Power load forecasting based on Improved Grey Model of particle swarm optimization

摘要

Grey theory plays a very important role in the field of power load forecasting. In order to improve the forecasting accuracy of medium and long-term power load data, an improved grey model forecasting method based on particle swarm optimization is proposed. First of all, the data transformation technology is used to reduce the prediction error of discrete data using continuous function model in the prediction process. Then the Markov prediction model is used to predict the best state interval. Through particle swarm optimization algorithm, the parameters of the state interval are optimized, and then the prediction results are modified. The method is applied to the load forecasting of Sichuan Province from 2010 to 2011, and the results verify the superiority of the method in accuracy.