Search

This paper studies the time-scale characteristics, model reduction, and oscillation stability of the grid-connected variable speed pumped storage unit (VSPSU). Firstly, a method based on the modal analysis and time-scale separation ratio indicator is established to analyze the time-scale characteristics of VSPSU. The results indicate that the state variables of VSPSU can be approximately separated on four-time scales. On this basis, the singular perturbation method (SPM) is applied to obtain the reduced-order model (ROM) of VSPSU under different conditions. The results show that the accuracy of ROMs can be affected by changes in operating conditions. To balance the complexity and accuracy of ROM, a model reduction strategy combining SPM and reduction margin is proposed. The results indicate that the proposed method enables the order minimization of ROM while the selected oscillation mode reaches a given accuracy condition. Finally, the feasibility of ROM for oscillation stability analysis is verified. The ROMs obtained with the proposed strategy are more accurate than those obtained with SPM for oscillation stability analysis of VSPSU. The influence of grid strength, turbine speed, and torque conditions on system oscillation stability is also revealed. This study provides new insights for model order reduction and stability analysis of VSPSU. [ABSTRACT FROM AUTHOR]

Efficient estimation of the uncertainty associated with wind speed forecast is crucial for evaluating wind farms' power quality and operation. Typically, the performance of prediction interval (PI) generating models; is restricted in terms of computational efficiency inheritably from the sequential data processing; whereas restrictions in forecast quality are derived from the PI generation techniques. This paper presents an efficient Gated Multi-Scale Convolutional Sequence Model (GMSCSM) to forecast wind speed PIs. GMSCSM while conserving the 'recurrence' of LSTMs also offers 'parallel input' advantage of CNNs for better computational efficiency which is highly desirable for short-term forecasting models. In addition, capturing features at various scales in the sequence, GMSCSM learns both local details and global context which is vital for multi-horizon forecasts. The model generates quality PIs utilizing an improved quality-driven loss which we proposed by invoking calibration assessment in its existing definition. Forecasts generated for eight different datasets obtained from two different wind farms show an improvement of 30 % and 6 % in the average coverage width criterion index while reducing the model training time to nearly half and one third of the respective values obtained from traditional and LSTM based models which showcases the proposed model's excellent prediction capability and efficiency. • An efficient wind speed interval prediction tool is developed which could prove helpful in tackling the wind power development problems. • Utilizing the parallel input advantage of CNNs and recurrence properties of RNNs, an efficient deep learning framework for wind speed interval prediction is proposed. • Combining different window sizes-based convolutions the study develops a smart and efficient multi-scale feature extraction mechanism to capture both local and long-term dependencies in the data. • Adding a calibration function, the study proposed an improved calibrated quality driven loss function (QD imp) which mitigates the threshold coverage problem specially under multi-horizon forecasting. [ABSTRACT FROM AUTHOR]

This paper aims to study the nonlinear damping characteristic of hydro-turbine governing systems (HTGS) in various frequency bands and improve the reliability of nonlinear damping quantification. Firstly, an HTGS model including multiple hydraulic-mechanical nonlinearities is established using an actual hydropower system as the object. Then, a trajectory quantification method is proposed to enhance the accuracy and stability of the damping calculation. On this basis, the influence of the hydraulic and controller parameters on the HTGS damping in the ultra-low and low frequency band is analyzed. Finally, a deviation indicator is defined to analyze the contribution level of each nonlinear factor to the damping characteristics, and the action mechanism of dominant nonlinearity on damping is further investigated. The results show that increasing the controller parameter and hydraulic parameter decreases the minimum damping of the HTGS. The total deviation of damping under the influence of nonlinearity reaches 1.31 times. Among them, water system nonlinearity and governor delay are two major nonlinearities, and their influence on damping characteristics accounts for 41.4% and 34.4% of the total nonlinear influence, respectively. This paper provides a powerful tool to quantify the damping of nonlinear HTGS and potentially supports the regulation performance enhancement of HTGS. [Display omitted] [ABSTRACT FROM AUTHOR]

As a well-known homologous information fusion technology, the full spectrum is widely used in orbit analysis of rotating machinery. However, due to the average effect of the Fourier transform, the instantaneous features of the axis orbit cannot be obtained in full spectrum. This limits the application of the full spectrum in a nonstationary vibration analysis. The time–frequency representation (TFR) of axis orbit has been proved to be an effective tool for analyzing nonstationary vibration signals. In this article, a new approach of instantaneous features extraction of harmonic axis orbits is proposed. Furthermore, based on these features, an approach to construct the purified orbit TFR (POTFR) is proposed. First, the estimated speed signal is extracted from the TFR of a single-channel signal by data fitting. Guided by the estimated speed signal, the harmonic components of interest are separated by the Vold–Kalman filter. Furthermore, the parameters of each harmonic instantaneous orbit are calculated from the time domain by using the separated harmonic signals. Based on these parameters, high-resolution POTFRs of all the harmonic orbits are constructed. Finally, the POTFR of the original signal is obtained by combining the POTFRs of all the harmonic components. The proposed approach is illustrated by numerical simulation and is further validated using laboratory experimental signals of oil whip and bistable behavior. The start-up signal from a hydroelectric generating set further demonstrates the superiority of the method. [ABSTRACT FROM AUTHOR]

The application of wind power interval prediction for power systems attempts to give more comprehensive support to dispatchers and operators of the grid. Lower upper bound estimation (LUBE) method is widely applied in interval prediction. However, the existing LUBE approaches are trained by meta-heuristic optimization, which is either time-consuming or show poor effect when the LUBE model is complex. In this paper, a deep interval prediction method is designed in the framework of LUBE and an efficient gradient descend (GD) training approach is proposed to train the LUBE model. In this method, the long short-term memory is selected as a representative to show the modelling approach. The architecture of the proposed model consists of three parts, namely the long short-term memory module, the fully connected layers and the rank ordered module. Two loss functions are specially designed for implementing the GD training method based on the root mean square back propagation algorithm. To verify the performance of the proposed model, conventional LUBE models, as well as popular statistic interval prediction models are compared in numerical experiments. The results show that the proposed approach performs best in terms of effectiveness and efficiency with average 45% promotion in quality of prediction interval and 66% reduction of time consumptions compared to traditional LUBE models. • A new deep LUBE model based on gradient descend optimization method is proposed for the first time. • Loss functions are designed to apply the root mean square back propagation method for effective model training. • An improved coverage width criterion index is proposed to effectively evaluate interval prediction model. • The superiority of the proposed method has been fully confirmed by 45% average performance promotion over its competitors. [ABSTRACT FROM AUTHOR]

