XRL-LLM: Explainable Reinforcement Learning Framework for Voltage Control
Energies · 06.04.2026 · 19 (7) · 1789
DOI: 10.3390/en19071789 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 06.04.2026. Verfasst von Shrenik Jadhav und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation, University of Michigan-Dearborn Experience+ Student Independent Research Grant.
Abstract (Originalsprache)
Reinforcement learning (RL) agents are increasingly deployed for voltage control in power distribution networks. However, their opaque decision-making creates a significant trust barrier, limiting their adoption in safety-sensitive operational settings. This paper presents XRL-LLM, a novel framework that generates natural language explanations for RL control decisions by combining game-theoretic feature attribution (KernelSHAP) with large language model (LLM) reasoning grounded in power systems domain knowledge. We deployed a Proximal Policy Optimization (PPO) agent on an IEEE 33-bus network to coordinate capacitor banks and on-load tap changers, successfully reducing voltage violations by 90.5% across diverse loading conditions. To make these decisions interpretable, KernelSHAP identifies the most influential state features. These features are then processed by a domain-context-engineered LLM prompt that explicitly encodes network topology, device specifications, and ANSI C84.1 voltage limits.Evaluated via G-Eval across 30 scenarios, XRL-LLM achieves an explanation quality score of 4.13/5. This represents a 33.7% improvement over template-based generation and a 67.9% improvement over raw SHAP outputs, delivering statistically significant gains in accuracy, actionability, and completeness (p
Förderung
- U.S. National Science Foundation
- University of Michigan-Dearborn Experience+ Student Independent Research Grant
Zitieren
APA
Jadhav, S., Sevak, B., & Bui, V. (2026). XRL-LLM: Explainable Reinforcement Learning Framework for Voltage Control. Energies, 19(7), 1789. https://doi.org/10.3390/en19071789
Vancouver
Jadhav S, Sevak B, Bui V. XRL-LLM: Explainable Reinforcement Learning Framework for Voltage Control. Energies. 2026;19(7):1789. doi:10.3390/en19071789
BibTeX
@article{Jadhav2026,
author = {Jadhav, Shrenik and Sevak, Birva and Bui, Van-Hai},
title = {XRL-LLM: Explainable Reinforcement Learning Framework for Voltage Control},
journal = {Energies},
year = {2026},
volume = {19},
number = {7},
pages = {1789},
doi = {10.3390/en19071789}
}
EUVIMED