Data-driven economic predictive control for sustainable management of renewable energy systems

Abstract

The transition to renewable energy sources is driven by the need to reduce greenhouse gas emissions, mitigate climate change, and enhance energy security. Renewable sources, such as solar, wind, and hydropower, are inherently intermittent, making their integration into the power grid complex. This paper emphasizes the significance of predictive modelling for renewable energy optimization and it establishes the connection between machine learning and economic model predictive control techniques for the realization of sustainable energy management of renewable sources. Machine Learning based frameworks can assist energy providers in preparing for fluctuating sustainable energy supplies by predicting energy demand and forecasting the power production capabilities in energy plants. Moreover, combining smart grid designs with proposed predictive control technique can ensure consumer satisfaction while adhering to sustainability requirements.