Electricity consumption plays a pivotal role in the economic progress of any nation. Accurately forecasting electricity consumption ensures a dependable and efficient power grid operation. Electricity prediction entails estimating future electricity demand or generation, making it a crucial instrument for electric utilities, industries, and governments. Forecasts indicate that different energy consumption sectors will experience rapid growth in the upcoming years. Such expansion will exert immense pressure on the country’s electricity grid, which underscores the need for precise models to predict electricity consumption. Forecasting energy consumption is essential to guaranteeing both environmental security and future economic prosperity. It is essential to the management of energy supply and demand by both public and commercial organisations. It helps determine how best to allocate the available resources for energy use and helps determine what infrastructure should be built to meet future needs. This paper includes views on the significance, difficulties, and general approach of projecting energy consumption. Furthermore, a discussion is held on several energy demand forecasting methods, such as machine learning (random forest, linear regression, and polynomial regression), polynomial regression, SVR, KNN) and deep learning model (LSTM) with 98% accuracy. Lastly, the broad matrices of forecasting accuracy are described to discuss the accuracy of energy demand forecasting.