Guardado en:
Detalles Bibliográficos
Autores principales: Purnananda, Vishesh, Wruck, Benjamin John, Guo, Mingyu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.07275
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918326144335872
author Purnananda, Vishesh
Wruck, Benjamin John
Guo, Mingyu
author_facet Purnananda, Vishesh
Wruck, Benjamin John
Guo, Mingyu
contents This research presents a novel application of Evolutionary Computation to the domain of residential electric vehicle (EV) energy management. While reinforcement learning (RL) achieves high performance in vehicle-to-grid (V2G) optimization, it typically produces opaque "black-box" neural networks that are difficult for consumers and regulators to audit. Addressing this interpretability gap, we propose a program search framework that leverages Large Language Models (LLMs) as intelligent mutation operators within an iterative prompt-evaluation-repair loop. Utilizing the high-fidelity EV2Gym simulation environment as a fitness function, the system undergoes successive refinement cycles to synthesize executable Python policies that balance profit maximization, user comfort, and physical safety constraints. We benchmark four prompting strategies: Imitation, Reasoning, Hybrid and Runtime, evaluating their ability to discover adaptive control logic. Results demonstrate that the Hybrid strategy produces concise, human-readable heuristics that achieve 118% of the baseline profit, effectively discovering complex behaviors like anticipatory arbitrage and hysteresis without explicit programming. This work establishes LLM-driven Evolutionary Computation as a practical approach for generating EV charging control policies that are transparent, inspectable, and suitable for real residential deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07275
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evolving LLM-Derived Control Policies for Residential EV Charging and Vehicle-to-Grid Energy Optimization
Purnananda, Vishesh
Wruck, Benjamin John
Guo, Mingyu
Neural and Evolutionary Computing
This research presents a novel application of Evolutionary Computation to the domain of residential electric vehicle (EV) energy management. While reinforcement learning (RL) achieves high performance in vehicle-to-grid (V2G) optimization, it typically produces opaque "black-box" neural networks that are difficult for consumers and regulators to audit. Addressing this interpretability gap, we propose a program search framework that leverages Large Language Models (LLMs) as intelligent mutation operators within an iterative prompt-evaluation-repair loop. Utilizing the high-fidelity EV2Gym simulation environment as a fitness function, the system undergoes successive refinement cycles to synthesize executable Python policies that balance profit maximization, user comfort, and physical safety constraints. We benchmark four prompting strategies: Imitation, Reasoning, Hybrid and Runtime, evaluating their ability to discover adaptive control logic. Results demonstrate that the Hybrid strategy produces concise, human-readable heuristics that achieve 118% of the baseline profit, effectively discovering complex behaviors like anticipatory arbitrage and hysteresis without explicit programming. This work establishes LLM-driven Evolutionary Computation as a practical approach for generating EV charging control policies that are transparent, inspectable, and suitable for real residential deployment.
title Evolving LLM-Derived Control Policies for Residential EV Charging and Vehicle-to-Grid Energy Optimization
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2602.07275