Search

Clean energy plays an essential role in responding to environmental crises. Accurate forecasting of clean energy power generation can provide necessary references for the formulation of energy policy. This paper proposes a novel fractional discrete grey model with a dynamic time delay function (DTDFF-DGM (1,1)) to forecast clean energy power generation. This model introduces the fractional accumulation operator and the dynamic time-delay function into the discrete grey model, which ensures the priority of new information in the original data and improves the model's adaptability to different sample data. The optimal parameters of the model are calculated by the dynamic linkage between the fitting error and the test error, which effectively avoids the overfitting problem. Empirical studies have proved that the model has better prediction accuracy compared to other methods. Finally, the proposed model is employed to forecast clean energy power generation in China. The results show that from 2020 to 2025, the overall growth rate of hydropower, wind power and nuclear power in China will be 9.27%, 119.61% and 36.38%, respectively. Based on the discussion of the forecast results, relevant policy suggestions were made. This paper realizes the transformation from a static model to a dynamic model in methodology and promotes the sustainable development of clean energy power generation in application. [Display omitted] • A novel fractional discrete grey model is established. • The model is the general paradigm of the existing six discrete grey models. • The jump error is avoided in the transition from discrete to continuous. • The dynamic time-delay function is introduced. • China's clean energy power generation is effectively predicted by the model. [ABSTRACT FROM AUTHOR]

Accurate PM 2.5 forecasting provides a possibility for establishing an early warning system to notify the public and take precautionary measures to prevent negative effects on ambient air quality and public health. Considering strong seasonal variation in meteorological conditions, in this paper, a seasonal stacked autoencoder model combining seasonal analysis and deep feature learning is proposed for forecasting the hourly PM 2.5 concentration, named DL-SSAE model. The original data are firstly decomposed into four seasonal subseries according to the Chinese calendar, and then the Kendall correlation coefficient method is employed to search inherent relationships between PM 2.5 concentrations and meteorological parameters within 1-h ahead for each seasonal time series. The inherent relationships of each seasonal subseries are finally extracted, learned, and modeled by different deep neural networks (stacked autoencoders for regression), and the hourly PM 2.5 forecasts are yielded. The addressed model is tested by the dataset collected from three environmental monitoring stations in Beijing, China. The results demonstrate that the proposed model outperforms all other considered models with/without seasonality consideration in this paper. [ABSTRACT FROM AUTHOR]

As global warming intensifies, the reduction of carbon emissions is imminent. Carbon price is directly related to whether carbon can be effectively reduced. Therefore, accurately forecasting carbon price has important practical significance. Aiming at the nonstationary and nonlinear characteristics of carbon price, this paper proposes a novel hybrid model for forecasting carbon price, which is based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), multiscale fuzzy entropy (MFE), complete ensemble empirical mode decomposition (CEEMD), improved random forest by salp swarm algorithm (SSARF), improved back propagation by cuckoo search (CSBP), improved extreme learning machine by whale optimization algorithm (WOAELM) and error correction (EC), named ICEEMDAN-MFE-CEEMD-SSARF-CSBP-WOAELM-EC. Firstly, carbon price is decomposed by ICEEMDAN, divided into high-, medium-, and low-complexity components by MFE. Secondly, high-complexity components are merged and secondarily decomposed by CEEMD, which are still recorded as high-complexity components. Then, SSARF, CSBP and WOAELM are used to forecast high-, medium-, and low-complexity components, respectively, and forecasting results are reconstructed. Finally, EC is carried out using an extreme learning machine to obtain the final forecasting results, and the Diebold-Mariano test is introduced for a comprehensive evaluation of the model. Taking carbon price in the pilot cities of Shenzhen and Hubei as examples, after 6 aspects and 20 comparative experiments, the results show that the proposed model has higher forecast accuracy, with MAPE, MAE and RMSE up to 0.03131, 0.00089 and 4.02e-06 in Hubei, and its forecasting ability is better than other commonly used international carbon financial price forecasting models, providing a theoretical and data basis for carbon pricing and formulating carbon reduction policies in China. The main contributions of this paper are the improved primary decomposition, the use of secondary decomposition, and the innovative combination of three optimal models to forecast carbon price, but it still needs to be optimized for practice. [Display omitted] • Propose improve CEEMDAN by using Hermite interpolation and calculating residuals first. • High complexity components are secondarily decomposed to reduce its complexity. • Improved RF by SSA, named SSARF, is proposed to solve the dilemmas of RF. • Propose a high-accuracy hybrid model for carbon price forecasting. • Compare multi-faceted experiments to prove the validity of the proposed model. [ABSTRACT FROM AUTHOR]

