Forecasting Power Demand Using Artificial Neural Networks for Sri Lankan Electricity Power System

Abstract

Accurate models for electric power load forecasting are essential to the operation and planning of an electricity company. Neural Networks are considered as a com- putational model that is capable of doing non linear curve tting. In this research, the application of neural networks to study the design of Short Term Load Fore- casting (STLF) Systems for Sri Lanka was explored. Three layered neural network architecture with back propagation algorithm is proposed to model STLF. Network is trained and tested using two years data which was gathered from the Ceylon Electricity Board. E ect of the momentum factor to the forecast, optimum number of hidden neurons that included in the neural network and the other parameters are analyzed in this research to nd out the best neural network architecture for accurate load forecasting. The results show that MLP network has the minimum forecasting error than the statistical models, and can be considered as an a e ective method to model the STLF systems for Sri Lankan electricity power system.