• A successive start-up model of a real-world PSPS is established and tested. • The analysis of the impact of successive time interval △T is carried out. • A novel multi-objective optimization scheme for successive start-up is proposed. This paper aims to study the optimal successive start-up strategy of two hydraulic coupling pumped storage units (PSUs) based on multi-objective control. Firstly, a successive start-up model of a pumped storage power station (PSPS) with two PSUs is established. Secondly, the analysis of the impact of successive time interval ΔT is carried out. Thirdly, a novel optimization scheme multi-objective with two PSUs owning different parameters (MODP) is proposed for start-up optimization. For comparison, three optimization schemes named single objective with two PSUs sharing the same parameters (SOSP), single objective with two PSUs owning different parameters (SODP) and multi-objective with two PSUs sharing the same parameters (MOSP) are also tested. Finally, according to the four optimization schemes, i.e. SOSP, SODP, MOSP and MODP, the optimization model is established and performed separately in MATLAB 9.1 based on a real case. The results indicate that the change of ΔT has a great effect on the transient process of 1# PSU, but less effect on the transient process of 2# PSU. ΔT should be chosen as a decision variable in the successive start-up optimization. For the successive start-up of a PSPS with two PSUs, the multi-objective scheme is superior to the single-objective scheme. The scheme of different parameters is superior to the scheme of sharing parameters. Among four schemes, MODP scheme is the best. The MODP scheme can obtain the Pareto Set that provides more choices for decision makers, which is flexible in engineering applications. MODP is a general method for successive start-up strategy optimization. [ABSTRACT FROM AUTHOR]

Abstract Guaranteed calculation for regulation (GCR) is indispensable in the operation of a pumped storage power station (PSPS), which aims to determine the rotational speed of turbines and pressure in the water diversion system under extreme conditions, such as load rejection. The closure law of guide vanes (CLGVs) requires optimization to minimize the maximum value of the water hammer pressure and the rotational speed in GCR. To address these two contradictory objectives, a multi-objective CLGV optimization (MOCLGVO) model is constructed in which these objectives are handled simultaneously. A recently proposed multi-objective artificial sheep algorithm (MOASA) is adopted to address the MOCLGVO problem. Thereafter, a recently proposed three-phase CLGV is adopted and compared with the traditional one- and two-phase CLGV in the GCR of a PSPS in China. According to a comparative study, the proposed three-phase CLGV optimized using MOASA achieves significant superiority over the traditional one- or two-phase CLGVs. Highlights • In this paper, the multi-objective CLGV in GCR for a pumped storage unit has been studied. • The multi-objective model and a novel meta-heuristic algorithm have been proposed. • A three-phase CLGV has been designed and optimized to achieve better performance than traditional CLGVs. • The performance of the proposed approach has been verified in a pumped storage power station in Jiangxi Province in China. [ABSTRACT FROM AUTHOR]

In this paper, a novel multi-objective artificial sheep algorithm (MOASA) is proposed. The basic search idea of MOASA inherits from the BASA, which is inspired by the social behavior of sheep herd, while some modifications are made to extend the algorithm to multi-objective problems. The Pareto-based theory is adopted in the MOASA along with external archive and leader selection mechanism to bring about multi-objective optimization. Furthermore, a novel neighborhood search method is proposed and applied to the external archive to enhance the performance of the algorithm. The proposed MOASA is then tested on 17 multi-objective benchmark problems to verify its efficiency and effectiveness by comparing with six powerful multi-objective optimization algorithms (MOAs). Experimental results show that the MOASA is generally superior to its competitors in solving those benchmark problems in terms of convergence and Pareto front distribution. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a new short-term multi-objective complementary scheduling problem for hydro-thermal-renewable power systems (HTRPSs). The economic/emission objectives, different from traditional economic/emission load dispatch problems, consider the on/off status of thermal power units as well as the dispatched load among engaged units as the optimization variables under various complicated nonlinear constraints. To solve the model with hybrid optimization variables, a multi-objective hybrid grey wolf optimization algorithm is proposed, in which continuous and discrete optimization variables are encoded and optimized synchronously. A daily scheduling simulation example of a hybrid power system consisting of cascade hydropower stations, thermal power units, and renewable energy (RE) power plants is studied to test the proposed model and algorithm. The results not only demonstrate that the proposed algorithm can achieve the best Pareto front for economic/emission bi-objectives compared to its competitors, but also confirm that the obtained scheduling schemes are completely within the feasible domain. Moreover, the impact of RE capacity on the power system is analyzed. Results indicate that the joint operation of RE and hydropower stations benefit both the economic and emission objectives, and the operational costs and pollution emissions decrease by 11.9% and 17.4%, respectively, when the RE capacity increases from 50% to 100% in the hybrid system. Highlights • A new problem of multi-objective complementary scheduling of hydro-thermal-RE power system is studied. • The on/off status of thermal power units and the load dispatch of thermal and hydropower units are optimized synchronously. • A multi-objective hybrid grey wolf optimizer is proposed for hybrid optimization of real and integral variables. • The proposed MOHGWO can get better Pareto front considering economic and environmental objective. • The impact of different RE capacity on the HTRPS is analyzed. [ABSTRACT FROM AUTHOR]

This paper aims to study the comprehensive stability of the multi-unit hydropower systems (MUHS) with complex hydraulic coupling under flexible operating conditions and to reduce the time consumption of batch conversions in the stability domain of high-order hydropower systems (HOHSs). Firstly, the models for an actual hydropower system with three-turbine sharing a long tailrace are established considering three typical operating scenarios. Subsequently, a trajectory search algorithm is proposed to improve the speed and flexibility of stable domain solving in HOHSs. On this basis, the stability variation law of the MUHS with the variation of water head and guide vane opening is studied, and the minimum stability domain index is introduced to evaluate the comprehensive stability of systems under full hydroturbine operating conditions. Finally, the comprehensive stability of the MUHS under flexible combination operating conditions is analyzed. Notably, the stability of the MUHS is poor when the hydroturbine is operated at a water head of 215–225 m and a guide vane opening within 55–70%. In addition, the reduction of operating units will significantly deteriorate the comprehensive stability of MUHS. This paper provides a powerful tool for the stability analysis of HOHSs and potentially supports the optimal operation of the MUHS. [Display omitted] • A stability domain solution method that fast and adaptable to order changes is proposed. • The relationship between the MUHS stability and flexible operating conditions is revealed. • A reliable index is proposed to evaluate the comprehensive stability of the system. • The multi-turbine HTGS model with multiple operating scenarios is established. [ABSTRACT FROM AUTHOR]