Under the trend of global low-carbon development, reasonable and accurate prediction of electricity consumption plays an essential role in vigorously adjusting power system structure, promoting electrification, and other energy-saving and emission reduction measures. Considering the development trend of energy consumption, this paper introduces the Logistic model of energy structure into the system structure, and establishes a novel grey prediction model with system structure. According to the division of energy factors with similar attributes, this model seeks the internal relationship of the development of electricity consumption and describes the interaction between related factors and multiple main factors in the form of equations, which makes the model have better applicability and stability. In the validation part, the ten types of energy are divided according to their attributes, and the main factor group and the related factor group are distinguished. The model proposed in this paper is used for simulation and prediction, and is compared with the three types of models (six models). In the two cases, the simulation error of the new model is as low as 3.9790%, and the prediction error is 0.5645%. Compared with other models, the new model has shown good performance in the case of electricity consumption forecasting in China. The effectiveness of the optimization of the model in structure, background, and application is verified. At the same time, based on the analysis and prediction of China's consumption data, this paper gives relevant policy suggestions for developing China's power structure. • A novel model based on energy background (EPMGM(1,M,N)) is established. • The relationship of factors in the system are characterized by the equations. • A Logistic model based on energy structure is introduced to the new model. • China's electricity consumption is effectively predicted by the model. [ABSTRACT FROM AUTHOR]

To perform better future trend prediction for an economy-energy-environment (3E) system and address the shortcomings of traditional multivariate grey models, this paper introduces a spatial correlation term into the multivariate discrete grey model, thus creating the SLDGM(1,n) model, and improves the final calculation of the model according to the priority of new information. The validity of the SLDGM(1,n) model is assessed using data from the 3E system in North China, and the SLDGM(1,n) model is applied to predict the future trends of the 3E system in North China. The following conclusions are obtained. First, the introduction of the spatial correlation term and the improvement of the final calculation method are reasonable; the prediction accuracy of the multivariate grey model is improved, and multiple systems are modeled simultaneously. Second, the SLDGM(1,n) model calculates the spatial spillover effect, and according to the simulation results for North China from 2010 to 2019, Hebei's energy consumption and carbon emissions are subject to the largest influence from other provinces, while its economic development level is subject to the smallest influence, and the carbon emissions of Shanxi and Inner Mongolia are subject to a negative spatial influence effect. Third, the prediction results indicate that under the effect of spatial correlation, the energy consumption of all five provinces in North China will continue to rise; the carbon emissions of Beijing will gradually decline while the carbon emissions of the other four provinces will all gradually rise, and the per capita GDP of the five provinces is expected to increase by more than 50% by 2025. [ABSTRACT FROM AUTHOR]

Economic growth, energy consumption, and urbanization are mutually influenced, therefore, forecasting economic growth, energy consumption and urbanization in China has always been important as it could help government to improve energy policies and plans. To this end, two novel grey multivariable models, SRMGM(1, M) and BRMGM(1, m), are designed in this paper. Compared with the MGM(1, M) model, the SRMGM(1, M) model can optimize the background of the traditional model according to the Simpson formula, and the BRMGM(1, m) model optimizes the background value according to a Boolean formula. The reconstruction of background value can reduce the prediction error of MGM(1, M) model. Furthermore, rolling prediction is added to these two new models based on the priority principle of new information. In order to validate their efficacy and accuracy, the two proposed models are employed to reproduce and predict economic growth, energy consumption, and urbanization compared with MGM(1, m) model and three linear regression models. FDs of our models, in both fitted and predicted stages are all over 97%, and the ADFs are all below 5%. The results show that our new models achieves higher fitted and predicted accuracy than MGM(1,m) model and the non-grey models. Eventually, the new models will be used to forecast economic growth, energy consumption, and urbanization from 2020 to 2025, and the forecast results provide a solid basis for economic growth policies and energy consumption plans. [Display omitted] • Two novel grey models are designed and theirs the validity are proved in the paper. • The background value is improved by Simpson formula and Boolean formula. • Two novel models perform best than the non-grey models. • The results improve economic growth policies and energy consumption plans. [ABSTRACT FROM AUTHOR]

