Comparison of Load Forecasting Algorithm for Industrial Loads

One of the most crucial steps in the real-time management of energy production and effective energy management systems is load forecasting. Short-term load forecasting requires decisions to be made quickly and with little margin for error. This paper relies on machine learning models for the prediction of load demands. The objective of this study is to compare the effectiveness of the two-machine learning algorithms, Long Short-Term Memory (LSTM) and Auto- Regressive Integrated Moving Average (ARIMA). The error values of individual algorithms are compared to determine the better ML algorithm in terms of accuracy. Four parameters suchas RMSE, MAPE, MSE, and MAE are considered. From the above parameters, it is concluded that ARIMA gives better results compared to LSTM.