What exactly is this about? Electricity is a factor that is being considered a lot lately in Sri Lanka as well as most of the other countries, at present the world will be nothing if we don’t have electricity because everything uses electricity nowadays, So getting an idea about generation, consumption, and revenue is a good thing for our present as well as future needs, as per Sri Lanka electricity is generated using various ways (CEB-Annual Report 2020): According to this there are 3 main ways in Sri Lanka, like this every country has their own way of generating and using electricity in different ways. The main problem a lot of countries are facing specially Sri Lanka is there’s no proper way to record, handle and predict future aspects in this field according to research Sri Lanka uses a model called ( MAED-2) (Ceylon Electricity Board, 2021) This is currently being done in statistical methods, probabilistic methods, and computational intelligence methods (Atef and Eltawil, 2019). According to the problem above we need a more convenient way to handle this issue for stronger insights and predictions using more reliable models and prediction methodologies. In Our project, the focus is on forecasting electricity consumption along with electricity generation prediction, and revenue and price forecasting using Artificial Neural Network called LSTM. These predictions can be made based on a wide range of factors such as global fuel prices, weather conditions, expenses in running power stations and the electricity grid Since we are considering many factors for electricity production it can be used in many countries with regarding the in their country to predict electricity generation, consumption and revenue predictions. We have built a user-friendly web application for every single person to access and get information on these 3 fields to see what’s for us in the future and present as well as past we had. and most importantly we have given the user the opportunity to change features and get their required information according to their own preferred needs From our project, we have Overall gained an Accuracy prediction of 81.06% for generation, 89.67% for consumption, and 91% for revenue