Electrical load forecasting is a central and integral process for planning periodical operation and expansion of facilities in power system. Load demand patterns are getting complex with every passing day due to the deregulation of electricity markets. To develop a regression model which can map input and output variables in such a dynamic scenario is not easy. This paper presents an application of Principal Component Analysis (PCA) in the load forecasting of a large distribution network. Different models of ANNs are developed with the help of PCA based feature selection. Efficacy of the proposed approach is evaluated in terms of error indices namely Mean Square Error (MSE), Minimum Average Error (MAE), Mean Absolute Percentage Error (MAPE).
Artificial Neural Network (ANN), Load Forecasting Mean Square Error, Principal Component Analysis, Radial Basis Function Neural Network (RBFNN)