Emission-Aware Reinforcement Learning for Sustainable Electric Vehicle Charging and Carbon Dioxide Reduction Under Varying Renewable Penetration
再生可能エネルギー普及変動下における持続可能なEV充電とCO2削減のための排出考慮型強化学習 (AI 翻訳)
Ninglin Ou, Mohammad A. Razzaque, Iftekher Islam Shovon, Shafkat Khan Siam, Shafiuzzaman K Khadem, Krishnendu Guha, Mayeen Uddin Khandaker, Md. Noor-A-Rahim
🤖 gxceed AI 要約
日本語
この論文は、電気自動車（EV）の充電スケジューリングに排出量を考慮した強化学習（RL）手法を提案。SACアルゴリズムを用い、炭素強度、再エネ自家消費率、ユーザー需要充足を多目的報酬として最適化。0-50%の再エネ普及率シナリオで評価し、最大87%の排出削減を達成。トランス過負荷も抑制。
English
This paper proposes an emission-aware reinforcement learning (RL) strategy using the Soft Actor-Critic (SAC) algorithm for EV charging scheduling. The multi-objective reward penalizes carbon emissions, curtailed renewables, and unmet demand. Under 0-50% renewable penetration scenarios, the RL agent achieves up to 87% emission reduction versus uncontrolled baseline, while keeping transformer overload below 7 kWh.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではEV普及に伴う系統負荷と再エネ活用が課題。本手法はSSBJ開示や企業のスコープ2削減策として、実時間の炭素強度データを用いた充電制御の実装可能性を示す。特に、Behind-the-meter太陽光・風力の自家消費促進と送電網負荷低減を両立する点で、日本企業のエネルギー管理戦略に示唆を与える。
In the global GX context
This work contributes to global GX by demonstrating a practical RL method that integrates carbon intensity forecasts into EV charging, aligning with ISSB/TCFD operational carbon management. The benchmarking on realistic data (EirGrid) offers a replicable model for reducing Scope 2 emissions under varying renewable penetration, relevant for CSRD and SEC climate disclosure.
👥 読者別の含意
🔬研究者:Provides a benchmark for emission-aware RL in EV charging with open-source platform and multi-scenario comparison; extendable to other DER or fleet optimization.
🏢実務担当者:Corporate sustainability teams can reduce EV fleet carbon footprint and grid costs, while meeting green certification requirements via real-time carbon-aware scheduling.
🏛政策担当者:Demonstrates feasibility of integrating carbon intensity signals into demand-side management; supports regulatory incentives like dynamic tariffs or carbon pricing for emission-aware charging.
📄 Abstract（原文）
The rapid growth of Electric Vehicle (EV) adoption challenges power distribution networks through peak load spikes, voltage instability, and transformer overloads from uncoordinated charging. While Model Predictive Control (MPC) and standard Reinforcement Learning (RL) methods have addressed these issues, existing approaches rarely treat real-time carbon intensity or fluctuating renewable energy (RE) availability as primary scheduling objectives, leaving substantial decarbonisation potential unrealised. This paper proposes an emission-aware RL strategy based on the Soft Actor Critic (SAC) algorithm, with a multi-objective reward that penalises carbon emissions, curtailed on-site renewables, and unmet user demand. The agent is trained within a unified benchmarking framework on the EV2Gym platform, incorporating behind-the-meter solar and wind profiles, time-varying EirGrid carbon intensity data, and realistic workplace EV behaviour across 25 Electric Vehicle Supply Equipment (EVSE) units. Nine control strategies, including heuristics, emission-aware MPC variants, and the proposed RL agent, are compared under five renewable penetration scenarios (0%-50%) over ten independent runs each. The RL agent achieves a carbon intensity as low as 23.96 grams of carbon dioxide per kilowatt-hour under 50% wind penetration, representing up to 87% emission reduction versus the uncontrolled baseline, and outperforms the external graph-based Power Distribution Network (PDN) benchmark. Transformer overload remains below 7 kWh across scenarios, against up to 1093 kWh for the As Fast As Possible (AFAP) heuristic, and renewable self-consumption reaches 52% under combined wind and solar supply. Embedding carbon intensity forecasts into the RL state and reward aligns charging with low-emission periods while preserving grid compliance and user satisfaction.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.48550/arxiv.2605.24543first seen 2026-06-15 05:00:05
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。