Forecasting CO 2 emissions in China always has been of great significance as it could help the government to improve energy policies and plans. To this end, a novel grey multivariable model is designed in this paper. Compared with the conventional grey multivariable model, which has certain drawbacks of inaccurate prediction and poor adaptability that restrict their applications in practical cases, the proposed model can make three improvements: first, an optimized grey model having a modified background value is proposed to predict the trends of the driving variables. Second, the novel grey multivariable model is established, combined with the changing trends of driving variables. Third, the adjustment coefficient in the new model is optimized to obtain optimal values for the time response function. To demonstrate its efficacy, the proposed model is employed to reproduce and predict the CO 2 emissions from fuel combustion compared with four benchmark models—the results show that the new model yields more accurate forecasting results than the competing models. Eventually, the new model will be used to quantify future Chinese CO 2 emissions from fuel combustion from 2014 to 2020, and the forecasted results can provide a solid basis for formulating environmental policies and energy consumption plans. [ABSTRACT FROM AUTHOR]

Urbanization results in a considerable economic disparity between urban and rural areas in developing countries, which has had a consequent significant impact on CO 2 emissions. To accommodate this directly, this paper presents a modified version of the Kaya Identity formula, U-Kaya, that includes a direct urbanization factor to determine the relationship between energy consumption intensity, population growth, urbanization rates, urban and rural GDP per capita and the volume of carbon emissions, for application in the dynamic forecasting of carbon emissions by Monte Carlo simulation. The method is demonstrated in forecasting China's likely carbon emissions in 2020 by three different modes of urbanization policy: the government-dominant mode, market-dominant mode and a hybrid government market-dominant mode. The results indicate that a higher urbanization rate, energy carbon emission coefficient and energy intensity will lead to increased carbon emissions. Finally, three policy implications are identified, comprising the narrowing of the economic gap between urban and rural areas, adjustments to the energy structure and technical innovation, which will provide a valuable reference for developing countries in their efforts to reduce carbon emissions. [ABSTRACT FROM AUTHOR]

Motivated by reducing carbon emissions, carbon trading market have been opened to promote environmental protection. Accurate carbon trading volume and price forecasts have far-reaching implications for environmental and energy policy formulation. As the country with the most massive carbon emissions in the world, China's carbon price trends, carbon trading volume trends, and policy orientation are of great significance. As matters stand, there are few studies on carbon price and trading volume forecasts, and no research paper has covered carbon price and trading volume forecasts for all carbon trading markets in China. In order to provide a relatively complete reference for the carbon price and trading volume in China, this paper uses six machine learning models to predict the daily carbon price and trading volume of eight carbon markets in China, including Beijing, Shenzhen, Guangdong, Hubei, Shanghai, Fujian, Tianjin, Chongqing. The prediction models include extreme gradient boosting, random forest, kernel-based nonlinear extension of the Arps decline model optimized by grey wolf optimizer (GWO-KNEA), support vector machine optimized by particle swarm optimizer, support vector machine optimized by fruit fly optimizer and simulated annealing algorithm, and radial basis function neural network (RBFNN). Moreover, an advanced data denoising method, i.e., complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), is used in the models to smooth the raw data. Because the eight carbon trading markets have different carbon price and trading volume distribution characteristics in time series, by comparing the prediction results, more suitable models for the specific carbon market can be obtained. The prediction results show that CEEMDAN-GWO-KNEA and CEEMDAN-RBFNN are more competitive in predicting carbon prices and trading volume in China because of their best performance in many datasets. The average accuracy of CEEMDAN-RBFNN and CEMDAN-GWO-KNEA in carbon price prediction is 98.40% and 97.89%, respectively. The predictive stability of each model in different application scenarios is also discussed. The results show that high prediction accuracy does not mean better prediction stability, but CEEMDAN-RBFNN and CEMDAN-GWO-KNEA can still guarantee high stability in most datasets. [ABSTRACT FROM AUTHOR]