Wind speed forecasting plays an important role in estimating the power produced from wind farms. However, because of the non-linear and non-stationary characteristics of the wind speed time series, it is difficult to model and predict such series precisely by traditional wind speed forecasting models. In this paper, a novel hybrid modelling method is proposed, in which time series decomposition, feature selection, and basic forecasting model are combined in a synchronous optimisation framework. In this method, the above-mentioned modelling factors, which affect model performance, could make a concerted effort to improve the model. Specifically, variational mode decomposition, the Gram–Schmidt orthogonal, and extreme learning machine, are optimized synchronously by gravitational search algorithm in the proposed hybrid short-term wind speed forecasting model. First, variational mode decomposition is employed to decompose the original wind speed time series into a set of modes and into one bias series. Subsequently, the Gram–Schmidt orthogonal is used to select the important features. Next, the set of modes are forecasted using the ELM. Finally, the key parameters of the models in three stages are optimized synchronously by gravitational search algorithm. Seven data sets from the Sotavento Galicia wind farm and two wind farms in China have been adopted to evaluate the proposed method. The results show that the proposed method achieves significantly better performance than the traditional signal forecasting models both on one-step and multi-step wind speed forecasting with at least 40% average performance promotion over all the seven competitors. [ABSTRACT FROM AUTHOR]

Hyper-plane-shaped clustering (HPSC) has been proved to be more effective in Takagi–Sugeno (T–S) fuzzy model identification compared with hyper-sphere-shaped clustering (HSSC). However, there is no special membership function matching HPSC in fuzzy modeling, and the commonly used bell-shaped Gaussian function is more suitable for HSSC. In this paper, a novel T–S fuzzy model identification method is adopted, in which a new fuzzy membership function designed for HSPC is designed. In this approach, a fuzzy c-regression model based clustering method is used to partition the fuzzy space firstly; and then a new HPSC fuzzy membership function is designed to identify the antecedent membership function (MF) parameters; finally the gravitational search algorithm is applied to optimize the MF parameters further. Experimental results on several benchmark problems show that modeling accuracies have been promoted significantly. The proposed approach has been applied in fuzzy modeling of pump-turbine governing system (PTGS). The comparative experimental results reveal that the proposed approach could achieve high accuracy and would be an effective modeling tool for complicated nonlinear system in engineering applications. [ABSTRACT FROM AUTHOR]

In this paper, the control problem of pumped storage unit (PSU) has been studied. A nonlinear generalized predictive control (NGPC) method has been applied to design the controller for a PSU. The NGPC controller is designed based on instantaneous linearization model of the control system, and the parameters of the linearized model are identified online by the recursive least square method (RLSM). Besides, in order to minimize the modelling error on initial state, a prior-knowledge learning method has been proposed to get the initial parameters for control model estimation. To verify the effectiveness of the NGPC controller, we chose a pumped-storage hydropower plant in China as the experimental subject and the simulation experiments respect to the control system are designed. The processes of start-up and speed disturbance under no-load condition have been simulated to testify the robustness and efficiency of the NGPC controller. Comparative experiments have been conducted, while the NGPC controller, a PID controller and a fractional order PID (FOPID) controller have been compared. Experimental results show that the designed NGPC could effectively restrain the oscillation of rotational speed in different working conditions of PSU and demonstrates higher robustness and stability than both the PID and FOPID controllers. [ABSTRACT FROM AUTHOR]

The low‐frequency oscillation has become one of the most threatening problems of the electrical power system in the past few decades. The traditional Prony analysis method is seriously affected by noise and order estimation which cannot get the dominant oscillation sometime. A singular value decomposition‐difference differential method is proposed for order estimation of Prony mode. A parameter optimisation method based on interior point method is also proposed eliminating the noise effects on dominant model parameters. The proposed method has a fairly good property in noise suppression and dominant oscillation mode tracking. The suitability of the proposed method had been demonstrated in the simulation and case study. [ABSTRACT FROM AUTHOR]

Multivariate signal processing methods are becoming more prevalent as sensors and modern science and technology improve. However, most existing multivariate signal decomposition methods suffer from the following challenges: (i) requiring prior knowledge of multivariate signal modes; (ii) limiting to narrowband signal analysis; (iii) presenting mode mixing. To overcome the challenges mentioned above, this study proposes a novel method, named adaptive multivariate chirp mode decomposition (AMCMD). The method captures time-varying joint modes one-by-one in a recursive framework without knowing the precise number of modes. Specifically, a multivariate chirp mode (MCM) is modeled first based on AM–FM signals, with the constraint that there is a joint frequency component between all signal channels. Furthermore, demodulation techniques are used to entail the wideband multivariate signal mode exhibit narrowband characteristics. Finally, the objective function is established and the modes of each channel signal are estimated one by one. The efficacy and superiority of the method are verified by a series of numerical examples. In addition, the analysis of real-world time-varying vibration signals also confirms the practicality of the method. The findings demonstrate that the proposed method can converge faster to the same satisfactory results as existing state-of-the-art methods at a faster rate, even without knowing the precise number of modes. [ABSTRACT FROM AUTHOR]

Wind power and photovoltaic power, two types of renewable energy (RE), have made large inroads into the power system. In this paper, we study a unit commitment (UC) problem that considers the uncertainty in RE and pumped hydro-energy storage (PHES). To improve the optimisation performance for this problem, we propose a novel heuristic algorithm called the Binary Artificial Sheep Algorithm (BASA) that is based on the social behaviour of sheep flock. To evaluate the effect of the uncertainty of RE, a scenario evaluation method is defined to assess quantitatively the stability and economy of the UC results with respect to different levels of RE forecasting errors. In addition, we investigate and analyse the effect of PHES on the UC problem. Three UC test systems with different RE and PHES combinations are used to verify the feasibility and effectiveness of the proposed BASA as well as its performance. The proposed BASA performed better than traditional fundamental metaheuristics in solving UC problems. Our results also demonstrated that the equivalent load fluctuation and operating costs of the thermal units will increase significantly with an increase in RE power forecast error, but the PHES can effectively counterbalance this adverse effect. [ABSTRACT FROM AUTHOR]

A Mixed-Strategy based Gravitational Search Algorithm (MS-GSA) is proposed in this paper, in which three improvement strategies are mixed and integrated in the standard GSA to enhance the optimization ability. The first improvement strategy is introducing elite agent's guidance into movement function to accelerate convergence speed. The second one is designing an adaptive gravitational constant function to keep a balance between the exploration and exploitation in the searching process. And the third improvement strategy is the mutation strategy based on the Cauchy and Gaussian mutations for overcoming the shortages of premature. The MS-GSA has been verified by comparing with 7 popular meta-heuristics algorithms on 23 typical basic benchmark functions and 7 CEC2005 composite benchmark functions. The results on these benchmark functions show that the MS-GSA has achieved significantly better performance than other algorithms. The effectiveness and significance of the results have been verified by Wilcoxon's test. Finally, the MS-GSA is employed to solve the parameter identification problem of Hydraulic turbine governing system (HTGS). It is shown that the MS-GSA is able to identify the parameters of HTGS effectively with higher accuracy compared with existing methods. [ABSTRACT FROM AUTHOR]

