GM(1,1) forecasting method for day-ahead electricity price based on moving average and particle swarm optimization

Under deregulated environment, accurate price forecasting provides crucial information for electricity market participants to make reasonable competing strategies. With comprehensive consideration of the changing rules of the day-ahead electricity price of the PJM electricity market, a day-ahead electricity price forecasting method based on particle swarm optimization (PSO) and GM(1, 1) model is proposed, in which the moving average method is used to process the raw data of electricity price series, and then the equal-dimension and new-information GM(1, 1) model is used to the processed series and the PSO is used to minimize the weighted mean absolute percent error to further optimize the grey background value. The numerical example based on the historical data of the PJM market from July to September in 2007 shows that the method can reflect the characteristics of electricity price better and the forecasting accuracy can be improved virtually compared with the conventional GM(1, 1) model. The forecasted prices accurate enough to be used by electricity market participants to prepare their bidding strategies.