the space domain through a particle swarm optimization algorithm, which balances energy consumption, running time and passenger comfort. For the lower layer, based on the optimized speed profile, an EMS is designed, using dynamic programming. The boundary range calculation of state variables for the dynamic programming is carried out in advance, based on the working mode analysis to reduce the computation load. In addition, a supervisory controller is developed to achieve reliable real-time control. Finally, to verify the proposed method, real rail line data in China are used as a case study, and the results show that the proposed method offers the better energy and tramway efficiency. • An optimal speed profile is constructed based on real line data. • An improved DP method reduces the computation load. • A supervisory controller improves the reliability of the real-time EMS. • The proposed method shows better energy and tramway efficiency. [ABSTRACT FROM AUTHOR]

A comfortable indoor environment plays an important role in improving students' learning efficiency and health. How to optimize the design of primary and secondary school education buildings to achieve a comfortable indoor environment, considering both energy and cost is a considerable challenge. This paper proposes a two-stage multi-objective optimization method based on a meta-model to obtain the optimal design scheme for primary and secondary school education buildings, based on daylighting, thermal comfort, energy savings and economy. The method has two stages: building envelope optimization and building generation system optimization. In the stage of building envelope optimization, an artificial neural network (ANN) model coupling optimization algorithm is used to optimize the building envelope. The performances of the non-dominated sorting genetic algorithm II (NSGA-II) and multi-objective particle swarm optimization (MOPSO) algorithm are compared in the optimization process. In the stage of building generation system optimization, the design optimization of the building photovoltaic generation system is studied. Finally, the effectiveness of the two-stage optimization method is verified by a typical teaching building in Nanjing. The results show that the optimal scheme set of building envelope design can be obtained by this optimization method, and the optimal tilt angle and azimuth angle of the photovoltaic generation system are 30° and 210°, respectively. The minimum payback periods of the photovoltaic generation system are 11.75 years and 9.32 years under the policy of selling electricity that is not permitted and selling electricity that is permitted, respectively. • A multi-objective optimization method based on the meta-model is presented. • Optimization considering daylighting, thermal comfort, energy saving and economy. • A sensitivity analysis method based on regression method is used. • The performance of the NSGA-II and MOPSO algorithm is compared. • The payback period of photovoltaic system under different policies is optimized. [ABSTRACT FROM AUTHOR]

• A new ET model (SW_OPT) integrates the SW and the Ts-VI model using PSO. • E, T and ET from SW_OPT were validated in a typical irrigated area of China. • SW_OPT calculates ET and its components with high accuracy. • SW_OPT is significantly more accurate compared to SW_Ori. • SW_OPT has low sensitivity to most of input and empirical parameters. Daily actual evapotranspiration (ET) and its components – soil evaporation (E) and vegetation transpiration (T) – play a key role in water resource management of irrigated areas. Nevertheless, due to large uncertainties in the parameterization of the resistances in irrigated areas, traditional ET models do not always provide accurate ET estimates, especially for its components. This uncertainty is mainly due to the difficulty of determining the empirical parameters accurately of soil and canopy resistances which is debated for a long time and the error in input variables. This paper proposed an optimized Shuttleworth-Wallace model (SW) using the particle swarm optimization (PSO) algorithm to integrate the original SW with the surface temperature-vegetation index (Ts-VI) triangle models (named Shuttleworth & Wallace_Temperature Vegetation Index model, SW_TVI).The performance of the SW_TVI model was significantly improved by optimizing the soil and canopy resistances in the original SW model using discontinuous regional ET estimates from the Ts-VI model under clear-sky conditions. Compared with the original SW model, the root mean squared error (RMSE) and mean absolute deviation (MAD) of the SW_TVI model were reduced by more than 30%, against in situ measurements in the Heihe River Basin. The Bias of the T/ET ratio was also significantly reduced from -22.3% for the original SW model to -5.5% for the SW_TVI model. The annual contributions of E and T to ET were about 20% and 80%, respectively, and had a strong seasonal variation in the typical irrigated area of China. In summary, the SW_TVI model shows three outstanding advantages: (1) it estimates daily continuous E, T, and total ET with high accuracy; (2) it is very robust and insensitive or slightly sensitive to most input variables and empirical parameters; (3) it is independent from ground data. This new SW_TVI model will benefit water resources management in irrigated areas, particularly in arid and semi-arid regions. [ABSTRACT FROM AUTHOR]

• A grey model with ISRU as the initial condition is proposed for electricity consumption forecast. • PSO is applied to determine the introduced coefficients to enhance calculation efficiency. • The model accuracy is validated by comparing with other improved prediction models. • Suggestions for the layout planning of future power system in China is proposed based on prediction. Accurate medium- and long-term power consumption forecast is the premise and foundation of secure scheduling and layout planning of power system, which are conducive to the coordinated development of various power generation channels so that renewable energy generation can be improved. In view of this problem, this paper analyzes power consumption intensity in different regions in China and proposes a modified grey model with novel initial condition to enhance its forecast accuracy. Influence of initial condition in grey model is analyzed synthetically by several commonly used models, and the Inverse Square Root Unit (ISRU) function with adjustable parameters is defined as the novel initial condition to better reveal the characteristics of data growth. Particle Swarm Optimization (PSO) algorithm is adopted to calculate the introduced coefficients. Using data available from National Bureau of Statistics of China from 2007 to 2014, consumption data of 31 provinces (municipalities) from 2015 to 2018 is forecasted to attest the efficiency and adaptability of ISRU-GM(1,1). Forecast results are compared with other improved prediction models as well. Potential power consumption ability in China in the next few years from provincial perspective is studied, which guides the layout planning of power system. [ABSTRACT FROM AUTHOR]