Deep Learning for Electrical Load Forecasting in an Industry

This work proposed to develop a forecasting model to estimate the electrical load based on the load demand of an industry in Kerala. Forecasting models have the advantage of assisting electric companies in efficiently distributing their energy demand, which reduces expenses and resource usage. Demand forecasting is crucial for industries since it lowers energy use and boosts effective utilization with optimal energy distribution. In this paper, deep learning techniques namely Multivariate Long Short-Term Memory and Gated Recurrent Units (GRU) are used for forecasting the electrical load demand. Performance evaluation metrics such as RMSE and MAE are used for testing the proposed model. The GRU model showed the best performance in terms of accuracy and minimal error after testing.