EVCAR-KG: A Knowledge-Infused Multi-Agent Reinforcement Learning Framework for Resilient Electric Vehicle Charging Network Recovery

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Abdelfattah, Mohamed
Format: Recurso digital
Langue:anglais
Publié: Zenodo 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866902053235720192
author Abdelfattah, Mohamed
author_facet Abdelfattah, Mohamed
contents <p>This repository contains the implementation of EVCAR-KG, an ontology-driven knowledge graph framework that enhances multi-agent reinforcement learning for electric vehicle charging network recovery after prolonged power outages.</p> <p>The framework integrates semantic knowledge through an OWL ontology with TD3-MADDPG agents to improve learning efficiency and decision quality during post-outage recovery scenarios. Key features include ontology-based action masking, priority-aware reward shaping, and aggregate representation for scalability.</p> <p>This work was presented at the 36th Forum Bauinformatik 2025 in Aachen, Germany.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15824931
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle EVCAR-KG: A Knowledge-Infused Multi-Agent Reinforcement Learning Framework for Resilient Electric Vehicle Charging Network Recovery
Abdelfattah, Mohamed
Electric Vehicle Charging Networks
Knowledge Graphs
Multi-Agent Reinforcement Learning
Power Grid Resilience
Quality of Service Recovery
<p>This repository contains the implementation of EVCAR-KG, an ontology-driven knowledge graph framework that enhances multi-agent reinforcement learning for electric vehicle charging network recovery after prolonged power outages.</p> <p>The framework integrates semantic knowledge through an OWL ontology with TD3-MADDPG agents to improve learning efficiency and decision quality during post-outage recovery scenarios. Key features include ontology-based action masking, priority-aware reward shaping, and aggregate representation for scalability.</p> <p>This work was presented at the 36th Forum Bauinformatik 2025 in Aachen, Germany.</p>
title EVCAR-KG: A Knowledge-Infused Multi-Agent Reinforcement Learning Framework for Resilient Electric Vehicle Charging Network Recovery
topic Electric Vehicle Charging Networks
Knowledge Graphs
Multi-Agent Reinforcement Learning
Power Grid Resilience
Quality of Service Recovery
url https://doi.org/10.5281/zenodo.15824931