Training Electric Vehicle Charging Controllers with Imitation Learning

TL;DR

This paper introduces a privacy-preserving method for training electric vehicle charging controllers using imitation learning, which improves performance and training speed over evolutionary algorithms on realistic data.

Contribution

It presents a novel approach combining quadratic optimization and imitation learning for privacy-preserving EV charging control training.

Findings

Improved controller performance on realistic data.

Faster training compared to evolutionary algorithms.

Effective privacy preservation without third-party communication.

Abstract

The problem of coordinating the charging of electric vehicles gains more importance as the number of such vehicles grows. In this paper, we develop a method for the training of controllers for the coordination of EV charging. In contrast to most existing works on this topic, we require the controllers to preserve the privacy of the users, therefore we do not allow any communication from the controller to any third party. In order to train the controllers, we use the idea of imitation learning -- we first find an optimum solution for a relaxed version of the problem using quadratic optimization and then train the controllers to imitate this solution. We also investigate the effects of regularization of the optimum solution on the performance of the controllers. The method is evaluated on realistic data and shows improved performance and training speed compared to similar controllers trained using evolutionary algorithms.