Medium-Term Load Forecasting In A Nigerian Electricity Distribution Region Using Regression Analysis Techniques

Abstract

Electrical energy enriches today’s world and so the forecast of its consumption aids energy industries, governments, as well as investors in making informed decisions at any point in time. It is on this background that this paper engaged regression analysis techniques to forecast on medium-term basis the electric power consumption within the region of Abeokuta in Ogun State of Nigeria. Three different regression techniques: linear, compound-growth and quadratic; were employed to forecast the energy demand based on previous load consumption of the study area. The performance evaluation metrics employed to measure the accuracy of the forecast are the Mean Average Percentage Error (MAPE) and the Root Mean Square Error (RMSE). Of the three techniques, linear regression recorded the least values of MAPE and RMSE. Therefore, with the employment of the linear regression technique, the load demand for July to December in 2018 was forecasted and the percentage load growth achieved for each of the months. The results obtained from this analysis could assist the management of the Regional Headquarters of the Ibadan Electricity Distribution Company on the need to make adequate planning that would facilitate efficient management of energy supply within the region.