IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v393y2025ics0306261925007238.html
   My bibliography  Save this article

A scalable demand-side energy management control strategy for large residential districts based on an attention-driven multi-agent DRL approach

Author

Listed:
  • Savino, Sabrina
  • Minella, Tommaso
  • Nagy, Zoltán
  • Capozzoli, Alfonso

Abstract

The growing penetration of renewable energy sources holds great potential for decarbonizing the building energy sector. However, the intermittent and unpredictable nature of renewable generation poses significant challenges to grid stability and energy integration. Demand-side management (DSM) has emerged as a promising solution, leveraging demand flexibility to align energy consumption with periods of peak renewable generation and mitigate grid instability. To fully harness this flexibility, energy coordination across multiple buildings is essential, enabling participation in flexibility markets and optimizing energy management at district level. This paper introduces attention-actor-critic multi-agent deep reinforcement learning (AAC-MADRL), an actor-critic algorithm built upon the centralized training with decentralized execution (CTDE) framework, enhanced with attention mechanisms with the aim of enabling scalable, coordinated, and autonomous DSM in residential districts. A parameterized reward structure allows systematic testing under different cooperation scenarios – fully cooperative, competitive, and mixed – highlighting the conditions where AAC-MADRL outperforms other deep reinforcement learning (DRL) approaches, including decentralized and non-attention-based cooperative methods. Evaluated through winter and summer scenarios in districts across Alameda County, California (73 buildings) and Texas County (100 buildings) using the CityLearn platform, AAC-MADRL demonstrates substantial improvements. AAC-MADRL achieves energy cost reductions of up to 18 % in Texas and 12.5 % in California compared to the rule-based controller. Additionally, it improves self-sufficiency by 6 %–10.5 % during periods of limited solar generation and significantly reduces peak demand. The algorithm also exhibited superior computational efficiency, with deployment times 40.5 % faster than decentralized DRL and 62.5 % faster than cooperative non-attention-based DRL approaches on average.

