Short Term Load Forecasting Using Neural Networks and Particle Swarm Optimization
Main Article Content
Abstract
Accurate models for electric power load forecasting are essential to the operation and planning of a utility company. A precise electric power system short term load forecasting will lead to economic cost saving and right decisions on generating electric power. In this paper, a short-term load forecasting (STLF) method based on back propagation (BP) neural networks which is optimized by particle swarm optimization (PSO) algorithm is presented. The PSO is used to optimize the initial parameters of the BP neural networks, and then based on the optimized results; the BP neural networks are used for short-term load forecasting. The results obtained show that the proposed technique has improved the accuracy and velocity of convergence of the BP neural networks method. Also it is shown that the proposed method can provide more accurate results than the back propagation (BP) neural networks techniques. The mean percent relative error of the BP neural network optimized by PSO model is less than 2 %.