Detection of Undeclared EV Charging Events in a Green Energy Certification Scheme

TL;DR

This paper presents a Bayesian method to detect undeclared EV charging events using GPS data, aiming to promote green energy use and support decarbonisation in transportation.

Contribution

It introduces a novel Bayesian hypothesis test for identifying undeclared EV charging, validated through extensive simulations in London.

Findings

High detection accuracy for undeclared charging events

Effective simulation results demonstrating method robustness

Potential to incentivize green charging compliance

Abstract

The green potential of electric vehicles (EVs) can be fully realized only if their batteries are charged using energy generated from renewable (i.e. green) sources. For logistic or economic reasons, however, EV drivers may be tempted to avoid charging stations certified as providing green energy, instead opting for conventional ones, where only a fraction of the available energy is green. This behaviour may slow down the achievement of decarbonisation targets of the road transport sector. In this paper, we use GPS data to infer whether an undeclared charging event has occurred. Specifically, we construct a Bayesian hypothesis test for the charging behaviour of the EV. Extensive simulations are carried out for an area of London, using the mobility simulator, SUMO, and exploring various operating conditions. Excellent detection rates for undeclared charging events are reported. We explain how the algorithm can serve as the basis for an incentivization scheme, encouraging compliance by drivers with green charging policies.