To search, Click below search items.


All Published Papers Search Service


An Efficient Hybrid Model to Load Forecasting


Khairul Hasan, Mohammad Asif A Khan, Suman Ahmmed, Ahmed Yousuf Saber


Vol. 10  No. 8  pp. 61-68


This paper presents a new hybrid approach of Neural Network (NN) along with Particle Swarm Optimization (PSO), hereafter called NN?PSO, to resolve the short?term load forecasting (STLF) tasks with improved generalization technique for the Regional Power Control Center of Saudi Electricity Company, Western Operation Area (SEC-WOA), The strength of this powerful technique lies in its ability to forecast accurately on weekdays, as well as, on weekends and holidays. In this research paper, first prediction is made by NN and then PSO is applied to optimize the prediction and thus improve its accuracy. NN is an effective mathematical tool for mapping complex relationships. It is also successful for doing forecasting, categorization, classification, and so forth. On the other hand, PSO is a novel random optimization method based on swarm intelligence, which has been found to be powerful in solving nonlinear optimization problems. It has better balance of local and global searching abilities and can handle huge multidimensional optimization problems efficiently with hundreds of thousands of constraints. PSO is applied to optimize the weighting factors of NN. To combine with NN, Particle Swarm Optimization has been proposed here to attain better performances. To evaluate the proposed NN-PSO algorithm it is applied on the real data set of SEC-WOA for the year 2003. The test results show that the proposed NN-PSO performs better and consistent with respect to only NN for most of the cases in load forecasting.


Back-propagation, heuristic, neural network, particle swarm optimization