Asynchronously updated predictions of electric vehicles' connection duration to a charging station

Abstract

Electric vehicles are promising to mitigate the in-creasing CO2 emissions from transport, provided that renew-able energy sources generate the demanded electricity. The stochasticity of renewable energy sources and charging demand require intelligent charging schemes. Smart charging achieves better performance when it is driven by reasonably accurate predictions of charging behaviour. Hence, for a smart charging scheme that dynamically updates a charging schedule, updating the predictions of charging behaviour could be beneficial. In this paper, we explore the potential to improve the accuracy of prediction models of the connection duration to a charging station by updating the predictions as the charging sessions unfold. We compare a single-model with multiple-models for regularly and irregularly spaced updates in time. The multiple-model with irregular updates achieves the best performance while improving the prediction accuracy up to 30 %, compared to conventional approaches. It is efficient to update the predictions with higher frequency in the very early stages of charging sessions. Later on, regular updates are sufficient.