Short-term Load Combination Forecasting Model Based on Causality Mining of Influencing Factors

Abstract

With the continuous development of the reform of the power market system, the operation of the power system is becoming more flexible and uncertain, and the traditional load forecasting method is difficult to cope with more influencing factors and stronger randomness. To solve this problem, a short-term load combination prediction model based on causal relationship mining of influencing factors is proposed in this paper. Firstly, the historical load series is decomposed into three components by using Optimal Variational Mode Decomposition (OVMD). Then, the Granger causality algorithm is used to mine the influencing factors closely related to each wave type load. Finally, a short-term load combination prediction model based on causality mining is established. Simulation results show that the proposed short-term load forecasting method can significantly improve the accuracy of short-term load forecasting.