基于分解{ - 优化 - 集成学习方法的电价预测

The accurate forecasting of electricity price, which is an indispensable indicator of the current market situation, can help market players avoid risks and maximize economic profits as the electricity market undergoes continuous development and reform. This study aims to propose decomposition-optimization-ensemble (DOE), which is a new hybrid approach, for the predicting electricity price data in the power market. First, we decomposed electricity price data into a series of intrinsic mode functions and a residual sequence using the fast ensemble empirical mode decomposition method. Next, we optimized the convergence speed, accuracy, and searching ability of the whale optimization algorithm. We then used the improved whale optimization algorithm to optimize the expansion coefficient of the RBF neural network. The improved model was used to predict the values of intrinsic mode functions and the residual sequence. Finally, we applied the ensemble method to calculate the final predicted values of the original electricity price data. We performed mid-long-term and short-term predictions with the electricity price data of the PJM electricity market in the United States to verify the forecasting performance of the DOE model. The empirical results showed that the DOE model can achieve high accuracy in both horizontal and directional precisions.