skip to main content
10.1145/3575813.3597453acmotherconferencesArticle/Chapter ViewAbstractPublication Pagese-energyConference Proceedingsconference-collections
research-article

Efficient and Accurate Peer-to-Peer Training of Machine Learning Based Home Thermal Models

Published: 16 June 2023 Publication History

Abstract

The integration of smart thermostats in home automation systems has created an opportunity to optimize space heating and cooling through the use of machine learning, for example for thermal model identification. Nonetheless, its full potential remains untapped due to the lack of a suitable learning scheme. Traditional centralized learning (CL) and federated learning (FL) schemes could pose privacy and security concerns, and result in a generic model that does not adequately represent thermal requirements and characteristics of each individual home. To overcome these limitations, in this paper we embrace the novel peer-to-peer learning scheme for on-device training of home thermal models. Specifically, we adapt the personalized peer-to-peer algorithm proposed in recent work (called P3) to efficiently train personalized thermal models on resource-constrained devices. Our preliminary experiments with data from 1,000 homes, using the LSTM model, demonstrate that the adapted P3 algorithm produces accurate and personalized thermal models while being extremely energy-efficient, consuming respectively 600 and 40 times less energy than the CL and FL schemes. This result suggests that the P3 algorithm offers a privacy-conscious, accurate, and energy-efficient solution for training thermal models for the many homes in the building stock.

