{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:34:49Z","timestamp":1774362889869,"version":"3.50.1"},"reference-count":30,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2015,3,11]],"date-time":"2015-03-11T00:00:00Z","timestamp":1426032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"United Kingdom by the EPSRC Intelligent Agents for Home Energy Management project (EP\/I000143\/1) and ORCHID programme","award":["EP\/I011587\/1"],"award-info":[{"award-number":["EP\/I011587\/1"]}]},{"name":"Kingdom of Saudi Arabia by the Deanship of Scientific Research (DSR), King Abdulaziz University, Jeddah (9-15-1432-HiCi)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2015,3,11]]},"abstract":"<jats:p>Minimizing the energy consumed by heating, ventilation, and air conditioning (HVAC) systems of residential buildings without impacting occupants\u2019 comfort has been highlighted as an important artificial intelligence (AI) challenge. Typically, approaches that seek to address this challenge use a model that captures the thermal dynamics within a building, also referred to as a thermal model. Among thermal models, gray-box models are a popular choice for modeling the thermal dynamics of buildings. They combine knowledge of the physical structure of a building with various data-driven inputs and are accurate estimators of the state (internal temperature). However, existing gray-box models require a detailed specification of all the physical elements that can affect the thermal dynamics of a building a priori. This limits their applicability, particularly in residential buildings, where additional dynamics can be induced by human activities such as cooking, which contributes additional heat, or opening of windows, which leads to additional leakage of heat. Since the incidence of these additional dynamics is rarely known, their combined effects cannot readily be accommodated within existing models.<\/jats:p>\n          <jats:p>To overcome this limitation and improve the general applicability of gray-box models, we introduce a novel model, which we refer to as a latent force thermal model of the thermal dynamics of a building, or LFM-TM. Our model is derived from an existing gray-box thermal model, which is augmented with an extra term referred to as the learned residual. This term is capable of modeling the effect of any a priori unknown additional dynamic, which, if not captured, appears as a structure in a thermal model\u2019s residual (the error induced by the model). More importantly, the learned residual can also capture the effects of physical elements such as a building\u2019s envelope or the lags in a heating system, leading to a significant reduction in complexity compared to existing models.<\/jats:p>\n          <jats:p>To evaluate the performance of LFM-TM, we apply it to two independent data sources. The first is an established dataset, referred to as the FlexHouse data, which was previously used for evaluating the efficacy of existing gray-box models [Bacher and Madsen 2011]. The second dataset consists of heating data logged within homes located on the University of Southampton campus, which were specifically instrumented to collect data for our thermal modeling experiments. On both datasets, we show that LFM-TM outperforms existing models in its ability to accurately fit the observed data, generate accurate day-ahead internal temperature predictions, and explain a large amount of the variability in the future observations. This, along with the fact that we also use a corresponding efficient sequential inference scheme for LFM-TM, makes it an ideal candidate for model-based predictive control, where having accurate online predictions of internal temperatures is essential for high-quality solutions.<\/jats:p>","DOI":"10.1145\/2629674","type":"journal-article","created":{"date-parts":[[2015,3,12]],"date-time":"2015-03-12T12:18:05Z","timestamp":1426162685000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Modeling the Thermal Dynamics of Buildings"],"prefix":"10.1145","volume":"6","author":[{"given":"Siddhartha","family":"Ghosh","sequence":"first","affiliation":[{"name":"University of Southampton"}]},{"given":"Steve","family":"Reece","sequence":"additional","affiliation":[{"name":"University of Oxford"}]},{"given":"Alex","family":"Rogers","sequence":"additional","affiliation":[{"name":"University of Southampton"}]},{"given":"Stephen","family":"Roberts","sequence":"additional","affiliation":[{"name":"University of Oxford"}]},{"given":"Areej","family":"Malibari","sequence":"additional","affiliation":[{"name":"King Abdulaziz University, Saudi Arabia"}]},{"given":"Nicholas R.","family":"Jennings","sequence":"additional","affiliation":[{"name":"University of Southampton and King Abdulaziz University, Saudi Arabia"}]}],"member":"320","published-online":{"date-parts":[[2015,3,11]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"9","article-title":"Latent force models","volume":"5","author":"\u00c1lvarez Mauricio A.","year":"2009","unstructured":"Mauricio A. \u00c1lvarez , David Luengo , and Neil D. Lawrence . 