ENERGY CONSUMPTION FORECASTING

Electricity consumption has increased gradually during the past few decades. This increase is causing burden to the electricity distributors. Therefore, predicting electricity consumption will provide an opportunityto the electricity distributor. Predicting electricity consumption requires many parameters. This study uses two approaches with one using a Recurrent Neural Network (RNN) and another one using a Long Short Term Memory (LSTM) network, which considers the previous electricity consumption, weather and holidays data to predict the future electricity consumption. This study uses the publicly available London smart meter dataset of electricity usage, weather conditions data and Holidays data of UK. To assess the applicability of the RNN and the LSTM network to predict the electricity consumption, they are used to predict the accurate electricity consumption.