This paper covers predicting high-resolution electricity peak demand features given lower-resolution data.This is a relevant setup as it answers whether limited higher-resolution monitoring helps to estimate future hi...This paper covers predicting high-resolution electricity peak demand features given lower-resolution data.This is a relevant setup as it answers whether limited higher-resolution monitoring helps to estimate future high-resolution peak loads when the high-resolution data is no longer available.That question is particularly interesting for network operators considering replacing high-resolution monitoring by predictive models due to economic considerations.We propose models to predict half-hourly minima and maxima of high-resolution(every minute)electricity load data while model inputs are of a lower resolution(30 min).We combine predictions of generalized additive models(GAM)and deep artificial neural networks(DNN),which are popular in load forecasting.We extensively analyze the prediction models,including the input parameters’importance,focusing on load,weather,and seasonal effects.The proposed method won a data competition organized by Western Power Distribution,a British distribution network operator.In addition,we provide a rigorous evaluation study that goes beyond the competition frame to analyze the models’robustness.The results show that the proposed methods are superior to the competition benchmark concerning the out-of-sample root mean squared error(RMSE).This holds regarding the competition month and the supplementary evaluation study,which covers an additional eleven months.Overall,our proposed model combination reduces the out-of-sample RMSE by 57.4%compared to the benchmark.展开更多
Grid-level large-scale electrical energy storage(GLEES) is an essential approach for balancing the supply–demand of electricity generation, distribution, and usage. Compared with conventional energy storage methods, ...Grid-level large-scale electrical energy storage(GLEES) is an essential approach for balancing the supply–demand of electricity generation, distribution, and usage. Compared with conventional energy storage methods, battery technologies are desirable energy storage devices for GLEES due to their easy modularization, rapid response, flexible installation, and short construction cycles. In general, battery energy storage technologies are expected to meet the requirements of GLEES such as peak shaving and load leveling, voltage and frequency regulation, and emergency response, which are highlighted in this perspective. Furthermore, several types of battery technologies, including lead–acid, nickel–cadmium, nickel–metal hydride, sodium–sulfur, lithium-ion, and flow batteries, are discussed in detail for the application of GLEES. Moreover, some possible developing directions to facilitate efforts in this area are presented to establish a perspective on battery technology, provide a road map for guiding future studies, and promote the commercial application of batteries for GLEES.展开更多
Distribution networks are commonly used to demonstrate low-voltage problems.A new method to improve voltage quality is using battery energy storage stations(BESSs),which has a four-quadrant regulating capacity.In this...Distribution networks are commonly used to demonstrate low-voltage problems.A new method to improve voltage quality is using battery energy storage stations(BESSs),which has a four-quadrant regulating capacity.In this paper,an optimal dispatching model of a distributed BESS considering peak load shifting is proposed to improve the voltage distribution in a distribution network.The objective function is to minimize the power exchange cost between the distribution network and the transmission network and the penalty cost of the voltage deviation.In the process,various constraints are considered,including the node power balance,single/two-way power flow,peak load shifting,line capacity,voltage deviation,photovoltaic station operation,main transformer capacity,and power factor of the distribution network.The big M method is used to linearize the nonlinear variables in the objective function and constraints,and the model is transformed into a mixed-integer linear programming problem,which significantly improves the model accuracy.Simulations are performed using the modified IEEE 33-node system.A typical time period is selected to analyze the node voltage variation,and the results show that the maximum voltage deviation can be reduced from 14.06%to 4.54%.The maximum peak-valley difference of the system can be reduced from 8.83 to 4.23 MW,and the voltage qualification rate can be significantly improved.Moreover,the validity of the proposed model is verified through simulations.展开更多
文摘This paper covers predicting high-resolution electricity peak demand features given lower-resolution data.This is a relevant setup as it answers whether limited higher-resolution monitoring helps to estimate future high-resolution peak loads when the high-resolution data is no longer available.That question is particularly interesting for network operators considering replacing high-resolution monitoring by predictive models due to economic considerations.We propose models to predict half-hourly minima and maxima of high-resolution(every minute)electricity load data while model inputs are of a lower resolution(30 min).We combine predictions of generalized additive models(GAM)and deep artificial neural networks(DNN),which are popular in load forecasting.We extensively analyze the prediction models,including the input parameters’importance,focusing on load,weather,and seasonal effects.The proposed method won a data competition organized by Western Power Distribution,a British distribution network operator.In addition,we provide a rigorous evaluation study that goes beyond the competition frame to analyze the models’robustness.The results show that the proposed methods are superior to the competition benchmark concerning the out-of-sample root mean squared error(RMSE).This holds regarding the competition month and the supplementary evaluation study,which covers an additional eleven months.Overall,our proposed model combination reduces the out-of-sample RMSE by 57.4%compared to the benchmark.
文摘Grid-level large-scale electrical energy storage(GLEES) is an essential approach for balancing the supply–demand of electricity generation, distribution, and usage. Compared with conventional energy storage methods, battery technologies are desirable energy storage devices for GLEES due to their easy modularization, rapid response, flexible installation, and short construction cycles. In general, battery energy storage technologies are expected to meet the requirements of GLEES such as peak shaving and load leveling, voltage and frequency regulation, and emergency response, which are highlighted in this perspective. Furthermore, several types of battery technologies, including lead–acid, nickel–cadmium, nickel–metal hydride, sodium–sulfur, lithium-ion, and flow batteries, are discussed in detail for the application of GLEES. Moreover, some possible developing directions to facilitate efforts in this area are presented to establish a perspective on battery technology, provide a road map for guiding future studies, and promote the commercial application of batteries for GLEES.
基金This work was supported by the Science and Technology Project of State Grid Corporation of China“Intelligent Coordination Control and Energy Optimization Management of Super-large Scale Battery Energy Storage Power Station Based on Information Physics Fusion-Simulation Model and Transient Characteristics of Super-large Scale Battery Energy Storage Power Station”(No.DG71-18-009).
文摘Distribution networks are commonly used to demonstrate low-voltage problems.A new method to improve voltage quality is using battery energy storage stations(BESSs),which has a four-quadrant regulating capacity.In this paper,an optimal dispatching model of a distributed BESS considering peak load shifting is proposed to improve the voltage distribution in a distribution network.The objective function is to minimize the power exchange cost between the distribution network and the transmission network and the penalty cost of the voltage deviation.In the process,various constraints are considered,including the node power balance,single/two-way power flow,peak load shifting,line capacity,voltage deviation,photovoltaic station operation,main transformer capacity,and power factor of the distribution network.The big M method is used to linearize the nonlinear variables in the objective function and constraints,and the model is transformed into a mixed-integer linear programming problem,which significantly improves the model accuracy.Simulations are performed using the modified IEEE 33-node system.A typical time period is selected to analyze the node voltage variation,and the results show that the maximum voltage deviation can be reduced from 14.06%to 4.54%.The maximum peak-valley difference of the system can be reduced from 8.83 to 4.23 MW,and the voltage qualification rate can be significantly improved.Moreover,the validity of the proposed model is verified through simulations.