The hydraulic turbine governing system (HTGS) is a crucial control system of hydroelectric generating units (HGUs). Parameter identification of HTGS is an important issue for the modeling and control of HGUs. The parameter identification problem of HTGS is more difficult if the elastic water hammer model is considered in the system, and existing algorithms are not effective to solve it. To solve this new problem, a modified gravitational search algorithm (MGSA) has been proposed in which modifications have been made to improve the performance of the GSA from two aspects. First, the constant attenuation factor is replaced by a hyperbolic function to generate a better gravitational constant to balance the global exploration and local exploitation during different searching stages. Second, agent mutation is introduced to increase the diversity of agents and to strengthen the ability to jump out of the local minima of the GSA. The performance of the MGSA has been verified by 13 typical benchmark problems, and the experimental results and statistical analysis demonstrate that the proposed MGSA significantly outperforms the standard GSA and some other popular optimization algorithms. The MGSA is then employed in the parameter identification of a nonlinear model of HTGS with an elastic water hammer, and the experimental results indicate that MGSA locates more precise parameter values than the compared methods. [ABSTRACT FROM AUTHOR]

Parameter optimization and feature selection influence the classification accuracy of support vector machine (SVM) significantly. In order to improve classification accuracy of SVM, this paper hybridizes chaotic search and gravitational search algorithm (GSA) with SVM and presents a new chaos embedded GSA-SVM (CGSA-SVM) hybrid system. In this system, input feature subsets and the SVM parameters are optimized simultaneously, while GSA is used to optimize the parameters of SVM and chaotic search is embedded in the searching iterations of GSA to optimize the feature subsets. Fourteen UCI datasets are employed to calculate the classification accuracy rate in order to evaluate the developed CGSA-SVM approach. The developed approach is compared with grid search and some other hybrid systems such as GA-SVM, PSO-SVM and GSA-SVM. The results show that the proposed approach achieves high classification accuracy and efficiency compared with well-known similar classifier systems. [ABSTRACT FROM AUTHOR]

• A refined non-linear model reflecting the grid-connected operation of a cluster of hydropower units is established. • An improved damping quantification method and parameter sensitivity analysis indices are proposed. • Influence of the operating conditions of a hydropower plant on the hydraulic-mechanical damping (HMD) is studied. • The variation law of HMD and its parameter sensitivity with system parameters is analyzed. Hydropower is probably the largest sustainable energy source in use and plays an important role in maintaining power and frequency stability of the power system. However, in hydropower-dominated power systems (HDPS), hydropower units often exhibit negative damping, increasing the risk of ultra-low frequency oscillations (ULFO). In this paper, the operating characteristics and parameter sensitivities of hydropower unit (HPU) damping in an HDPS are investigated, taking a large hydropower plant in southwest China as an example. To this end, a refined mathematical model of a cluster of HPUs is established, and an improved damping quantification method and parameter sensitivity analysis indices are proposed for the complex energy system. On this basis, the damping of the HPU with different control modes under a ULFO is investigated with the change of operating conditions represented by guide vane opening, water head and the number of parallel-running units. Meanwhile, the sensitivity of the damping to the system parameters is analyzed to reveal the influence mechanism of the parameters on the ULFO. Also, measures to suppress the ULFO are formulated from two levels of operation and control combined with theoretical analysis. [ABSTRACT FROM AUTHOR]

Abstract: Heuristic optimization has shown its superiority in handling identification problem of complicated system, for methods based on heuristic optimization do not have special requirements on model structures of the target system. In this paper, a piecewise function based gravitational search algorithm (PFGSA) is proposed and applied in parameter identification of automatic voltage regulator (AVR) system. In the proposed algorithm, a piecewise function is designed as the gravitational constant function to replace the traditional exponential equation. The piecewise function provides more rational gravitational constant to control the convergence of algorithm, and thus excellent searching ability is likely to be achieved. Moreover a new weighted objective function is proposed in the identification frame. Comparative experimental studies are conducted to test the searching ability of PFGSA and to verify the performance of proposed identification strategy, while genetic algorithm, particle swarm optimization and GSA are employed for comparison. The experimental results show that PFGSA performs the best on term of accuracy and stability in the parameter identification of AVR system, and the proposed identification strategy is effective. [Copyright &y& Elsevier]

Abstract: Hydraulic turbine governing system (HTGS) is a complicated nonlinear system that controls the frequency and power output of hydroelectric generating unit (HGU). The modeling of HTGS is an important and difficult task, because some components, like hydraulic turbine and governor actuator, are with strong nonlinearity. In this paper, a novel Takagi–Sugeno (T–S) fuzzy model identification method based on chaotic gravitational search algorithm (CGSA) is proposed and applied in the modeling of HTGS. In the proposed method, fuzzy c-regression model clustering algorithm is used to partition the input space and identify the coarse antecedent membership function (MF) parameters at first. And then, a novel CGSA is proposed to search better MF parameters around the coarse results, in which chaotic search has been embedded in the iteration of basic GSA to search and replace the current best solution of GSA. The performance of the proposed fuzzy model identification method is validated by benchmark problems, and the results show that the accuracies of identified models have been improved significantly compared with the other existing models. Finally, the proposed approach has been applied to approximate the dynamic behaviors of HTGS of a HGU in a hydropower station of Jiangxi Province of China. The experimental results show that our approach can identify the HTGS satisfactorily with acceptable accuracy. [Copyright &y& Elsevier]

Ultra-low frequency oscillations are the typical dynamic stability problem of hydropower-dominated power systems. Hydraulic factors can directly affect hydropower unit damping, and related studies focus on the influence of hydraulic parameters on unit damping under a fixed operation situation, while ignoring the characteristics of water diversion system topologies (WDST) and diverse hydropower operation scenarios. In this paper, some simulation models of the hydro-turbine governing system (HTGS) with a variety of WDST are first established. Then, a damping calculation method based on phase diagrams is used to calculate the damping of overall system under different WDST and operation scenarios. The results show that the increase of the number of branch pipes in WDST will deteriorate the damping characteristics and setting a surge tank can effectively increase the damping. In addition, if there is a hydraulic connection between the unit integrated into a small power grid (SPG) and the unit integrated into a large power grid (LPG), the strong stability of the LPG will increase the damping of the unit integrated into SPG. Closing some units in multi-unit HTGS will improve damping characteristics of the running unit. Some measures to suppress ULFO are proposed from the perspective of design and stable operation. • A non-linear hydro-turbine governing system model with 18 types of water diversion systems is established. • The effect of surge tanks and the number of branch pipes on damping is researched. • The effects of grid-connection types and the number of running units on damping is clarified. • Several strategies to suppress ultra-low frequency oscillations are proposed from the perspective of design and operation. [ABSTRACT FROM AUTHOR]

