Optimal control of ventilation in enclosed spaces using Adversarial Neural Networks
Optimal control of ventilation in enclosed spaces using Adversarial Neural Networks
Systems that manage and control air quality are the main energy consumers within a building and their design often relies on assumptions that lead to excessive energy usage. This paper proposes a new method based on Computational Fluid Dynamics (CFD) and Artificial Intelligence (AI) that can assimilate observations and control ventilation systems to achieve a certain goal, such as maintaining a particular temperature range in an indoor environment. An AI-based reduced-order model (ROM) is used here because current CFD methods generally have too large a computational expense for real-time control. We use proper orthogonal decomposition (POD) to represent the spatial distributions of the CFD simulations and learn the evolution of the POD coefficients in time with an Adversarial Neural Network. With this AI-based ROM, we can perform 4D Variational Data Assimilation (4D-Var DA) and control with a rapid workflow that incorporates the spatial variation of all the key variables: air flow velocity, CO 2, temperature, relative humidity and viral load. The proposed method is applied to three scenarios: (i) a ventilation scenario in which the aim is to keep the occupants healthy (indicated by ventilation and CO 2 levels) as well as thermally comfortable while minimising energy consumption; (ii) a pandemic scenario in which the priority is to keep people infection-free; (iii) a compromise between (i) and (ii). These three scenarios are developed within a classroom containing 26 children and one teacher, and are combined with an extensive set of measurement data, collected in the classroom of a primary school located in London. Our method successfully met the control objectives in all three scenarios.
Adversarial neural network, Computational fluid dynamics, Control, Data assimilation, Indoor air quality, Machine learning, Thermal comfort
Guo, Donghu
a01e7fac-7e4b-489b-b9a6-0a911936fbc3
Heaney, Claire E.
8a5f3df5-a50c-4ab9-837f-043d671eb296
Chen, Boyang
38408480-0426-493d-ac98-99924f2d2357
Tang, Jieyi
6eac8a51-6e52-40a3-a284-c305f466ddc9
Cammarano, Andrea
c0c85f55-3dfc-4b97-9b79-e2554406a12b
Kumar, Prashant
5e332e6f-0450-48c9-9fce-4c663452b8d8
Pain, Christopher C.
8cf8e928-1a3d-4c4b-8bcd-2bf111f1a44a
22 October 2025
Guo, Donghu
a01e7fac-7e4b-489b-b9a6-0a911936fbc3
Heaney, Claire E.
8a5f3df5-a50c-4ab9-837f-043d671eb296
Chen, Boyang
38408480-0426-493d-ac98-99924f2d2357
Tang, Jieyi
6eac8a51-6e52-40a3-a284-c305f466ddc9
Cammarano, Andrea
c0c85f55-3dfc-4b97-9b79-e2554406a12b
Kumar, Prashant
5e332e6f-0450-48c9-9fce-4c663452b8d8
Pain, Christopher C.
8cf8e928-1a3d-4c4b-8bcd-2bf111f1a44a
Guo, Donghu, Heaney, Claire E., Chen, Boyang, Tang, Jieyi, Cammarano, Andrea, Kumar, Prashant and Pain, Christopher C.
(2025)
Optimal control of ventilation in enclosed spaces using Adversarial Neural Networks.
Building and Environment, 287 (Part B.), [113858].
(doi:10.1016/j.buildenv.2025.113858).
Abstract
Systems that manage and control air quality are the main energy consumers within a building and their design often relies on assumptions that lead to excessive energy usage. This paper proposes a new method based on Computational Fluid Dynamics (CFD) and Artificial Intelligence (AI) that can assimilate observations and control ventilation systems to achieve a certain goal, such as maintaining a particular temperature range in an indoor environment. An AI-based reduced-order model (ROM) is used here because current CFD methods generally have too large a computational expense for real-time control. We use proper orthogonal decomposition (POD) to represent the spatial distributions of the CFD simulations and learn the evolution of the POD coefficients in time with an Adversarial Neural Network. With this AI-based ROM, we can perform 4D Variational Data Assimilation (4D-Var DA) and control with a rapid workflow that incorporates the spatial variation of all the key variables: air flow velocity, CO 2, temperature, relative humidity and viral load. The proposed method is applied to three scenarios: (i) a ventilation scenario in which the aim is to keep the occupants healthy (indicated by ventilation and CO 2 levels) as well as thermally comfortable while minimising energy consumption; (ii) a pandemic scenario in which the priority is to keep people infection-free; (iii) a compromise between (i) and (ii). These three scenarios are developed within a classroom containing 26 children and one teacher, and are combined with an extensive set of measurement data, collected in the classroom of a primary school located in London. Our method successfully met the control objectives in all three scenarios.
Text
1-s2.0-S0360132325013289-main
- Version of Record
More information
Accepted/In Press date: 12 October 2025
e-pub ahead of print date: 21 October 2025
Published date: 22 October 2025
Keywords:
Adversarial neural network, Computational fluid dynamics, Control, Data assimilation, Indoor air quality, Machine learning, Thermal comfort
Identifiers
Local EPrints ID: 511323
URI: http://eprints.soton.ac.uk/id/eprint/511323
ISSN: 0360-1323
PURE UUID: d2b710a4-3a70-482b-bd9b-333cac7b4e2e
Catalogue record
Date deposited: 12 May 2026 16:32
Last modified: 13 May 2026 02:11
Export record
Altmetrics
Contributors
Author:
Donghu Guo
Author:
Claire E. Heaney
Author:
Boyang Chen
Author:
Jieyi Tang
Author:
Andrea Cammarano
Author:
Prashant Kumar
Author:
Christopher C. Pain
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics