Short-term load forecasting based on least square support vector machine combined with fuzzy control

摘要

A short-term load forecasting method based on least square support vector machine(LS-SVM) combined with fuzzy control was proposed. The peak load and valley load was forecasted by LS-SVM model which was built by analysis of load data and meteorological data. Then the peak load and valley load was tuned by fuzzy rules which has been built by forecasting error data. One day and one week ahead load has been got by combing peak load and valley load with similar day load change coefficient. The load data and meteorological data of Shan Dong electrical company of 2008 was utilized to test the forecasting model. The simulation result shows the proposed method can improve the predicting accuracy.