BP Neural Network Optimized with PSO Algorithm for Daily Load Forecasting

Accurate forecasting of daily electricity load has been one of the most important issues in the electricity industry. In recent few decades, the artificial neural network has been successfully employed to solve this problem because of the powerful capability to generalize the nonlinear relationships between the inputs and the desired outputs, without considering real problem domain expressions. A short-term load forecasting method based on BP neural network which is optimized by particle swarm optimization (PSO) algorithm is presented in this paper. The PSO is used to optimize the initial parameters of the BP neural network, then based on the optimized result, the BP neural network is used for short-term load forecasting. The experiment results show the method in the paper has greater improvement in both accuracy and velocity of convergence for BP neural network. Consequently, the model is practical and effective and provides a alternative for forecasting electricity load.