Optimising electric vehicle charging stations on UK motorways using deep neural networks: A scenario-based case study of the M40

Abstract

The UK’s electric vehicle (EV) adoption is accelerating rapidly, with over 1.4 million EVs on the road and projections reaching 14 million by 2030. However, while approximately 75,000 public chargers have been installed to date, this remains far short of the govern-ment’s 300,000 target by 2030. Planning adequate infrastructure involves more than fore-casting national demand—it requires estimating the number of chargers needed in specific locations, such as motorway corridors, while accounting for traffic volumes, grid capacity, and funding limitations. Most existing approaches rely on linear models that fail to capture the full complexity and interdependence of these factors.

This study proposes a predictive framework using Deep Neural Networks (DNNs) to estimate the number of ultra-fast EV charging stations required under varying planning conditions and constraints. Unlike traditional methods, the DNN model learns nonlinear relationships across ten key input features, integrating both technical variables (e.g., traffic flow, substation capacity, energy consumption) and policy-relevant constraints (e.g., budgets, installation costs). A scenario-based case study was conducted on the M40 motorway to demonstrate the model’s flexibility in real world contexts—covering Crowded, Energy Constrained, Budget-Constrained, and Balanced scenarios using actual traffic, charger, and substation data. The results show that this DNN-based approach offers a scalable, data informed planning tool that can support UK policymakers in making more resilient and adaptive infrastructure decisions.