Data analysis and interpretable machine learning for HVAC predictive control - A case-study based implementation

Aug 4, 2026

Upload by Patrick

Energy efficiency and thermal comfort drive Heating, Ventilation and Air Conditioning (HVAC) design, and continuous sensing enabled by IoT allows preemptive optimization of both system performance and occupant comfort. This paper presents a case study with two aims: evaluating a conventional HVAC approach via data analytics and developing interpretable machine learning for HVAC predictive control. A new interpretable method, Permutation Feature-based Frequency Response Analysis (PF-FRA), is proposed for room temperature forecasting using historical, environmental, and time-series features, supported by surrogate models and Shapley graphs for global and local interpretability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Background

Data analytics and HVAC performance

Interpretable machine learning approach

PF-FRA and forecasting results

Model interpretation methods

University of Birmingham Data analysis and interpretable machine learning for HVAC predictive control: A case-study based implementation Mao, Jianqiao; Grammenos, Ryan; Karagiannis, Konstantinos DOI: 10.1080/23744731.2023.2239081 License: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND) Document Version Publisher's PDF, also known as Version of record Citation for published version (Harvard): Mao, J, Grammenos, R & Karagiannis, K 2023, 'Data analysis and interpretable machine learning for HVAC predictive control: A case-study based implementation', Science and Technology for the Built Environment, pp. 1-21. [https://doi.org/10.1080/23744731.2023.2239081](https://doi.org/10.1080/23744731.2023.2239081) Link to publication on Research at Birmingham portal General rights Unless a licence is specified above, all rights (including copyright and moral rights) in this document are retained by the authors and/or the copyright holders. The express permission of the copyright holder must be obtained for any use of this material other than for purposes permitted by law. •Users may freely distribute the URL that is used to identify this publication. •Users may download and/or print one copy of the publication from the University of Birmingham research portal for the purpose of private study or non-commercial research. •User may use extracts from the document in line with the concept of ‘fair dealing’ under the Copyright, Designs and Patents Act 1988 (?) •Users may not further distribute the material nor use it for the purposes of commercial gain. Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive. If you believe that this is the case for this document, [please contact UBIRA@lists.bham.ac.uk](please contact UBIRA@lists.bham.ac.uk) providing details and we will remove access to the work immediately and investigate. Download date: 03. Aug. 2026 Science and Technology for the Built Environment ISSN: (Print) (Online) Journal homepage: [https://www.tandfonline.com/loi/uhvc21](https://www.tandfonline.com/loi/uhvc21) Data analysis and interpretable machine learning for HVAC predictive control: A case-study based implementation Jianqiao Mao, Ryan Grammenos & Konstantinos Karagiannis To cite this article: Jianqiao Mao, Ryan Grammenos & Konstantinos Karagiannis (2023): Data analysis and interpretable machine learning for HVAC predictive control: A casestudy based implementation, Science and Technology for the Built Environment, DOI: 10. 1080/23744731 .2023.2239081 To link to this article: [https://doi.org/10.1080/23744731.2023.2239081](https://doi.org/10.1080/23744731.2023.2239081) Copyright © 2023 The Author(s) . Published with license by Taylor & Francis Group, LLC. | Published online: 24 Aug 2023. | | --- | | Submit your article to this journal | | Article views: 133 | | View related articles | | View Crossmark data | Full Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=uhvc21](https://www.tandfonline.com/action/journalInformation?journalCode=uhvc21) Science and Technology for the Built Environment,(2023) 0, 1–21 Copyright \# 2023 The Author(s) . Published with license by Taylor & Francis Group, LLC. ISSN: 2374-4731 print / 2374-474X online DOI: 10. 1080/23744731 .2023.2239081 Data analysis and interpretable machine learning for HVAC predictive control: A case-study based implementation JIANQIAO MAO 1,2􀀁 , RYAN GRAMMENOS 1 , AND KONSTANTINOS KARAGIANNIS3 1Department of Electronic and Electrical Engineering, University Colleg

FAQs

What problem does the study address for HVAC systems?

The study targets improving HVAC predictive control by balancing energy efficiency and thermal comfort through continuous monitoring and forecasting of room temperature.

What are the two main goals of the paper?

First, analyze the performance of a conventional HVAC system using data analytics. Second, explore interpretable machine learning techniques for HVAC predictive control.

How does the proposed model support interpretability?

The paper uses surrogate models and Shapley graphs to explain both global and local model behavior, increasing trust in the predictions.

Aug 4, 2026

Upload by Patrick