SHORT TERM LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORK: A COMPARISON WITH GENETIC ALGORITHM IMPLEMENTATION

Accurate load forecasting holds a great saving potential for electric utility corporations since it determines its main source of income, particularly in the case of distributors. Precise load forecasting helps the electric utility to make unit commitment decisions, reduce spinning reserve capacity and schedule device maintenance plan properly. It is therefore necessary that the electricity generating organizations should have prior knowledge of future demand with great accuracy. Some data mining algorithms play the greater role to predict the load forecasting. This research work examines and analyzes the use of artificial neural networks (ANN) and genetic algorithm (GA) as forecasting tools for predicting the load demand for three days ahead and comparing the results. Specifically, the ability of neural network (NN) models and genetic algorithm based neural networks (GA-NN) models to predict future electricity load demand is tested by implementing two different techniques such as back propagation algorithm and genetic algorithm based back propagation algorithm (GA-BPN).