Distributed Charging Control of Electric Vehicles Using Online Learning

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 the distribution company and EV customers. This assumption is impractical at present and also raises security and privacy concerns. Our algorithm does not use this assumption; however, at the expense of slower convergence to the optimal solution and by relaxing the sense of optimality. The proposed algorithm requires one-way communication, which is implemented through the distribution company publishing the pricing profiles for the previous days. We provide convergence results for the algorithm and illustrate the results through numerical examples.