Orfanoudakis Stavros, Robu Valentin, Salazar E Mauricio, Palensky Peter, Vergara Pedro P
Intelligent Electrical Power Grids, Delft University of Technology, Delft, The Netherlands.
Intelligent & Autonomous Systems Group, Centrum Wiskunde & Informatica (CWI), Amsterdam, The Netherlands.
Commun Eng. 2025 Jul 1;4(1):118. doi: 10.1038/s44172-025-00457-8.
As the adoption of electric vehicles (EVs) accelerates, addressing the challenges of large-scale, city-wide optimization becomes critical in ensuring efficient use of charging infrastructure and maintaining electrical grid stability. This study introduces EV-GNN, a novel graph-based solution that addresses scalability challenges and captures uncertainties in EV behavior from a Charging Point Operator's (CPO) perspective. We prove that EV-GNN enhances classic Reinforcement Learning (RL) algorithms' scalability and sample efficiency by combining an end-to-end Graph Neural Network (GNN) architecture with RL and employing a branch pruning technique. We further demonstrate that the proposed architecture's flexibility allows it to be combined with most state-of-the-art deep RL algorithms to solve a wide range of problems, including those with continuous, multi-discrete, and discrete action spaces. Extensive experimental evaluations show that EV-GNN significantly outperforms state-of-the-art RL algorithms in scalability and generalization across diverse EV charging scenarios, delivering notable improvements in both small- and large-scale problems.
随着电动汽车（EV）的采用加速，应对大规模、全市范围优化的挑战对于确保充电基础设施的高效利用和维持电网稳定性至关重要。本研究介绍了EV-GNN，这是一种基于图的新颖解决方案，从充电点运营商（CPO）的角度解决了可扩展性挑战并捕捉了电动汽车行为中的不确定性。我们证明，通过将端到端图神经网络（GNN）架构与强化学习相结合并采用分支剪枝技术，EV-GNN提高了经典强化学习（RL）算法的可扩展性和样本效率。我们进一步证明，所提出架构的灵活性使其能够与大多数最先进的深度强化学习算法相结合，以解决广泛的问题，包括具有连续、多离散和离散动作空间的问题。广泛的实验评估表明，在各种电动汽车充电场景中，EV-GNN在可扩展性和泛化能力方面显著优于最先进的强化学习算法，在小规模和大规模问题上均有显著改进。
