1.College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;2.Guangzhou Power Supply Bureau of Guangdong Power Grid Co., Ltd., Guangzhou 510600, China
To better manage the demand response resources on user side and reduce ultra-short-term load forecasting error, an ultra-short-term load forecasting method considering the demand response in the load aggregator mode is proposed. Firstly, the demand response mechanism of load aggregator is analyzed. Considering the energy usage habits of users, self-built photovoltaics, energy storage behavior and electro-thermal coupling, the optimization model for each type of demand response resources is established. Also, the uncertainty of user participation in demand response is denoted by fuzzy parameters to improve the optimization model. The demand response signal after the integration of various resources is obtained by using CPLEX solver. Then, based on the historical load data, a long short-term memory network model for iterative prediction is established with the demand response signal. After the comparison of three prediction scenarios, the example verifies that the prediction error can be effectively reduced considering demand response signal, and the prediction accuracy can be further improved considering the uncertainty of demand response.
This work is supported by National Natural Science Foundation of China (No. 51877190).
|||GUO Yizong, FENG Bin, YUE Boxiong, et al. Ultra-short-term Load Forecasting Considering Demand Response in Load Aggregator Mode[J]. Automation of Electric Power Systems,2021,45(1):79-87. DOI:10.7500/AEPS20200330014|