EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking

TL;DR

EV2Gym addresses the challenge of evaluating smart charging under V2G by offering a flexible, open-source Gym-based simulator capable of simulating up to $T$ steps with a timescale of $\\Delta t$ minutes. It integrates realistic EV, charger, and transformer models derived from real data, supports PST and V2G profit maximization problems, and provides a comprehensive baseline set (heuristics, MPC, and RL) within a standardized environment. Key contributions include detailed degradation and behavior models, configurable topologies, and evaluation metrics, all accessible through an extensible, modular interface. The platform enables robust benchmarking and rapid prototyping of novel charging strategies, with practical impact on research, standardization, and real-world smart charging deployments.

Abstract

As electric vehicle (EV) numbers rise, concerns about the capacity of current charging and power grid infrastructure grow, necessitating the development of smart charging solutions. While many smart charging simulators have been developed in recent years, only a few support the development of Reinforcement Learning (RL) algorithms in the form of a Gym environment, and those that do usually lack depth in modeling Vehicle-to-Grid (V2G) scenarios. To address the aforementioned issues, this paper introduces the EV2Gym, a realistic simulator platform for the development and assessment of small and large-scale smart charging algorithms within a standardized platform. The proposed simulator is populated with comprehensive EV, charging station, power transformer, and EV behavior models validated using real data. EV2Gym has a highly customizable interface empowering users to choose from pre-designed case studies or craft their own customized scenarios to suit their specific requirements. Moreover, it incorporates a diverse array of RL, mathematical programming, and heuristic algorithms to speed up the development and benchmarking of new solutions. By offering a unified and standardized platform, EV2Gym aims to provide researchers and practitioners with a robust environment for advancing and assessing smart charging algorithms.

Figures (9)

• Figure 1: An EV2Gym simulation comprises three phases: the configuration phase, which initializes the models; the simulation phase, which spans $T$ steps, during which the state of models like EVs and charging stations is updated according to the decision-making algorithm; and finally, in the last phase, the simulator generates evaluation metrics for comparisons, produces replay files for reproducibility, and generates real-time renders for evaluation.
• Figure 2: Directory and file structure of the EV2Gym package.
• Figure 3: Exploring the relation between actual and modeled SoC as a function of current in AC and DC charging and discharging.
• Figure 4: Visualizing calendar aging as a function of average SoC over a day, and cyclic degradation as a function of the total energy exchanged.
• Figure 5: Distributions of arrival and departure times of EVs as a function of time and scenario (public, work, and residential).