This is the authors' abstract. We don't add key points for this paper.
Positive Energy Districts (PEDs) integrate renewable energy sources such as photovoltaics (PV) and smart technologies to improve efficiency and enable communities to generate more energy than they consume annually, often leveraging shared Energy Storage Systems (ESS) for surplus energy management. In such a community, Vehicle-to-Grid (V2G) technology can play a crucial role by allowing Electric Vehicles (EVs) to act as mobile energy storage units, further increasing energy management flexibility and self-sufficiency. Designing an effective charging and discharging strategy can significantly improve energy performance; however, managing V2G-enabled EVs in such a system is complex due to variable household consumption, fluctuating electricity prices, and unpredictable EV availability. For such a community, we propose a Multi-Agent Deep Reinforcement Learning (MADRL)-based approach for decentralized V2Genabled EV charging and discharging scheduling, optimizing energy use within the community while preserving confidential information from other households. By leveraging realistic datasets, we demonstrate that this solution can improve energy self-sufficiency, i.e., increase energy autonomy, compared to heuristic approaches for V2G-enabled EVs charging.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Hribar et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: