Short Term Load Forecasting Using a Hybrid Neural Network

Artificial neural network (ANN) training is one of the major challenges in using a prediction model for short term load forecasting. But slow convergence rate and falling intolocal minimum, limits its application and accuracy. To overcome the defects of neural network (NN) using back-propagationalgorithm (BPNN), the particle swarm optimization (PSO) algorithm was adopted to optimize BPNN model for short-term load forecasting (SLTF). PSO was used to optimize initial weightsand thresholds of BPNN model because the major defects of BPNN are partly caused by the random selection of network’sinitial value. In this paper the ability of metaheuristics and greedy gradient based algorithms are combined to obtain ahybrid improved opposition based particle swarm optimization and a back propagation algorithm with the momentum term foraccurate short term load forecasting. The simulation results ofdaily and weekly loads forecasting for actual power system show that the proposed forecasting model can effectively improve the accuracy of SLTF model. Furthermore, its forecasting performance is far better than that of simple BPNN model.

کلیدواژه ها:

Short term load forecasting ، Neural network ، Particle swarm optimization