Short term load forecasting based on the particle swarm optimization with simulated annealing

This paper presented an artificial neural network (ANN) method based on the particle swarm optimization (PSO) and simulated annealing (SA) for load forecasting. Using the modified PSO with SA train the ANN network and facilitate the tuning of the optimal network weight and threshold. The ANN network has a better ability to escape from the local optimum and is more effective than the conventional PSO-based ANN. Then use the network to forecast the daily load. Simulation example shows that the proposed approach has good accuracy.