2009 . Latent force models . Journal of Machine Learning Research - Proceedings Track 5 (2009), 9 -- 16 . Mauricio A. \u00c1lvarez, David Luengo, and Neil D. Lawrence. 2009. Latent force models. Journal of Machine Learning Research - Proceedings Track 5 (2009), 9--16.","journal-title":"Journal of Machine Learning Research - Proceedings Track"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of Neural Information Processing Systems (NIPS\u201910)","author":"\u00c1lvarez Mauricio A.","unstructured":"Mauricio A. \u00c1lvarez , Jan Peters , Bernhard Sch\u00f6lkopf , and Neil D. Lawrence . 2010. Switched latent force models for movement segmentation . In Proceedings of Neural Information Processing Systems (NIPS\u201910) . 55--63. Mauricio A. \u00c1lvarez, Jan Peters, Bernhard Sch\u00f6lkopf, and Neil D. Lawrence. 2010. Switched latent force models for movement segmentation. In Proceedings of Neural Information Processing Systems (NIPS\u201910). 55--63."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-7788(98)00069-3"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2161242"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2011.02.005"},{"key":"e_1_2_1_6_1","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher M.","unstructured":"Christopher M. Bishop . 2006. Pattern Recognition and Machine Learning . Springer . Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning. Springer."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859921"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2008.09.015"},{"key":"e_1_2_1_9_1","volume-title":"Time Series Analysis by State Space Methods. Number 24","author":"Durbin James","unstructured":"James Durbin and Siem Jan Koopman . 2001. Time Series Analysis by State Space Methods. Number 24 . Oxford University Press . James Durbin and Siem Jan Koopman. 2001. Time Series Analysis by State Space Methods. Number 24. Oxford University Press."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/30.85542"},{"key":"e_1_2_1_11_1","volume-title":"When the optimal is not the best: Parameter estimation in complex biological models. PLoS ONE 5, 10","author":"Slezak Diego Fern\u00e1ndez","year":"2010","unstructured":"Diego Fern\u00e1ndez Slezak , Cecilia Su\u00e1rez , Guillermo A. Cecchi , Guillermo Marshall , and Gustavo Stolovitzky . 2010. When the optimal is not the best: Parameter estimation in complex biological models. PLoS ONE 5, 10 ( 2010 ). Diego Fern\u00e1ndez Slezak, Cecilia Su\u00e1rez, Guillermo A. Cecchi, Guillermo Marshall, and Gustavo Stolovitzky. 2010. When the optimal is not the best: Parameter estimation in complex biological models. PLoS ONE 5, 10 (2010)."},{"key":"e_1_2_1_12_1","volume-title":"Andrews","author":"Grewal Mohinder S.","year":"2001","unstructured":"Mohinder S. Grewal and Angus P . Andrews . 2001 . Kalman Filtering : Theory and Practice Using MATLAB. Wiley-Interscience . Mohinder S. Grewal and Angus P. Andrews. 2001. Kalman Filtering: Theory and Practice Using MATLAB. Wiley-Interscience."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2010.5589113"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of Uncertainty in Artificial Intelligence (UAI\u201911)","author":"Hartikainen Jouni","year":"2011","unstructured":"Jouni Hartikainen and Simo S\u00e4rkk\u00e4 . 2011 . Sequential inference for latent force models . In Proceedings of Uncertainty in Artificial Intelligence (UAI\u201911) . 311--318. Jouni Hartikainen and Simo S\u00e4rkk\u00e4. 2011. Sequential inference for latent force models. In Proceedings of Uncertainty in Artificial Intelligence (UAI\u201911). 311--318."},{"key":"e_1_2_1_15_1","volume-title":"Jimenez and Henrik Madsen","author":"Miguel","year":"2008","unstructured":"Miguel J. Jimenez and Henrik Madsen . 2008 . Models for describing the thermal characteristics of building components. Building and Environment 43, 2 (2 2008), 152--162. Miguel J. Jimenez and Henrik Madsen. 2008. Models for describing the thermal characteristics of building components. Building and Environment 43, 2 (2 2008), 152--162."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869983.1870005"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0378-7788(94)00904-X"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI\u201911)","author":"El-Din Mady Alie","unstructured":"Alie El-Din Mady , Gregory Provan , Conor Ryan , and Kenneth N. Brown . 