A comprehensive framework for predicting electric vehicle's participation in ancillary service markets

Abstract

Electric vehicles (EVs) have significant potential to offer unused capacity in ancillary service markets, providing unique opportunities for market operators to utilise these resources. EVs have a rapid response and high availability, making them a good fit for the frequency containment reserve (FCR) market. However, EV aggregators (EVAGs) must aggregate capacity blocks due to the limited capacity of individual EVs. An application of a supervised machine learning method named XGBoost is suggested to help EVAGs predict the amount of EV participation in the FCR market. The objective is to forecast yearly involvement using data from only a single week, using the game theory method SHapley Additive exPlanations (SHAP) to minimise extra data. The proposed strategy helps aggregators and uses feature engineering to select EVs with high potential to boost revenue. The proposed framework is effective in predicting EV performance in the DK-2 market, as shown by multiple analyses.