References

[1]
2023. Thermal P3. https://github.com/karimboubouh/Thermal-P3.
[2]
Sonny Ali and Zia Yusuf. 2018. Mapping the smart-home market.
[3]
Onur Ayan and Belgin Turkay. 2018. Smart thermostats for home automation systems and energy savings from smart thermostats. In 2018 6th International Conference on Control Engineering & Information Technology (CEIT). IEEE, 1–6.
[4]
Peder Bacher and Henrik Madsen. 2011. Identifying suitable models for the heat dynamics of buildings. Energy and Buildings 43, 7 (2011), 1511–1522.
[5]
Robert Basmadjian, Karim Boubouh, Amine Boussetta, Rachid Guerraoui, and Alexandre Maurer. 2022. On the advantages of P2P ML on mobile devices. In Proceedings of the Thirteenth ACM International Conference on Future Energy Systems. 338–353.
[6]
Robert Basmadjian, Amirhossein Shaafieyoun, and Sahib Julka. 2021. Day-Ahead Forecasting of the Percentage of Renewables Based on Time-Series Statistical Methods. Energies 14, 21 (2021). https://doi.org/10.3390/en14217443
[7]
Karim Boubouh, Amine Boussetta, Yahya Benkaouz, and Rachid Guerraoui. 2020. Robust P2P Personalized Learning. In 2020 International Symposium on Reliable Distributed Systems (SRDS). IEEE, 299–308.
[8]
Patrick Cousot and Radhia Cousot. 2014. Abstract interpretation: past, present and future. In Proceedings of the Joint Meeting of the Twenty-Third EACSL Annual Conference on Computer Science Logic (CSL) and the Twenty-Ninth Annual ACM/IEEE Symposium on Logic in Computer Science (LICS). 1–10.
[9]
Drury B Crawley, Linda K Lawrie, Curtis O Pedersen, and Frederick C Winkelmann. 2000. Energy plus: energy simulation program. ASHRAE journal 42, 4 (2000), 49–56.
[10]
Drury B Crawley, Linda K Lawrie, Frederick C Winkelmann, Walter F Buhl, Y Joe Huang, Curtis O Pedersen, Richard K Strand, Richard J Liesen, Daniel E Fisher, Michael J Witte, 2001. EnergyPlus: creating a new-generation building energy simulation program. Energy and buildings 33, 4 (2001), 319–331.
[11]
L. Di Natale, B. Svetozarevic, P. Heer, and C.N. Jones. 2022. Physically Consistent Neural Networks for building thermal modeling: Theory and analysis. Applied Energy 325 (2022), 119806.
[12]
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, and Michael Moeller. 2020. Inverting gradients-how easy is it to break privacy in federated learning?Advances in Neural Information Processing Systems 33 (2020), 16937–16947.
[13]
Grant Hernandez, Orlando Arias, Daniel Buentello, and Yier Jin. 2014. Smart nest thermostat: A smart spy in your home. Black Hat USA2015 (2014).
[14]
Md Monir Hossain, Tianyu Zhang, and Omid Ardakanian. 2019. Evaluating the Feasibility of Reusing Pre-Trained Thermal Models in the Residential Sector. In Proceedings of the 1st ACM International Workshop on Urban Building Energy Sensing, Controls, Big Data Analysis, and Visualization(UrbSys’19). ACM, 23–32.
[15]
Md Monir Hossain, Tianyu Zhang, and Omid Ardakanian. 2021. Identifying grey-box thermal models with Bayesian neural networks. Energy and Buildings 238 (2021), 110836.
[16]
Brent Huchuk, Scott Sanner, and William O’Brien. 2019. Comparison of machine learning models for occupancy prediction in residential buildings using connected thermostat data. Building and Environment 160 (2019), 106177.
[17]
Kalpana D Joshi and PS Nalwade. 2013. Modified k-means for better initial cluster centres. International Journal of Computer Science and Mobile Computing 2, 7 (2013), 219–223.
[18]
Mohd Ehmer Khan and Farmeena Khan. 2012. A comparative study of white box, black box and grey box testing techniques. International Journal of Advanced Computer Science and Applications 3, 6 (2012).
[19]
Julien Leprince, Henrik Madsen, Clayton Miller, Jaume Palmer Real, Rik van der Vlist, Kaustav Basu, and Wim Zeiler. 2022. Fifty shades of grey: Automated stochastic model identification of building heat dynamics. Energy and Buildings 266 (2022), 112095.
[20]
Na Luo and Tianzhen Hong. 2022. Ecobee Donate Your Data 1,000 homes in 2017. (3 2022). https://doi.org/10.25584/ecobee/1854924
[21]
Miguel Martínez Comesaña, Lara Febrero-Garrido, Francisco Troncoso-Pastoriza, and Javier Martínez-Torres. 2020. Prediction of building’s thermal performance using LSTM and MLP neural networks. Applied Sciences 10, 21 (2020), 7439.
[22]
Leopold Mba, Pierre Meukam, and Alexis Kemajou. 2016. Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region. Energy and Buildings 121 (2016), 32–42.
[23]
Giorgio Mustafaraj, Gordon Lowry, and Jie Chen. 2011. Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural network models for an open office. Energy and Buildings 43, 6 (2011), 1452–1460.
[24]
SL Patil, HJ Tantau, and VM Salokhe. 2008. Modelling of tropical greenhouse temperature by auto regressive and neural network models. Biosystems engineering 99, 3 (2008), 423–431.
[25]
Quoc Bao Huy Tran and Sun-Tae Chung. 2020. Smart Thermostat based on Machine Learning and Rule Engine. Journal of Korea Multimedia Society 23, 2 (2020), 155–165.
[26]
Charalampos Vallianos, Andreas Athienitis, and Benoit Delcroix. 2022. Automatic generation of multi-zone RC models using smart thermostat data from homes. Energy and Buildings 277 (2022), 112571.
[27]
Paul Vanhaesebrouck, Aurélien Bellet, and Marc Tommasi. 2017. Decentralized Collaborative Learning of Personalized Models over Networks. In Artificial Intelligence and Statistics (AISTATS).
[28]
Chengliang Xu, Huanxin Chen, Jiangyu Wang, Yabin Guo, and Yue Yuan. 2019. Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method. Building and Environment 148 (2019), 128–135.
[29]
Danilo Yu, Abdolreza Abhari, Alan S Fung, Kaamran Raahemifar, and Farahnaz Mohammadi. 2018. Predicting indoor temperature from smart thermostat and weather forecast data. In Proceedings of the Communications and Networking Symposium. 1–12.

Cited By

View all
  • (2023)PePTM: An Efficient and Accurate Personalized P2P Learning Algorithm for Home Thermal ModelingEnergies10.3390/en1618659416:18(6594)Online publication date: 13-Sep-2023

Index Terms

  1. Efficient and Accurate Peer-to-Peer Training of Machine Learning Based Home Thermal Models

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    e-Energy '23: Proceedings of the 14th ACM International Conference on Future Energy Systems
    June 2023
    545 pages
    ISBN:9798400700323
    DOI:10.1145/3575813
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 16 June 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Smart thermostats
    2. energy-efficiency
    3. peer-to-peer machine learning
    4. personalized models.
    5. thermal models

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    e-Energy '23
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 160 of 446 submissions, 36%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)22
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 25 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2023)PePTM: An Efficient and Accurate Personalized P2P Learning Algorithm for Home Thermal ModelingEnergies10.3390/en1618659416:18(6594)Online publication date: 13-Sep-2023

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media