Load Forecasting using Artificial Neural Network: Case Study at Kolej Komuniti Kuantan

Abstract

For the electrical power system, load forecasting is important to achieve maximum savings and profit in terms of the megawatt hours available. In pursuit of acquiring ideal and effective methods of predicting electrical energy output or load forecasting, this study applies a load demand dataset collected at Kolej Komuniti Kuantan from 2016 to 2019 over 4 years. The Artificial Neural Network will be used as a method of machine learning to predict load forecasting. In order to demonstrate the efficacy of the proposed machine learning, the mean absolute percentage error (MAPE) and root mean square error (RMSE) is measured, and from the errors found, it can be inferred that the proposed technique provides relatively accurate results and is efficient in forecasting the electrical load forecast. The simulation was conducted in the MATLAB Software environment.