Personalizing Individual Comfort in the Group Setting

Maintaining individual thermal comfort in indoor spaces shared by multiple occupants is difficult because it requires both intuition about the thermal properties of the room, as well as an understanding of the thermal comfort preferences of each individual. We explore an approach to optimizing individual thermal comfort within a group through temperature set-point optimization of HVAC equipment. We propose a weakly-supervised algorithm to learn the individual thermal comfort preferences and an autoencoding framework to learn static approximations of room thermodynamics. We further propose two approaches to learn a control law that sets the HVAC set-points subject to the preferred user temperatures. The proposed method is tested on a real data-set obtained from workers in an open office. The results show that, on average, the temperature in the room at each user's location can be regulated to within 0.5C of the user's desired temperature.

[1]  Muhammad Azam,et al.  Autoregressive neural networks with exogenous variables for indoor temperature prediction in buildings , 2020, Building Simulation.

[2]  Yong Luo,et al.  Heterogeneous Transfer Learning for Thermal Comfort Modeling , 2019, BuildSys@SenSys.

[3]  Lim Xin Yi,et al.  Predicting Individual Thermal Comfort , 2019, IRC-SET 2018.

[4]  A. Natarajan,et al.  Transfer Active Learning Framework to Predict Thermal Comfort , 2023, International Journal of Prognostics and Health Management.

[5]  Joyce Kim,et al.  Personal comfort models – A new paradigm in thermal comfort for occupant-centric environmental control , 2018 .

[6]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[7]  Hui Zhang,et al.  Augmenting Smart Buildings and Autonomous Vehicles with Wearable Thermal Technology , 2017, HCI.

[8]  Daniel Nikovski,et al.  An IoT system to estimate personal thermal comfort , 2016, 2016 IEEE 3rd World Forum on Internet of Things (WF-IoT).

[9]  Juhi Ranjan,et al.  ThermalSense: determining dynamic thermal comfort preferences using thermographic imaging , 2016, UbiComp.

[10]  Lai Jiang,et al.  Modelling personal thermal sensations using C-Support Vector Classification (C-SVC) algorithm , 2016 .

[11]  Krishna R. Pattipati,et al.  Predicting individual thermal comfort using machine learning algorithms , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[12]  Mark W. Newman,et al.  The potential and challenges of inferring thermal comfort at home using commodity sensors , 2015, UbiComp.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Jianjun Hu,et al.  A state-space modeling approach and multi-level optimization algorithm for predictive control of multi-zone buildings with mixed-mode cooling , 2014 .

[15]  Mallory L Taub,et al.  Power to the people: personal control in offices for thermal comfort and energy savings , 2013 .

[16]  R. Balmer Chapter 12 – Mixtures of Gases and Vapors , 2011 .

[17]  M Morari,et al.  Energy efficient building climate control using Stochastic Model Predictive Control and weather predictions , 2010, Proceedings of the 2010 American Control Conference.

[18]  Sean P. Meyn,et al.  Building thermal model reduction via aggregation of states , 2010, Proceedings of the 2010 American Control Conference.

[19]  Frédéric Haldi,et al.  Towards a Unified Model of Occupants" Behaviour and Comfort for Building Energy Simulation , 2010 .

[20]  Alan Hedge,et al.  Thermal Effects on Office Productivity , 2005 .

[21]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[22]  Standard Ashrae Thermal Environmental Conditions for Human Occupancy , 1992 .