Improving the quality of Wind Speed Interval prediction is important to maximize the usage of integrated wind energy as well as to reduce the adverse effects of the uncertainties, introduced by the random fluctuations of wind, to the power systems. This paper utilizes independently recurrent neural network to propose two new interval prediction frameworks. This network possesses the ability to retain memory at different lengths, which is helpful in capturing temporal features, especially for multi-horizon forecasts where the local dynamics get quite involved. In the first approach, we integrated a quantile regression loss function into this network to generate the intervals. This framework however, require to train different regressors to generate the conditional quantiles. Removing this limitation, a new simple and intuitive approach, is proposed which estimates the prediction intervals using a Gaussian function centered on the prediction and estimated error by a point prediction model and an error prediction model respectively. In our computational experiments, which involve two different wind fields contributing to eight different cases, an improvement of 43% and 12%, in average coverage width criterion index, over traditional models and LSTM based model respectively is remarkable. Thus, the proposed framework is able to produce high quality PIs while simultaneously reducing the computational cost. • New models are developed for wind speed probabilistic forecasting. • Independently recurrent neural network is utilized to improve multi-horizon forecast. • Quantile regression is integrated to obtain the prediction intervals. • A simple and intuitive method is proposed to generate wind speed interval forecasts. [ABSTRACT FROM AUTHOR]

Abstract: Clustering is a popular data analysis and data mining technique. In this paper, a novel chaotic particle swarm fuzzy clustering (CPSFC) algorithm based on chaotic particle swarm (CPSO) and gradient method is proposed. Fuzzy clustering model optimization is challenging, in order to solve this problem, adaptive inertia weight factor (AIWF) and iterative chaotic map with infinite collapses (ICMIC) are introduced, and a new CPSO algorithm combined AIWF and ICMIC based chaotic local search is studied. The CPSFC algorithm utilizes CPSO to search the fuzzy clustering model, exploiting the searching capability of fuzzy c-means (FCM) and avoiding its major limitation of getting stuck at locally optimal values. Meanwhile, gradient operator is adopted to accelerate convergence of the proposed algorithm. Its superiority over the FCM algorithm and another two global optimization algorithm-based clustering methods is extensively demonstrated for several artificial and real life data sets in comparative experiments. [Copyright &y& Elsevier]

Abstract: Parameter identification of hydraulic turbine governing system (HTGS) is crucial in precise modeling of hydropower plant and provides support for the analysis of stability of power system. In this paper, a newly developed optimization algorithm, called gravitational search algorithm (GSA), is introduced and applied in parameter identification of HTGS, and the GSA is improved by combination of the search strategy of particle swarm optimization. Furthermore, a new weighted objective function is proposed in the identification frame. The improved gravitational search algorithm (IGSA), together with genetic algorithm, particle swarm optimization and GSA, is employed in parameter identification experiments and the procedure is validated by comparing experimental and simulated results. Consequently, IGSA is shown to locate more precise parameter values than the compared methods with higher efficiency. [ABSTRACT FROM AUTHOR]

Abstract: In order to build accurate model for complicated nonlinear system in engineering, like boiler–turbine system, a novel fuzzy-modeling approach is proposed, which is based on a new fuzzy c-regression model (NFCRM) clustering algorithm and is able to determine the right number of rules automatically. In this method, NFCRM is applied to build the fuzzy structure and then identify the premise parameters; a new criterion is proposed to auto determine the number of rules in fuzzy modeling; after the fuzzy rules have been decided, orthogonal least square is exploited to identify the consequent parameters. Simulation examples are given to demonstrate the validity of the proposed modeling approach, and the results show the new approach is very efficient with high accuracy. Finally, the new approach is applied in fuzzy modeling of a typical boiler–turbine system successfully. [Copyright &y& Elsevier]

Abstract: This paper proposes a novel approach for identification of Takagi–Sugeno (T–S) fuzzy model, which is based on a new fuzzy c-regression model (FCRM) clustering algorithm. The clustering prototype in fuzzy space partition is hyper-plane, so FCRM clustering technique is more suitable to be applied in premise parameters identification of T–S fuzzy model. A new FCRM clustering algorithm (NFCRMA) is presented, which is deduced from the fuzzy clustering objective function of FCRM with Lagrange multiplier rule, possessing integrative and concise structure. The proposed approach consists mainly of two steps: premise parameter identification and consequent parameter identification. The NFCRMA is utilized to partition the input–output data and identify the premise parameters, which can discover the real structure of the training data; on the other hand, orthogonal least square is exploited to identify the consequent parameters. Finally, some examples are given to verify the validity of the proposed modeling approach, and the results show the new approach is very efficient and of high accuracy. [Copyright &y& Elsevier]

[Display omitted] • A refined integration model of multi-unit hydro-turbine regulation system is established. • An accurate damping quantification evaluation for complex system is proposed. • The influence mechanism of hydraulic coupling on unit damping is studied. • The influence mechanism of electrical coupling on unit damping is studied. In hydropower dominated power systems, low-frequency oscillations (LFO), that challenge the safe and stable operation of the system, occur from time to time. Although the study of system damping is an important way to reveal the mechanism of LFO, relevant analysis is mainly based on simplified models that consider a single scale, leading to an incomplete understanding of the phenomenon. Against this background, a cluster of hydropower units in a real power station is taken in this paper as the research object. Firstly, a refined non-linear model of the hydro-turbine regulation system with the layout of three units sharing one common tailrace tunnel is established and validated based on mechanism analysis and measured data. Then, an accurate quantitative evaluation method of damping for complex systems is proposed to overcome the application limitations of traditional methods. Finally, the variation laws of the damping of a hydropower unit with the hydraulic-electrical network structures and the operating conditions, studied from the scales of hydraulic coupling and electrical coupling, respectively, reveal the influence mechanism of the hydraulic-mechanical–electrical coupling on unit damping. The results show that the increase in the complexity of the hydraulic or electrical network structure will reduce the damping of the hydropower unit, which changes from 1.3860 to −1.3223 for hydraulic factor and from 1.1869 to −0.8817 for electrical factor. The operating conditions of the adjacent units have different degrees of influence on the damping of the unit itself due to their hydraulic or electrical connections. Some measures to suppress LFO are also given. [ABSTRACT FROM AUTHOR]

[Display omitted] • A refined neural network model of hydro-turbine is established and verified. • An accurate quantitative evaluation of system damping is proposed. • The effect of operating condition on the hydraulic-mechanical damping is studied. • The relation between the control stability and damping is revealed. • The hydraulic-mechanical damping is decomposed. Hydropower is a renewable energy source with flexible and rapid regulation. Its efficient utilization is of significance in improving the stability of the electric power grid and its ability to absorb renewable energy. The current day power grid is facing security challenges due to its composition and structural changes. To understand the damping mechanism of the hydropower unit on the power grid, a new quantitative evaluation method is proposed for the analysis of the damping characteristics of the hydropower unit under full operating conditions and control parameters. In order to improve the simulation accuracy, firstly a hydro-turbine regulation system simulation platform for quantitative analysis is built and a refined hydro-turbine model using a polynomial correction neural network is proposed. Secondly, to realize the damping analysis of the hydropower unit, an accurate quantitative evaluation method based on gradient-descent algorithm is proposed. Finally, taking a large hydropower station in China as an example, damping of the hydropower unit under full operating conditions (FOC) and control parameters is computed and analyzed considering two control modes. The results show that the damping of the hydropower unit on the power grid changes from −1.1415 to 0.4402 with a certain regularity under FOC and increases with the increase of control parameters. The damping under power control mode is generally better than that under opening control mode. Conclusions drawn from an in-depth analysis of the damping mechanism of hydropower units can provide necessary theoretical guidance and application value for optimizing the operation mode of the units. [ABSTRACT FROM AUTHOR]

