Energy forecasting is affected by various factors like seasonality, abrupt weather changes, system malfunctions, and lack of efficient resource management. Hence, towards meeting the energy demand of consumers, there is a need to generate energy efficiently which can be from renewable or nonrenewable sources like coal, wind, solar etc. This requires the need of machine learning and deep learning technique to forecast the generation of energy efficiently and economically. This work focuses on solving the issue related to energy generation forecasting by analyzing energy generation from various fuel sources over the course of 8 years by applying various techniques such as Bi-LSTM, Nbeats, ETS, Xgboost and MLP. From the performance analysis for four seasons, it has been concluded that Bi-LSTM performed the best overall 4 seasons with an average SMAPE of 20.412. This would really benefit utility companies in forecasting the fuel generation effectively in meeting the consumer demand.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.