Comparative Study on Backpropagation and Levenberg Marquardt Algorithm on Short Term Load Forecasting

Variable electrical load and ever increasing load demand needs to be predicted or forecasted in order to avoid the energy crisis. This paper presents a comparison between the back propagation algorithm and Levenberg marquardt algorithm for short term load forecasting. The live load data from a typical 66 kV sub-station of the Punjab State Power Corporation Limited (PSPCL) for a selected site is procured for the presented simulation study. The collected live data is divided into three categories, i.e. validation, training and testing for the simulation study considering neural network approach. To check the performance of the two proposed methods, different parameters or errors are used like MSE (Mean Square Error), RMSE (Root Mean Square Error), MAE (Mean Percentage Error), SSE (Sum of Square of Error) and MAPE (Mean Percentage Absolute Error). This would help to ascertain the fluctuation in electric load well in advance, and making a room for preparation to meet the sudden load demand thereby, meeting the expectations of an effective load forecasting with numerous applications in power system arena.