Forecasting electricity demand is a key activity in power systems as it is one of the most important entries for production planning; particularly in liberalized, deregulated markets. With the growing penetration of renewable energy sources, there is a pressing need for better load forecasting, since the generated power in wind and solar farms cannot be scheduled and dispatched in the classical sense. Consequently, in addition to the need of accurate load forecasts, a reliable forecasting method of such intermittent energy resources is an important issue that can helps the grid operators to better manage supply/demand balance. The purpose of this work is to develop a feed-forward back propagation neural network (FF-BPNN) based approach for performing hour-ahead electricity demand and wind-solar power generation forecasting. Results from real-world case study; based on the quarter-hourly electricity demand and power generation data in French, are presented in order to illustrate the proficiency of the proposed method. With an average MAPE value of electricity demand, wind, and solar power forecasting respectively equal to 0.765%, 6.008%, and 6.414%; the effectiveness of the proposed methodology is clearly implied.
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.