Machine learning analysis for a flexibility energy approach towards renewable energy integration with dynamic forecasting of electricity balancing power

Abstract

One of the most important instruments to be able to provide the needed level of flexibility in the electricity system supporting renewable energy integration are balancing markets. We propose a dynamic approach of balancing procurement using machine learning algorithms. We apply a simulation for a Dynamic Day-Ahead Dimensioning Model to the Austrian delta control area. By using public data on renewables, generation and load we show that dynamic dimensioning and procurement of balancing power enables savings in comparison to static dimensioning and procurement with the same level of security.