• A promising wind speed interval prediction method with deep learning technique is proposed. • TCNs are employed to develop a neotype interval prediction method in LUBE framework. • An interval width adaptive adjustment strategy is designed to optimize the model by directly constructing training labels. • Experimental results demonstrate the superiority of the method on prediction accuracy and reliability by comparing with the state of art methods. Wind speed interval prediction is one of the most elusive and long-standing challenges in wind power production. As a data source with intermittent and fluctuant characteristics, wind speed time series require highly nonlinear temporal features for the prediction tasks. In this paper, a novel interval prediction model is proposed based on temporal convolutional networks to forecast wind speed. A temporal convolutional networks architecture layer, multiple fully connected layers using tanh activation function and an end-to-end sorting layer are respectively served as input, hidden and output layers of the temporal convolutional networks interval prediction model which can generate prediction intervals directly. Additionally, an adaptive interval construction optimization strategy is put forward to devise training labels for learning of model. Eight cases from two wind fields are implemented to test and verify the proposed method. Specially, experiments have been designed to compare the prediction accuracy and reliability between the proposed model and the most recent state-of-the-art models. The forecasting results suggest that the proposed model has a significant performance improvement on both prediction interval coverage probability and prediction interval width criteria and thus can be a practical tool for wind speed forecasting. [ABSTRACT FROM AUTHOR]

Wind energy is a renewable energy source with great development potential. However, its inherent instability and randomness have brought great challenges to the maximum utilization of wind energy. Wind speed forecasting is one of the most effective ways to mitigate these challenges, which plays an important role in the operational management and decision-making of wind power system operators. In this study, a novel wind speed interval prediction model based on gated recurrent unit, Variational Mode Decomposition, and Particle Swarm Optimization was proposed. The original wind speed sequence was decomposed into several smoother sub-sequences through the Variational Mode Decomposition algorithm, and corresponding sub-models were established based on the gated recurrent unit. To better supervise the training process, artificial prediction intervals with adaptive adjustment strategies were devised. Moreover, the Particle Swarm Optimization algorithm was adopted to search for the optimal superposition weights of PIs to achieve the integral optimization of the model. The qualitative and quantitative performance of the proposed method has been fully tested and verified in a series of real cases. • A novel hybrid wind speed interval prediction model was proposed. • Adaptive interval construction and automatic hyperparameter tuning methods were devised. • Intelligent superposition optimization scheme was designed. • The qualitative and quantitative performance of the proposed method has been fully verified. [ABSTRACT FROM AUTHOR]

• A coupling model of VSU with nonlinear pump-turbine is established for analyzing. • The advantages of VSU avoiding running to S-shaped region are revealed and analyzed. • Quantitative comparisons are carried out to show the advantages of VSU. Pumped storage units (PSU) as the most efficient energy storage device (ESD) play an important role in absorbing renewable energy (RE) sources. Nevertheless, pump-turbines have inherent S-shaped characteristics caused by their reversible design which seriously threaten the operation stability of PSU. In recent years, the variable-speed pumped storage units (VSU) have been proposed as an alternative to the fixed-speed pumped storage units (FSU). Therefore, it is a meaningful subject to evaluate the operation advantage of VSU, which has not been adequately quantified. This paper aims to analyse the advantages of VSU in operation stability by revealing the mechanism of avoiding trapping in the S-shaped region. Firstly, a precise coupling model for VSU with nonlinear pump-turbine characteristics is established and the operation areas in turbine mode are analysed. Then, the mechanism of how the trap of S-shaped region could be avoided is revealed and the regulation performance of the control system is quantified by comparing with FSU. Based on a real Chinese VSU, three scenarios are studied, including turbine start-up process, power regulation and turbine closing process. The results indicate that the S-shaped region could be escaped effectively by operating the VSU. The periodic oscillations times and setting time index of rotational speed in turbine start-up process are 0.5 and 20.74 s respectively, which are much smaller than the values of FSU. VSU outperforms the FSU in the aspect of power regulation performance: much smaller average and standard deviation of power difference for wind and load disturbance. Moreover, VSU can also obtain a significantly higher assessment in closure process: the maximum water pressure deviation is only 40% of FSU. [ABSTRACT FROM AUTHOR]

Inter type-2 fuzzy model has been confirmed to be more effective in Takagi–Sugeno (T–S) fuzzy model identification compared to type-1 fuzzy model. It is indisputable that some algorithms based on inter type-2 fuzzy model have already been developed and shown remarkable modeling performance. To further improve the modeling accuracy, the optimization methods and the neural network are taken into consideration. In this paper, an evolving modified inter type-2 fuzzy c-regression model (MIT2-FCRM) algorithm based on gravitational search algorithm (GSA) and a consequent parameter identification method based on extreme learning machine algorithm with forgetting factor for processing online sequences (namely WOS-ELM) were proposed. Then a novel approach for T–S fuzzy modeling was presented, in which, the coefficients of the upper and lower hyperplanes were obtained by evolving MIT2-FCRM algorithm based on GSA, a hyper-plane-shaped membership function (MF) was utilized to identify the antecedent parameters of the T–S fuzzy model, and WOS-ELM was employed to identify the consequent parameters. The modeling results of six examples indicate that the proposed approach is superior to other studies in terms of identification accuracy, compact fuzzy rules and noise resistance ability. [ABSTRACT FROM AUTHOR]

As an extensively applied signal decomposition method, Variational Mode Decomposition (VMD) has many favorable characteristics for addressing signals with noise interference. However, the requirement of presetting modal number K and balancing parameter α makes this method difficult to use in some cases where prior knowledge of the analyzed signal cannot be acquired. In this paper, a modified VMD method (MVMD) is proposed to overcome this drawback. First, an envelope nesting method is adopted to preliminarily guide the latent central frequencies. Then, a Permutation Entropy and orthogonality-based modal number adjusting process is conducted, after which the modal number can be determined. Finally, a coarse-to-fine search procedure aiming at the optimal α value is carried out, under the guidance of a multi-criteria target function. The effectiveness and practicability of the proposed method have been proven by experiments which adopt a synthetic signal and three different kinds of fault-bearing vibration signals. A comparison between the proposed method and conventional methods has been made to demonstrate the superiority of the proposed MVMD method on the accuracy of modal number estimation, the independence of individual modes and the robustness of decomposition under heavy noise conditions. [ABSTRACT FROM AUTHOR]

