Abstract: This study presents a new approach for short term - daily peak load forecasting using Particle Swarm Optimization based Combinations of Artificial Neural Network (PSOCANN) modules. In this study, a set of neural networks has been trained with different architecture and with different training parameters. The Artificial Neural Networks (ANNs) are trained and tested for the actual load data of Chennai city (India). A method of optimal linear combination is used to combine selected networks to produce better results, rather than using a single best trained ANN. The obtained test results indicate that the proposed method of approach improves the accuracy of the load forecasting.
P. Subbaraj and V. Rajasekaran , 2007. PSO Based Combinations of ANNs for Short Term-Daily Peak Load Forecasting. Asian Journal of Information Technology, 6: 154-159.