A Game-Theoretic Framework for Intelligent EV Charging Network Optimisation in Smart Cities

A team of researchers has published a novel AI framework that applies game theory to solve one of smart cities' most pressing infrastructure problems: planning efficient and profitable electric vehicle (EV) charging networks. The model, named JPPO-DE (Joint Placement and Pricing Optimisation under Driver Equilibrium), treats drivers as strategic agents in a coupled non-atomic congestion game. It allows public authorities to simultaneously optimize where to build charging stations and how to price them, with the goal of minimizing overall social costs—including travel times, queuing delays, and charging expenses—while ensuring the network remains economically viable.

The core innovation is a two-level approximation method that decomposes complex driver behavior and uses integer relaxation to solve what would otherwise be an intractable Mixed-Integer Nonlinear Programme. Tested on the benchmark Sioux Falls Transportation Network, the framework consistently outperformed single-parameter baseline methods. It demonstrated robust performance improvements of at least 16% over state-of-the-art approaches, effectively adapting to variables like different city budgets, levels of EV adoption, and station capacities. The paper, accepted for the IEEE ITSC 2025 conference, also includes a generalisation procedure to scale the solution to larger, real-world urban networks.