• A refined nonlinear model of PSHSs under successive load rejection is established. • Proposing a control scheme optimization strategy for successive load rejections. • Successive load rejection parameters have significant impact on the transient process. • The optimized control scheme is applicable to various working conditions. • The work can strongly support the safe operation of pumped storage hydropower stations. Pumped hydropower is the most important sustainable energy in a power grid, which is converted into electricity through pumped storage hydropower systems. The energy conversion process in a pumped storage hydropower system, however, may be greatly threatened by extreme energy conversion conditions, especially successive load rejections. Although successive load rejections have been addressed in previous studies, the optimal control scheme for successive load rejections has not yet been reported. In this study, a refined nonlinear model for successive load rejections is constructed by incorporating a guaranteed calculation for regulation (GCR), and the effects of the rejection parameters on the transient processes of pumped storage hydropower systems are investigated quantitatively based on the refined model. The results show that: (1) the rejection parameters significantly impact the successive load rejections, and the worst working condition of a successive load rejection can be identified by the worst combination of rejection parameters; (2) the rotational speed and the water pressure of the pump storage unit are conflicting objectives with variation in the control schemes. Moreover, a novel two-stage multi-objective optimization strategy for the optimal control scheme of pumped hydropower systems is proposed and a case study is conducted based on a real pumped storage hydropower system in China. Compared with the on-site measurements, the proposed optimization strategy can improve the maximum volute water pressure and the minimum draft tube water pressure by at most 7.6% and 17.4% under the worst working condition of a successive load rejection. Furthermore, it is verified that the obtained optimal control scheme meets the GCR criterion under various working conditions that are not the worst case. These results highlight the effectiveness and availability of the proposed optimization strategy for sustaining the safe operation of pumped storage hydropower systems. [ABSTRACT FROM AUTHOR]

With increasing share of renewable energy (RE) in power system, the unit commitment of hybrid power system have become more complicated due to network security demand and integration of pumped hydro energy storage (PHES). In this paper, a network-constrained unit commitment (NCUC) problem considering RE uncertainty and modulation of PHES has been raised. The NCUC model, with AC network security constraints and environmental constraints as well as traditional terms of constraints, is complicated to be solved. A novel Binary Artificial Sheep Algorithm (BASA) is used to solve the NCUC model. In the frame of BASA, the NCUC problem is decomposed as a master UC problem to determine start/stop status and economic load dispatch and a sub problem to check the AC network constraints. Based on the NCUC model and the solving method, the joint impacts of RE uncertainty and PHES have been studied. Test systems with different size have been adopted to verify the feasibility and effectiveness of the BASA. It is seen that the BASA has achieve an overall competitive performance on terms of operation cost and convergence speed by comparing it with existing methods. A modified IEEE 30-bus system with wind and photovoltaic power stations has been designed to reveal the impacts of RE and PHES. The results demonstrate that uncertainty of RE affects operation cost and security of the hybrid power system, and the adverse impact would aggravate as the RE forecasting error increase. The results also confirm the significant effect of PHES in restraining the negative influence of RE uncertainty. • The NCUC problem consisting of RE uncertainty and PHES has been studied. • A decomposition method based on BASA is designed to solve the NCUC problem. • Network constraints based on AC power flow are checked. • Joint impact of RE uncertainty and PHES has been analyzed quantificationally. [ABSTRACT FROM AUTHOR]

The combined operation of renewable energy and pumped storage unit (PSU) has become an important researching tendency in rural electrification, for handling the variable characteristics of power as well as load demand, particularly in standalone applications. Recently, adjustable-speed pumped storage unit (ASU) has been developed as an evolutionary version of fixed-speed pumped storage unit (FSU) due to its adjustable power in pumping mode, larger output range and higher efficiency in generating mode, but presents an increased capital outlay in terms of equipment. Therefore, it is a meaningful topic to appraise the economic benefit of using ASU as energy storage device for the hybrid system, which has rarely been studied quantitatively. In this paper, a scheduling model composed of a photovoltaic generator, a wind turbine, a diesel generator and a PSU, is presented and the technical features of two different PSUs are analysed. The main purpose of the proposed model is to highlight the potential of the ASU to reduce the operation cost for the developed hybrid system. The simulations have been carried out using Cplex called by Matlab. Two scenarios are investigated, including a summer and a winter case. The results show that using the ASU for the developed hybrid system, 46.7% fuel can be saved on a summer day and 11.24% fuel saving can be achieved on a winter day compared to the case where the FSU is used as the energy storage device. [ABSTRACT FROM AUTHOR]

This study presents a two-step fault diagnosis scheme combined with statistical classification and random forests-based classification for rolling element bearings. Considering the inequality of features sensitivity in different diagnosis steps, the proposed method utilizes permutation entropy and variational mode decomposition to depict vibration signals under single scale and multiscale. In the first step, the permutation entropy features on the single scale of original signals are extracted and the statistical classification model based on Chebyshev's inequality is constructed to detect the faults with a preliminary acquaintance of the bearing condition. In the second step, vibration signals with fault conditions are firstly decomposed into a collection of intrinsic mode functions by using variational mode decomposition and then multiscale permutation entropy features derived from each mono-component are extracted to identify the specific fault types. In order to improve the classification ability of the characteristic data, the out-of-bag estimation of random forests is firstly employed to reelect and refine the original multiscale permutation entropy features. Then the refined features are considered as the input data to train the random forests-based classification model. Finally, the condition data of bearings with different fault conditions are employed to evaluate the performance of the proposed method. The results indicate that the proposed method can effectively identify the working conditions and fault types of rolling element bearings. [ABSTRACT FROM AUTHOR]

In view of the complex and changeable operating environment of pumped storage power stations and the noise and outliers in the modeling data, this study proposes a sparse robust least squares support vector machine (LSSVM) model based on the hybrid backtracking search algorithm for the model identification of a pumped turbine governing system. By introducing the maximum linearly independent set, the sparsity of the support vectors of the LSSVM model are realized, and the complexity is reduced. The robustness of the identification model to noise and outliers is enhanced using the weighted function based on improved normal distribution. In order to further improve the accuracy and generalization performance of the sparse robust LSSVM identification model, the model input variables, the kernel parameters, and the regularization parameters are optimized synchronously using a binary-real coded backtracking search algorithm. Experiments on two benchmark problems and a real-world application of a pumped turbine governing system in a pumped storage power station in China show that the proposed sparse robust LSSVM model optimized by the hybrid backtracking search algorithm can not only obtain higher identification accuracy, it also has better robustness and a higher generalization performance compared with the other existing models. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-objective optimization method for the start-up strategy of pumped storage units (PSU) for the first time. In the multi-objective optimization method, the speed rise time and the overshoot during the process of the start-up are taken as the objectives. A precise simulation platform is built for simulating the transient process of start-up, and for calculating the objectives based on the process. The Multi-objective Particle Swarm Optimization algorithm (MOPSO) is adopted to optimize the widely applied start-up strategies based on one-stage direct guide vane control (DGVC), and two-stage DGVC. Based on the Pareto Front obtained, a multi-objective decision-making method based on the relative objective proximity is used to sort the solutions in the Pareto Front. Start-up strategy optimization for a PSU of a pumped storage power station in Jiangxi Province in China is conducted in experiments. The results show that: (1) compared with the single objective optimization, the proposed multi-objective optimization of start-up strategy not only greatly shortens the speed rise time and the speed overshoot, but also makes the speed curve quickly stabilize; (2) multi-objective optimization of strategy based on two-stage DGVC achieves better solution for a quick and smooth start-up of PSU than that of the strategy based on one-stage DGVC. [ABSTRACT FROM AUTHOR]

