Improved grey neural network based short-term electricity price forecast method considering gas-electricity price linkage

Under the background of global low-carbon transition, the coupling relationship between natural gas market and electricity market is getting closer and closer. In recent years, global natural gas price and electricity price risk events occur frequently, which makes the short-term electricity price forecast considering the linkage between natural gas and electricity price is of great significance to deal with the price crisis. Given this background, an improved model of short-term electricity price forecast based on grey neural network is proposed. Firstly, the principal component analysis is carried out on the historical data of natural gas and electricity prices to reduce the redundancy between the data and obtain new synthetic variables. Then, taking the principal component analysis of synthetic variables as the input to improve the effectiveness of the training data set, the gray neural network model is used to obtain the forecast results of electricity price. Finally, case studies on the historical data of the electricity price in the United States are performed to verify the effectiveness of the proposed models, and the results show that the improved electricity price forecasting model has higher precision and significantly improves the forecast of the trend change of electricity price.