Recently, predictive analytic contributes very well for reliable electric power supply. It provides advanced techniques to process, interpret and analyze big energy data and make it more valuable. In this paper, we have presented a benchmark of the most used forecasting models in predicting electrical energy consumption for educational institutions. This study is based on a real use case, implemented using Big Data eco-system based on SMACK architecture. The proposed system analyzes six years of data sets that highly impact National School of Applied Sciences of El Jadida-Morocco energy consumption including planning data (courses, activities, holiday etc) and meteorological data (temperature, pressure, humidity etc). The aim of this benchmark is to evaluate the prediction performance of each forecasting model in order to choose the accurate one to predict electricity consumption in educational institutions.
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.