• OVMD is achieved with center frequency observation method and proposed LSEI index. • SSA and PSR are implemented to realize dominant ingredient chaotic analysis. • An improved hybrid GWO-SCA (IHGWOSCA) is proposed for parameters optimization. • Parameters of PSR and ELM are optimized by IHGWOSCA with two coding strategies. • Superiority of the proposed approach is verified by contrastive experiments. Accurate wind speed prediction possesses a significant impact on reasonable scheduling and safe operation of power system. For this purpose, a novel hybrid approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA (IHGWOSCA) algorithm and extreme learning machine (ELM) is proposed for multi-step short-term wind speed prediction, in which the multi-scale dominant ingredient chaotic analysis combines the proposed optimal variational mode decomposition (OVMD), singular spectrum analysis (SSA) and phase space reconstruction (PSR). To begin with, the mode number and updating step of VMD are pre-determined by center frequency observation method and the proposed least-squares error index (LSEI), thus decomposing the non-stationary wind speed series into a set of intrinsic mode functions (IMFs). Later, the extraction of the dominant ingredient and residuary ingredient for each sub-series is implemented by SSA for the construction of forecasting components. Subsequently, the proposed IHGWOSCA algorithm coded with discrete integers and real-valued are investigated to search optimal parameters in PSR and ELM successively. Lastly, the ultimate forecasting results of the original wind speed are calculated by accumulating results of all the predicted components. Furthermore, seven data sets from Sotavento Galicia and Inner Mongolia have been employed to evaluate the proposed approach. The results illustrate that: (1) the proposed OVMD-based models obtained better RMSE, MAE and MAPE indexes comparing with the benchmark models through weakening the non-stationary of the original signal; (2) the proposed dominant ingredient chaotic analysis combining SSA and PSR enhanced the multi-steps prediction performance effectively; (3) the proposed IHGWOSCA optimization algorithm possessed good capability for optimal parameters searching and fast convergence. [ABSTRACT FROM AUTHOR]

Wind power (WP) interval prediction has attracted more and more attention in recent years due to WP's intermittency and uncertainty. However, traditional interval prediction models suffer from data distribution assumptions, fixed interval widths, etc. This paper proposes a hybrid WP interval prediction method to eliminate these constraints. First, the mean impact value is applied to select the optimal inputs from meteorological factors, which are considered together with the WP data. Then, we propose a time-varying interval optimization strategy to construct prediction intervals (PIs) and avoid the restrictive condition of data distribution, which can provide a time-varying interval width simultaneously. Meanwhile a convolutional gated recurrent unit is performed to extract the spatial-temporal features and generates the prediction results. Based on these results, the final PIs are generated by the proposed multi-objective elephant clan optimization, in which three objectives are optimized simultaneously. To evaluate the performance of the proposed model, two WP datasets in Ningxia, China, are used. Finally, the obtained PIs are applied for decision-making to offer planned productions in the future and estimate the operational costs. The comparison results indicate that the proposed model can provide high-quality PIs and achieve lower operational costs than the benchmark models in decision-making. • A novel MIV-CGRU-MOECO method is proposed for wind power interval prediction. • A time-varying interval optimization strategy is proposed to construct PIs. • CGRU is used to capture temporal-spatial features of the data. • MOECO algorithm is proposed to balance the conflicting objectives. • Applications in decision-making is discussed based on the obtained PIs. [ABSTRACT FROM AUTHOR]

Reliable wind speed forecasting is essential for wind power integration in wind power generation system. The purpose of paper is to develop a novel hybrid model for short-term wind speed forecasting and demonstrates its efficiency. In the proposed model, a compound structure of extreme learning machine (ELM) based on feature selection and parameter optimization using hybrid backtracking search algorithm (HBSA) is employed as the predictor. The real-valued BSA (RBSA) is exploited to search for the optimal combination of weights and bias of ELM while the binary-valued BSA (BBSA) is exploited as a feature selection method applying on the candidate inputs predefined by partial autocorrelation function (PACF) values to reconstruct the input-matrix. Due to the volatility and randomness of wind speed signal, an optimized variational mode decomposition (OVMD) is employed to eliminate the redundant noises. The parameters of the proposed OVMD are determined according to the center frequencies of the decomposed modes and the residual evaluation index (REI). The wind speed signal is decomposed into a few modes via OVMD. The aggregation of the forecasting results of these modes constructs the final forecasting result of the proposed model. The proposed hybrid model has been applied on the mean half-hour wind speed observation data from two wind farms in Inner Mongolia, China and 10-min wind speed data from the Sotavento Galicia wind farm are studied as an additional case. Parallel experiments have been designed to compare with the proposed model. Results obtained from this study indicate that the proposed hybrid model can provide an effective modeling approach to capture the nonlinear characteristics of wind speed signal and thus providing more satisfactory forecasting results. [ABSTRACT FROM AUTHOR]

The vibration signals from defective rolling bearings are multi-component amplitude modulation (AM)-frequency modulation (FM) signals. Traditional envelope analysis method is based on a filter. The centre frequency and bandwidth of the filter are set according to experience. So the filter method will induce a demodulation error. This research proposes a rolling bearing fault diagnosis method based on adaptive local iterative filtering (ALIF) and envelope spectrum. The ALIF method is a new method for the analysis of non-stationary signals. It uses an iterative filters strategy together with an adaptive, data-driven filter length selection to achieve the necessary decomposition. Smooth filters with compact support from the solutions of the Fokker–Planck equations are used within the ALIF method. The ALIF method offers good performance in obtaining more accurate components of non-stationary signals and in suppressing mode mixing. The ALIF method can decompose a multi-component AM-FM signal into a number of stationary components. The envelope demodulation method is used to analyse those components containing fault information which, in turn, can reveal bearing fault features. The vibration signals from a rolling bearing with an outer race fault and an inner race fault are used to verify the proposed method. The results show that this method can effectively extract bearing fault features. [ABSTRACT FROM AUTHOR]