Forecasting the Total Non-coincidental Monthly System Peak Demand in the Philippines: A Comparison of Seasonal Autoregressive Integrated Moving Average Models and Artificial Neural Networks

This paper aims to determine suitable seasonal autoregressive integrated moving average (SARIMA) and feed-forward neural network (FFNN) models forecast the total non-coincidental monthly system peak demand in Philippines. To satisfy stationary requirement of SARIMA model, differencing, first-differencing were applied. The findings reveal that (0,1,1)(0,1,1)12 is appropriate model. All model parameters statistically significant. Also, residuals normally distributed. For networks, NNAR (10,1,6)12 was found be evaluation statistics indicate developed are for forecasting. A comparison has been performed by examining their respective root mean square error (RMSE), absolute (MAE), percent (MAPE) values. It FFNN performs better most demand.