Mid-long term power load forecasting based on MG-CACO and SVM method

To improve the accuracy of power load forecasting, a new model for load forecasting based on support vector machine and continuous ant colony optimization algorithm is established in this paper. A new continuous ant colony optimization algorithm called MG-CACO is used to optimize the parameters of SVM in this model. Then the case study of SVM base on continuous ant colony optimization algorithm to a mid-long term load prediction of an actual power system of Tianjin is proposed. Forecasting result shows that this method can improve the accuracy and speed in forecasting, and that the feasibility and effectiveness in the mid-long term forecasting.