Long-Term Peak Load Estimate and Forecast: A Case Study of Uyo Transmission Substation, Akwa Ibom State, Nigeria

Abstract

This paper presents an approach for long-term estimation and forecasting of electric peak load. A 10-year peak load forecast is performed on Uyo transmission substation in Akwa Ibom State, Nigeria. The peak loads of the past ten years (from 2006 to 2010) are used as input data used to develop the model for forecasting the peak load demand in Uyo metropolis. Particularly, Multiple Linear Regression (MLR) method is used to model the annual peak load. The explanatory variables, namely, temperature, population and gross domestic product are used in the analysis. The peak load model parameters are estimated using only the data of the year 2006 to the year 2012, which accounts for 70% of the entire dataset for training and 30% (that is, 2013 to 2015) of the data are used for cross validation. The results show that with respect to the training dataset the prediction model has Mean Absolute Percentage Error (MAPE) of 0.00613%, Mean Absolute Deviation (MAD) of 0.277743 and Coefficient of Determination (R2) value of 0.99184 which shows that about 99.184% of the peak load are explained by the explanatory variables used in the prediction. Furthermore, with respect to the validation dataset (2013 to 2015) the prediction model has RMSE of 1.038042 and percentage error of less that 2% which shows that the proposed peak-load-demand model can effectively predict the peak load demand for Uyo.