2011. Stochastic model predictive controller for the integration of building use and temperature regulation . In Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI\u201911) . Alie El-Din Mady, Gregory Provan, Conor Ryan, and Kenneth N. Brown. 2011. Stochastic model predictive controller for the integration of building use and temperature regulation. In Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI\u201911)."},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of Neural Information Processing Systems (NIPS\u201996)","author":"Mozer Michael","unstructured":"Michael Mozer , Lucky Vidmar , and Robert H. Dodier . 1996. The neurothermostat: Predictive optimal control of residential heating systems . In Proceedings of Neural Information Processing Systems (NIPS\u201996) . 953--959. Michael Mozer, Lucky Vidmar, and Robert H. Dodier. 1996. The neurothermostat: Predictive optimal control of residential heating systems. In Proceedings of Neural Information Processing Systems (NIPS\u201996). 953--959."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2011.09.022"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2012.10.024"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2012.08.040"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2133806.2133825"},{"key":"e_1_2_1_24_1","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen Carl","unstructured":"Carl Rasmussen and Christopher Williams . 2005. Gaussian Processes for Machine Learning . MIT Press . Carl Rasmussen and Christopher Williams. 2005. Gaussian Processes for Machine Learning. MIT Press."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/37.845037"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 2nd Agent Technologies for Energy Systems Workshop (AAMAS\u201911)","author":"Rogers Alex","year":"2011","unstructured":"Alex Rogers , Sasan Maleki , Siddhartha Ghosh , and Nick Jennings . 2011 . Adaptive home heating control through Gaussian process prediction and mathematical programming . In Proceedings of the 2nd Agent Technologies for Energy Systems Workshop (AAMAS\u201911) . Alex Rogers, Sasan Maleki, Siddhartha Ghosh, and Nick Jennings. 2011. Adaptive home heating control through Gaussian process prediction and mathematical programming. In Proceedings of the 2nd Agent Technologies for Energy Systems Workshop (AAMAS\u201911)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030151"},{"key":"e_1_2_1_28_1","volume-title":"H Infinity, and Nonlinear Approaches","author":"Simon Dan","unstructured":"Dan Simon . 2006. Optimal State Estimation: Kalman , H Infinity, and Nonlinear Approaches . Wiley . Dan Simon. 2006. Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches. Wiley."},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS\u201913)","author":"Urieli Daniel","year":"2013","unstructured":"Daniel Urieli and Peter Stone . 2013 . A learning agent for heat-pump thermostat control . In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS\u201913) . 1093--1100. Daniel Urieli and Peter Stone. 2013. A learning agent for heat-pump thermostat control. In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS\u201913). 1093--1100."},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the 2012 IEEE Power and Energy Society General Meeting. 1--9.","author":"Yu Zhe","year":"2012","unstructured":"Zhe Yu , Linda McLaughlin , Liyan Jia , Mary C. Murphy-Hoye , Annabelle Pratt , and Lang Tong . 2012 . Modeling and stochastic control for home energy management . In Proceedings of the 2012 IEEE Power and Energy Society General Meeting. 1--9. Zhe Yu, Linda McLaughlin, Liyan Jia, Mary C.Murphy-Hoye, Annabelle Pratt, and Lang Tong. 2012. Modeling and stochastic control for home energy management. In Proceedings of the 2012 IEEE Power and Energy Society General Meeting. 1--9."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2629674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2629674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:13:30Z","timestamp":1750227210000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2629674"}},"subtitle":["A Latent-Force- Model-Based Approach"],"short-title":[],"issued":{"date-parts":[[2015,3,11]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,3,11]]}},"alternative-id":["10.1145\/2629674"],"URL":"https:\/\/doi.org\/10.1145\/2629674","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3,11]]},"assertion":[{"value":"2013-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2014-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2015-03-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}