Distributed Charging Control of Electric Vehicles Using Online Learning

TL;DR

This paper introduces a distributed EV charging control algorithm based on online learning that requires only one-way communication, addressing privacy concerns and demonstrating convergence through numerical simulations.

Contribution

It presents a novel online learning-based algorithm for EV charging control that operates with one-way communication, unlike existing methods requiring two-way communication.

Findings

The algorithm converges to the optimal solution over time.

One-way communication suffices for effective distributed control.

Numerical examples validate the convergence and effectiveness.

Abstract

We propose an algorithm for distributed charging control of electric vehicles (EVs) using online learning and online convex optimization. Many distributed charging control algorithms in the literature implicitly assume fast two-way communication between a distribution company and EV customers. This assumption is impractical at present and raises privacy and security concerns. Our algorithm does not use this assumption; however, at the expense of slower convergence to the optimal solution. The proposed algorithm requires one-way communication, which is implemented through the distribution company publishing the pricing profiles of the previous days. We provide convergence results of the algorithm and illustrate the results through numerical examples.