This paper investigates the time lag effect of carbon emissions using a novel temporal input-output approach (TIO). The sectoral average production time of various sectors is evaluated based on the turnover rate data of 3394 listed companies in China's A-share market. Then, a polynomial function is developed to fit the indirect carbon emissions and time lag at each consumption stage in the industrial chains. Finally, an empirical study is carried out to forecast the time lag effect of carbon emissions with final demand fluctuations based on the latest 2017 input-output table for China. The results show that indirect carbon emissions caused by sectoral economic activities decline stage by stage in the industrial chains, and the decline rate and time lag intensity vary significantly among sectors. The logistics industry has the highest spread efficiency for indirect carbon emissions in the industrial chains, and the construction industry is the first industry affected by the indirect carbon emissions caused by the manufacturing industry. The power/thermal industry's impact on China's carbon emissions is the fastest, but its duration is the shortest, while the impact of the manufacturing and mining industries are more stable and durable. However, considering the fluctuations in final demand, the manufacturing industry has replaced the power/thermal industry as the most important industry affecting the time lag effect of China's carbon emissions. This study provides important theoretical and practical value for indirect carbon emissions forecasting. • A novel temporal input-output approach is investigated. • Indirect carbon emissions and time lags in industrial chains are calculated. • A polynomial function is developed to fit the time lag functions of carbon emissions. • An empirical study is conducted based on the 2017 I–O table for China. [ABSTRACT FROM AUTHOR]

As one of the three major fields of building energy consumption, public buildings (PBs)are under pressure regarding energy saving and emission reductions, with PB energy consumption accounting for 38% of the total consumption. Thus, CO 2 emissions released in PBs have become crucial for China in achieving its emission mitigation goal in the "Post Paris" period. This paper is the first to develop a support vector machine (SVM) method to predict and diagnose PB energy consumption based on 11 input parameters, including historical energy consumption data, climatic factors and time-cycle factors. Months with air-conditioning energy consumption in Wuhan were considered the study period, and we used June and July data for model prediction training, August data as the test set, and September data to diagnose the air conditioner energy consumption anomaly. The results show that air conditioning energy consumption was abnormal for four days in September. Relevant policies and suggestions are proposed based on the causal analysis. This research is expected to provide theoretical guidance and a practical data reference for building operations management. [ABSTRACT FROM AUTHOR]

Understanding the structural characteristics, evolution, and associated mechanisms of different types of eco-industrial parks (EIPs) is important. Using complex network methods, this paper distinguishes planned-type and spontaneous-type EIPs by analyzing some cases of EIPs (especially China's Xinzhuang EIP). The findings are as follows: (1) planned-type EIPs demonstrate more diverse sub-structures than spontaneous EIPs (more specifically, planned-type EIPs usually involve more obvious clustering phenomena and closer communication); (2) though in planned EIPs all kinds of centralities are reasonable for determining key enterprises, in spontaneous EIPs closeness and between centrality prove better measures than eigenvector centrality; (3) small-world and scale-free characteristics are important for enhancing flow transmission in both planned EIPs and spontaneous EIPs (specifically, planned EIPs show more significant small-world/scale-free effects than spontaneous EIPs, and scale-free characteristics with degree distribution coefficient 0.5–2.0 make EIPs less invulnerable); and (4) the Xinzhuang EIP is vulnerable in the network configuration under the attacks. It is important to maintain the stable stay and development of the key enterprises in an EIP. Comparing information and environmental scenarios for Xinzhuang EIP reveals that the park's performance or efficiency is likely to be better in an information scenario. In a word, our results reveal the development mechanisms of EIPs, methods of evaluating key enterprises, ways of link reforms, structural stability of EIPs, and future scenarios predictions in terms of the practical situations. • Different sub-structural patterns and clustering features for planned EIPs and spontaneous EIPs. • Centrality measures of identifying key enterprises are dependent on the type of EIPs. • Planned EIPs show more significant small-world and scale-free effects than spontaneous EIPs. • Scale-free characteristics make EIPs vulnerable, and EIPs may easily collapse under attacks. • Greater and more effective impact of information scenario on the Xinzhang EIP than environmental scenario. [ABSTRACT FROM AUTHOR]

