Federated proximal policy optimization with action masking: Application in collective heating systems

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Sara Ghane , Stef Jacobs , Furkan Elmaz , Thomas Huybrechts , Ivan Verhaert , Siegfried Mercelis
{"title":"Federated proximal policy optimization with action masking: Application in collective heating systems","authors":"Sara Ghane ,&nbsp;Stef Jacobs ,&nbsp;Furkan Elmaz ,&nbsp;Thomas Huybrechts ,&nbsp;Ivan Verhaert ,&nbsp;Siegfried Mercelis","doi":"10.1016/j.egyai.2025.100506","DOIUrl":null,"url":null,"abstract":"<div><div>This paper introduces a novel privacy-aware Federated Proximal Policy Optimization (FPPO) method combined with action masking. As a Federated Reinforcement Learning (FRL) approach, the proposed method is used for optimizing the reloading of Domestic Hot Water (DHW) storage tanks, with a focus on energy savings and DHW thermal comfort in collective heating systems. The proposed approach combines FedProx as the Federated Learning (FL) method and Proximal Policy Optimization (PPO) as the Deep Reinforcement Learning (DRL) technique to address the challenges of distributed control while ensuring data privacy. Key contributions include: (1) employing action masking to guarantee compliance with comfort level, (2) designing a global reward function to align agents actions toward collective energy savings, (3) implementing a privacy-aware design where only model parameters are shared with a global aggregator, avoiding raw data transmission, and (4) optimizing PPO’s loss function for improved performance.</div><div>PPO was benchmarked using a common FL method (FedAvg) alongside two other DRL methods, where PPO outperformed both in scalability and energy savings, especially in larger systems. Then, PPO-based FRL was refined into FPPO by integrating a proximal term with coefficient <span><math><mi>μ</mi></math></span> into the loss function to enhance the performance. Experiments were conducted with both fixed and dynamically adjusted <span><math><mi>μ</mi></math></span>, with the latter demonstrating better energy savings and comfort. Results show that FPPO achieves up to 10.08% energy savings while maintaining DHW discomfort below 8.72% in systems with at least 20 dwellings. These findings highlight FPPO as a scalable, privacy-aware, and energy-efficient solution for distributed control in collective heating systems.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"20 ","pages":"Article 100506"},"PeriodicalIF":9.6000,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and AI","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666546825000382","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

This paper introduces a novel privacy-aware Federated Proximal Policy Optimization (FPPO) method combined with action masking. As a Federated Reinforcement Learning (FRL) approach, the proposed method is used for optimizing the reloading of Domestic Hot Water (DHW) storage tanks, with a focus on energy savings and DHW thermal comfort in collective heating systems. The proposed approach combines FedProx as the Federated Learning (FL) method and Proximal Policy Optimization (PPO) as the Deep Reinforcement Learning (DRL) technique to address the challenges of distributed control while ensuring data privacy. Key contributions include: (1) employing action masking to guarantee compliance with comfort level, (2) designing a global reward function to align agents actions toward collective energy savings, (3) implementing a privacy-aware design where only model parameters are shared with a global aggregator, avoiding raw data transmission, and (4) optimizing PPO’s loss function for improved performance.
PPO was benchmarked using a common FL method (FedAvg) alongside two other DRL methods, where PPO outperformed both in scalability and energy savings, especially in larger systems. Then, PPO-based FRL was refined into FPPO by integrating a proximal term with coefficient μ into the loss function to enhance the performance. Experiments were conducted with both fixed and dynamically adjusted μ, with the latter demonstrating better energy savings and comfort. Results show that FPPO achieves up to 10.08% energy savings while maintaining DHW discomfort below 8.72% in systems with at least 20 dwellings. These findings highlight FPPO as a scalable, privacy-aware, and energy-efficient solution for distributed control in collective heating systems.

Abstract Image

求助全文
约1分钟内获得全文 求助全文
来源期刊
Energy and AI
Energy and AI Engineering-Engineering (miscellaneous)
CiteScore
16.50
自引率
0.00%
发文量
64
审稿时长
56 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信