Suggested Citation

  • Savino, Sabrina & Minella, Tommaso & Nagy, Zoltán & Capozzoli, Alfonso, 2025. "A scalable demand-side energy management control strategy for large residential districts based on an attention-driven multi-agent DRL approach," Applied Energy, Elsevier, vol. 393(C).
    • Handle: RePEc:eee:appene:v:393:y:2025:i:c:s0306261925007238
    DOI: 10.1016/j.apenergy.2025.125993
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261925007238
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2025.125993?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Charbonnier, Flora & Morstyn, Thomas & McCulloch, Malcolm D., 2022. "Scalable multi-agent reinforcement learning for distributed control of residential energy flexibility," Applied Energy, Elsevier, vol. 314(C).
    2. Ajagekar, Akshay & Decardi-Nelson, Benjamin & You, Fengqi, 2024. "Energy management for demand response in networked greenhouses with multi-agent deep reinforcement learning," Applied Energy, Elsevier, vol. 355(C).
    3. Charbonnier, Flora & Peng, Bei & Vienne, Julie & Stai, Eleni & Morstyn, Thomas & McCulloch, Malcolm, 2025. "Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility," Applied Energy, Elsevier, vol. 377(PA).
    4. Omid Pedram & Ehsan Asadi & Behrang Chenari & Pedro Moura & Manuel Gameiro da Silva, 2023. "A Review of Methodologies for Managing Energy Flexibility Resources in Buildings," Energies, MDPI, vol. 16(17), pages 1-30, August.
    5. Harrold, Daniel J.B. & Cao, Jun & Fan, Zhong, 2022. "Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning," Applied Energy, Elsevier, vol. 318(C).
    6. Bai, Yuyang & Chen, Siyuan & Zhang, Jun & Xu, Jian & Gao, Tianlu & Wang, Xiaohui & Wenzhong Gao, David, 2023. "An adaptive active power rolling dispatch strategy for high proportion of renewable energy based on distributed deep reinforcement learning," Applied Energy, Elsevier, vol. 330(PA).
    7. Pinto, Giuseppe & Kathirgamanathan, Anjukan & Mangina, Eleni & Finn, Donal P. & Capozzoli, Alfonso, 2022. "Enhancing energy management in grid-interactive buildings: A comparison among cooperative and coordinated architectures," Applied Energy, Elsevier, vol. 310(C).
    8. Tang, Lingfeng & Xie, Haipeng & Wang, Xiaoyang & Bie, Zhaohong, 2023. "Privacy-preserving knowledge sharing for few-shot building energy prediction: A federated learning approach," Applied Energy, Elsevier, vol. 337(C).
    9. Pinto, Giuseppe & Deltetto, Davide & Capozzoli, Alfonso, 2021. "Data-driven district energy management with surrogate models and deep reinforcement learning," Applied Energy, Elsevier, vol. 304(C).
    10. Xie, Jiahan & Ajagekar, Akshay & You, Fengqi, 2023. "Multi-Agent attention-based deep reinforcement learning for demand response in grid-responsive buildings," Applied Energy, Elsevier, vol. 342(C).
    11. Zhu, Dafeng & Yang, Bo & Liu, Yuxiang & Wang, Zhaojian & Ma, Kai & Guan, Xinping, 2022. "Energy management based on multi-agent deep reinforcement learning for a multi-energy industrial park," Applied Energy, Elsevier, vol. 311(C).
    12. Karlson Hargroves & Benjamin James & Joshua Lane & Peter Newman, 2023. "The Role of Distributed Energy Resources and Associated Business Models in the Decentralised Energy Transition: A Review," Energies, MDPI, vol. 16(10), pages 1-15, May.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Liu, Jiejie & Ma, Yanan & Chen, Ying & Zhao, Chunlu & Meng, Xianyang & Wu, Jiangtao, 2025. "Multi-agent deep reinforcement learning-based cooperative energy management for regional integrated energy system incorporating active demand-side management," Energy, Elsevier, vol. 319(C).
    2. Omar Al-Ani & Sanjoy Das, 2022. "Reinforcement Learning: Theory and Applications in HEMS," Energies, MDPI, vol. 15(17), pages 1-37, September.
    3. Panagiotis Michailidis & Iakovos Michailidis & Elias Kosmatopoulos, 2025. "Reinforcement Learning for Optimizing Renewable Energy Utilization in Buildings: A Review on Applications and Innovations," Energies, MDPI, vol. 18(7), pages 1-40, March.
    4. Muhammad Ikram & Daryoush Habibi & Asma Aziz, 2025. "Networked Multi-Agent Deep Reinforcement Learning Framework for the Provision of Ancillary Services in Hybrid Power Plants," Energies, MDPI, vol. 18(10), pages 1-34, May.
    5. Bashyal, Atit & Boroukhian, Tina & Veerachanchai, Pakin & Naransukh, Myanganbayar & Wicaksono, Hendro, 2025. "Multi-agent deep reinforcement learning based demand response and energy management for heavy industries with discrete manufacturing systems," Applied Energy, Elsevier, vol. 392(C).
    6. Nweye, Kingsley & Sankaranarayanan, Siva & Nagy, Zoltan, 2023. "MERLIN: Multi-agent offline and transfer learning for occupant-centric operation of grid-interactive communities," Applied Energy, Elsevier, vol. 346(C).
    7. Pavirani, Fabio & Van Gompel, Jonas & Karimi Madahi, Seyed Soroush & Claessens, Bert & Develder, Chris, 2025. "Predicting and publishing accurate imbalance prices using Monte Carlo Tree Search," Applied Energy, Elsevier, vol. 392(C).
    8. Xie, Jiahan & Ajagekar, Akshay & You, Fengqi, 2023. "Multi-Agent attention-based deep reinforcement learning for demand response in grid-responsive buildings," Applied Energy, Elsevier, vol. 342(C).
    9. Qiu, Dawei & Xue, Juxing & Zhang, Tingqi & Wang, Jianhong & Sun, Mingyang, 2023. "Federated reinforcement learning for smart building joint peer-to-peer energy and carbon allowance trading," Applied Energy, Elsevier, vol. 333(C).
    10. Chen, Longxiang & He, Huan & Jing, Rui & Xie, Meina & Ye, Kai, 2024. "Energy management in integrated energy system with electric vehicles as mobile energy storage: An approach using bi-level deep reinforcement learning," Energy, Elsevier, vol. 307(C).
    11. Li, Sichen & Hu, Weihao & Cao, Di & Chen, Zhe & Huang, Qi & Blaabjerg, Frede & Liao, Kaiji, 2023. "Physics-model-free heat-electricity energy management of multiple microgrids based on surrogate model-enabled multi-agent deep reinforcement learning," Applied Energy, Elsevier, vol. 346(C).
    12. Ayas Shaqour & Aya Hagishima, 2022. "Systematic Review on Deep Reinforcement Learning-Based Energy Management for Different Building Types," Energies, MDPI, vol. 15(22), pages 1-27, November.
    13. Gao, Yuan & Matsunami, Yuki & Miyata, Shohei & Akashi, Yasunori, 2022. "Multi-agent reinforcement learning dealing with hybrid action spaces: A case study for off-grid oriented renewable building energy system," Applied Energy, Elsevier, vol. 326(C).
    14. Li, Yonggang & Su, Yaotong & Zhang, Yuanjin & Wu, Weinong & Xia, Lei, 2024. "Two-layered optimal scheduling under a semi-model architecture of hydro-wind-solar multi-energy systems with hydrogen storage," Energy, Elsevier, vol. 313(C).
    15. Pasta, Edoardo & Faedo, Nicolás & Mattiazzo, Giuliana & Ringwood, John V., 2023. "Towards data-driven and data-based control of wave energy systems: Classification, overview, and critical assessment," Renewable and Sustainable Energy Reviews, Elsevier, vol. 188(C).
    16. Liu, Mingzhe & Guo, Mingyue & Fu, Yangyang & O’Neill, Zheng & Gao, Yuan, 2024. "Expert-guided imitation learning for energy management: Evaluating GAIL’s performance in building control applications," Applied Energy, Elsevier, vol. 372(C).
    17. Lan, Penghang & Chen, She & Li, Qihang & Li, Kelin & Wang, Feng & Zhao, Yaoxun, 2024. "Intelligent hydrogen-ammonia combined energy storage system with deep reinforcement learning," Renewable Energy, Elsevier, vol. 237(PB).
    18. Chen, Bingyang & Zeng, Xingjie & Zhang, Weishan & Fan, Lulu & Cao, Shaohua & Zhou, Jiehan, 2023. "Knowledge sharing-based multi-block federated learning for few-shot oil layer identification," Energy, Elsevier, vol. 283(C).
    19. Xiong, Kang & Hu, Weihao & Cao, Di & Li, Sichen & Zhang, Guozhou & Liu, Wen & Huang, Qi & Chen, Zhe, 2023. "Coordinated energy management strategy for multi-energy hub with thermo-electrochemical effect based power-to-ammonia: A multi-agent deep reinforcement learning enabled approach," Renewable Energy, Elsevier, vol. 214(C), pages 216-232.
    20. Ren, Haoshan & Ma, Zhenjun & Fai Norman Tse, Chung & Sun, Yongjun, 2022. "Optimal control of solar-powered electric bus networks with improved renewable energy on-site consumption and reduced grid dependence," Applied Energy, Elsevier, vol. 323(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:393:y:2025:i:c:s0306261925007238. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.