Electricity Market Price Prediction Based on Differential Evolutionary Algorithm and Neural Network

Abstract

In order to obtain a practical and high-precision prediction method of the clearing price in the spot market of electric power, this paper tries to apply the neural network optimized by differential evolutionary algorithm to the prediction of the clearing price in the spot market. Firstly, the weights and thresholds of BP neural network are optimized based on differential evolutionary algorithm, and then the BP neural network model is used to test on the basis of the PJM spot market data in the United States. The experiment shows that the prediction accuracy of the proposed method is improved obviously and the prediction effect is stable.