View in EDS

Asynchronous multi-agent reinforcement learning for coordinated control of natural ventilation and radiant cooling.

Saved in:
Bibliographic Details
Title: Asynchronous multi-agent reinforcement learning for coordinated control of natural ventilation and radiant cooling.
Authors: Chen, Elence Xinzhu1,2 (AUTHOR) xinzhuchen@alumni.harvard.edu, Malkawi, Ali1,2 (AUTHOR), Samuelson, Holly3 (AUTHOR), Shen, Gulai1,2 (AUTHOR), Li, Na1 (AUTHOR)
Source: Energy & Buildings. Jun2026, Vol. 360, pN.PAG-N.PAG. 1p.
Subjects: Natural ventilation, Reinforcement learning, Thermal comfort, Energy consumption, Indoor air quality, Radiant heating, Building operation management, Adaptive control systems
Abstract: Optimal control for building systems requires coordinating different types of systems and balancing multiple objectives, yet most Building Management Systems still rely on isolated, rule-based controls that fail to optimize across interdependent systems. This paper addresses two critical challenges in advanced building control: (1) coordinating systems with fast (automated window) and slow (radiant floor cooling) dynamics, and (2) eliminating the need for complex physical models through a fully model-free approach. We propose a novel Multi-Agent Deep Reinforcement Learning Control (MA-DRLC) framework that introduces sQ-learning, a slow-response Q-learning variant that incorporates multiple past valve actions to account for thermal lag in radiant systems, and a hierarchical action protocol enabling the valve agent to guide the window agent, with seamless bidirectional state sharing. A unified reward function balances thermal comfort, indoor air quality, and cooling energy. In a real-world office deployment, MA-DRLC maintained thermal comfort and good indoor air quality for more than 90% of occupied hours while reducing mechanical cooling hours by 21% compared to conventional rule-based control. These results demonstrate the scalability of the method, its adaptability to changing weather forecasts, and its potential to transform building automation through autonomous, model-free coordination of multi-timescale subsystems. [ABSTRACT FROM AUTHOR]
Copyright of Energy & Buildings is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 192988559
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Asynchronous multi-agent reinforcement learning for coordinated control of natural ventilation and radiant cooling.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Elence+Xinzhu%22">Chen, Elence Xinzhu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> xinzhuchen@alumni.harvard.edu</i><br /><searchLink fieldCode="AR" term="%22Malkawi%2C+Ali%22">Malkawi, Ali</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Samuelson%2C+Holly%22">Samuelson, Holly</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shen%2C+Gulai%22">Shen, Gulai</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Na%22">Li, Na</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energy+%26+Buildings%22">Energy & Buildings</searchLink>. Jun2026, Vol. 360, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Natural+ventilation%22">Natural ventilation</searchLink><br /><searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Thermal+comfort%22">Thermal comfort</searchLink><br /><searchLink fieldCode="DE" term="%22Energy+consumption%22">Energy consumption</searchLink><br /><searchLink fieldCode="DE" term="%22Indoor+air+quality%22">Indoor air quality</searchLink><br /><searchLink fieldCode="DE" term="%22Radiant+heating%22">Radiant heating</searchLink><br /><searchLink fieldCode="DE" term="%22Building+operation+management%22">Building operation management</searchLink><br /><searchLink fieldCode="DE" term="%22Adaptive+control+systems%22">Adaptive control systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Optimal control for building systems requires coordinating different types of systems and balancing multiple objectives, yet most Building Management Systems still rely on isolated, rule-based controls that fail to optimize across interdependent systems. This paper addresses two critical challenges in advanced building control: (1) coordinating systems with fast (automated window) and slow (radiant floor cooling) dynamics, and (2) eliminating the need for complex physical models through a fully model-free approach. We propose a novel Multi-Agent Deep Reinforcement Learning Control (MA-DRLC) framework that introduces sQ-learning, a slow-response Q-learning variant that incorporates multiple past valve actions to account for thermal lag in radiant systems, and a hierarchical action protocol enabling the valve agent to guide the window agent, with seamless bidirectional state sharing. A unified reward function balances thermal comfort, indoor air quality, and cooling energy. In a real-world office deployment, MA-DRLC maintained thermal comfort and good indoor air quality for more than 90% of occupied hours while reducing mechanical cooling hours by 21% compared to conventional rule-based control. These results demonstrate the scalability of the method, its adaptability to changing weather forecasts, and its potential to transform building automation through autonomous, model-free coordination of multi-timescale subsystems. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Energy & Buildings is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192988559
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.enbuild.2026.117337
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Natural ventilation
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: Thermal comfort
        Type: general
      – SubjectFull: Energy consumption
        Type: general
      – SubjectFull: Indoor air quality
        Type: general
      – SubjectFull: Radiant heating
        Type: general
      – SubjectFull: Building operation management
        Type: general
      – SubjectFull: Adaptive control systems
        Type: general
    Titles:
      – TitleFull: Asynchronous multi-agent reinforcement learning for coordinated control of natural ventilation and radiant cooling.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Elence Xinzhu
      – PersonEntity:
          Name:
            NameFull: Malkawi, Ali
      – PersonEntity:
          Name:
            NameFull: Samuelson, Holly
      – PersonEntity:
          Name:
            NameFull: Shen, Gulai
      – PersonEntity:
          Name:
            NameFull: Li, Na
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 03787788
          Numbering:
            – Type: volume
              Value: 360
          Titles:
            – TitleFull: Energy & Buildings
              Type: main
ResultId 1