Businesses are constrained by and dependent upon nature and institutional context. The global climate crisis has put pressure on and increased firm sensitivity to environmental issues. Predicting corporate environmental performance can help plan for environmental impact mitigation by adjusting organizational practices. Lack of environment-related information makes it difficult to make such predictions. This paper tends to provide useful insights into corporate environmental performance among firms to facilitate better environmental management for both government and firms. A theoretical framework informed by the natural-resource-based view (NRBV) of the firm and institutional theory is used to identify variables for predicting corporate environmental performance. Five dimensions including institutional context, governance capability, information management capability, system capability, and technology-related capability, populated with 14 variables are used to empirically investigate the relationship of these variables with corporate environmental performance. Using 1100 data points on energy service companies (ESCOs) from 2011 to 2015 in mainland China, the Extreme Gradient Boosting (XGBoost) algorithm, a statistical nonlinear machine learning approach, is utilized to predict corporate environmental performance. The results demonstrate that the XGBoost model can be effective for ESCO environmental performance prediction, with satisfactory prediction accuracy. This study also adopted the SHapley Additive exPlanations (SHAP) values for model interpretation, indicating that total assets, amount of proactive environmental costs, proportion of technicians and number of patents contribute most to corporate environmental performance. Several policies and environmental strategies for improving corporate environmental performance in the ESCO industry are derived from this analysis. [ABSTRACT FROM AUTHOR]

Accurate prediction of PM 2.5 concentration for its monitoring and early warning has become the major concern in terms of frequent occurrences of severe haze episodes in China. In this paper, a novel model for hourly PM 2.5 concentration prediction during severe haze episodes is suggested, where mode decomposition-recombination technique and ensemble learning approach are innovatively introduced into high concentration PM 2.5 forecasting. Firstly, the fast ensemble empirical mode decomposition (FEEMD) is applied to decompose the original complex non-stationary data into several modes with different frequencies to offset the impact of data noise. The sample entropy (SE) is used to further recombine similar modes aiming at avoiding excessive-decomposition to promote accurate information extraction and computational efficiency. Next, the partial autocorrelation analysis (PACF) is executed on the recombined modes to select appropriate input features of the forecasting model. Finally, the Stacking-driven ensemble model (SDEM) is developed as the forecasting model to enhance the feature representation and information utilization capacities in which K-fold cross-validation is carried out in each base-model to enhance the generalization performance. Outputs of each base-models are new input for the meta-model to acquire ultimate superior forecasting values. The empirical results of Baoding during autumn and winter illustrate that: (1) the proposed model exhibits effectiveness and robustness in PM 2.5 concentration prediction, particularly, these superiorities will not be weakened even at extremely high concentration points of PM 2.5 ; (2) the decomposition-recombination technique is potential to handle nonlinear and high volatility data; (3) the ensemble learning approach can inherit and integrate merits of single models; (4) the developed FEEMD-SE-SDEM model outperforms other contrast models in terms of forecasting accuracy, stability and class prediction correct rate, which is promising in early air quality warning system. • A model to forecast hourly PM 2.5 concentration in severe haze episodes is proposed. • Mode decomposition-recombination is executed to enhance prediction performance. • Ensemble learning is explored to inherit and integrate the merits of single models. • Potential for early air quality warning system and high concentration prediction. [ABSTRACT FROM AUTHOR]

Urbanization results in a considerable economic disparity between urban and rural areas in developing countries, which has had a consequent significant impact on CO 2 emissions. To accommodate this directly, this paper presents a modified version of the Kaya Identity formula, U-Kaya, that includes a direct urbanization factor to determine the relationship between energy consumption intensity, population growth, urbanization rates, urban and rural GDP per capita and the volume of carbon emissions, for application in the dynamic forecasting of carbon emissions by Monte Carlo simulation. The method is demonstrated in forecasting China’s likely carbon emissions in 2020 by three different modes of urbanization policy: the government-dominant mode, market-dominant mode and a hybrid government market-dominant mode. The results indicate that a higher urbanization rate, energy carbon emission coefficient and energy intensity will lead to increased carbon emissions. Finally, three policy implications are identified, comprising the narrowing of the economic gap between urban and rural areas, adjustments to the energy structure and technical innovation, which will provide a valuable reference for developing countries in their efforts to reduce carbon emissions. [ABSTRACT FROM AUTHOR]