Short-term load forecasting based on MA-LSSVM

Abstract

Aiming at the problems of low accuracy and poor accuracy of short-term load forecasting (STLF), monkey algorithm (MA) and least square support vector machine (LSSVM) are combined for STLF. The input factors of the model are load data and meteorological information. MA is used to optimize the kernel function parameter σ and the regularization parameter λ of LSSVM to obtain the optimal solution of the least square support vector machine prediction model. Then a STLF model was established.