Research Article

A Multi-Agent Deep Reinforcement Learning Framework for Decentralized Peer-to-Peer Energy Trading in Microgrids with High Photovoltaic Penetration

128 reads
SciMatic J Energy Phys Renew Sys, 2026, 1 (1), 2-8, ISSN

Abstract

The rapid deployment of distributed photovoltaic (PV) systems in modern distribution networks challenges traditional centralized grid management, causing issues such as reverse power flow and voltage fluctuations. Peer-to-peer (P2P) energy trading offers a promising decentralized solution to enhance local self-consumption and lower electricity costs. However, managing highly dynamic, uncertain, and multi-actor interactions in P2P markets remains a formidable challenge. This paper proposes a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to facilitate decentralized P2P energy trading in microgrids with high PV penetration. Each prosumer is modeled as an autonomous agent that learns optimal pricing and trading strategies under local supply-demand fluctuations and time-varying utility tariffs, without sharing private operational data. To improve convergence and market efficiency, we incorporate a continuous action space and a customized reward function that balances individual economic benefits with local grid stability. Simulation results based on real-world consumption and generation profiles demonstrate that the proposed MADRL framework reduces average prosumer energy costs by up to 18.4% and lowers the peak-to-average ratio (PAR) of the microgrid by 22.1% compared to traditional peer-to-grid and rule-based trading baselines. These findings highlight the potential of decentralized, learning-based approaches in enabling resilient and self-organizing community energy systems.

Keywords microgrids peer-to-peer energy trading Multi-agent deep reinforcement learning Photovoltaic penetration Decentralized energy management
Authors 3

The team behind this paper

3 authors, 3 institutions.

This paper University of Cambridge — United Kingdom University of Cambridge 1 author Technical University of Munich — Germany Technical University of… 1 author National University of Singapore — Singapore National University of … 1 author Dr. Yuki Bergström — corresponding author YB Dr. Yuki Bergström ✉ Dr. Carlos Nair CN Dr. Carlos Nair Dr. Fatima Silva FS Dr. Fatima Silva

Readership

128 reads over 5 months.

#5 most read in this journal this month
July 2026 November 2026

Bibliographic Information

Dr. Yuki Bergström, Dr. Carlos Nair, Dr. Fatima Silva, (2026). A Multi-Agent Deep Reinforcement Learning Framework for Decentralized Peer-to-Peer Energy Trading in Microgrids with High Photovoltaic Penetration, SciMatic Journal of Energy Physics and Renewable Systems, 1(1): 2-8
Bibtex Citation
@article{dr._yuki_bergström2026sjeprs,
author = {Dr. Yuki Bergström and Dr. Carlos Nair and Dr. Fatima Silva},
title = {A Multi-Agent Deep Reinforcement Learning Framework for Decentralized Peer-to-Peer Energy Trading in Microgrids with High Photovoltaic Penetration},
journal = {SciMatic Journal of Energy Physics and Renewable Systems},
year = {2026},
volume = {1},
number = {1},
pages = {2-8},
doi = {},
url = {https://scimatic.org/show_manuscript/8518}
}
APA Citation
Bergström, D.Y., Nair, D.C., Silva, D.F., (2026). A Multi-Agent Deep Reinforcement Learning Framework for Decentralized Peer-to-Peer Energy Trading in Microgrids with High Photovoltaic Penetration. SciMatic Journal of Energy Physics and Renewable Systems, 1(1), 2-8. https://doi.org/

Author Information

  • To change your profile photo, login to scimatic.org, go to your profile and change the photo.
  • Any photo that shows your face will do: we crop it to your head and shoulders and give it a plain background automatically.
  • To sign in, go to Sign in and enter the e-mail address registered with the article: we e-mail you a one-time sign-in link (there is no password).
  • In case of any other problem, contact your editor directly or write to us at info @ scimatic.org