 This paper proposes three different deep learning algorithms LSTM, GRU, and RNN to accurately forecast the electrical load of an electricity company. The GRU model was found to be the most accurate with an R-squared of 90.228%, MSE of 0.00215, and MAE of 0.03266. This model can be used by electricity companies to improve their power system performance, reliability, safety, instability while also lowering operating costs. This article was authored by Mabarak Abumasan, Amani Yusefota, and Majdi Oda.