Predicting household occupancy for smart heating control: A comparative performance analysis of state-of-the-art approaches

Abstract This paper provides a comparative study of state-of-the-art means of predicting occupancy for smart heating control applications. We focus on approaches that predict the occupancy state of a home using occupancy schedules – that is, past records of the occupancy state. We ran our analysis on actual occupancy schedules covering several months for 45 homes. Our results show that state-of-the-art, schedule-based occupancy prediction algorithms achieve an overall prediction accuracy of over 80%. We also show that the performance of these algorithms is close to the theoretical upper bound expressed by the predictability of the input schedules. Building upon these results, we used ISO 13790-standard modelling techniques to analyse the energy savings that can be achieved by smart heating controllers that use occupancy predictors. Furthermore, we investigated the trade-off between achievable savings (typically 6–17% on average) and the risk of comfort loss for household residents.

[1]  Daniel Gatica-Perez,et al.  Discovering routines from large-scale human locations using probabilistic topic models , 2011, TIST.

[2]  Silvia Santini,et al.  Occupancy Detection from Electricity Consumption Data , 2013, BuildSys@SenSys.

[3]  Edward Henry Mathews,et al.  A first-order thermal model for building design , 1994 .

[4]  Kamin Whitehouse,et al.  The hitchhiker's guide to successful residential sensing deployments , 2011, SenSys.

[5]  John Krumm,et al.  EarlyOff: using house cooling rates to save energy , 2012, BuildSys@SenSys.

[6]  Cecilia Mascolo,et al.  NextPlace: A Spatio-temporal Prediction Framework for Pervasive Systems , 2011, Pervasive.

[7]  Kent Larson,et al.  Adding GPS-Control to Traditional Thermostats: An Exploration of Potential Energy Savings and Design Challenges , 2009, Pervasive.

[8]  Silvia Santini,et al.  Using unlabeled Wi-Fi scan data to discover occupancy patterns of private households , 2013, SenSys '13.

[9]  Hojung Cha,et al.  Occupancy Prediction Algorithms for Thermostat Control Systems Using Mobile Devices , 2013, IEEE Transactions on Smart Grid.

[10]  Thomas Weng,et al.  Duty-cycling buildings aggressively: The next frontier in HVAC control , 2011, Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks.

[11]  Prashant J. Shenoy,et al.  Non-Intrusive Occupancy Monitoring using Smart Meters , 2013, BuildSys@SenSys.

[12]  N. Helbig,et al.  Application of the radiosity approach to the radiation balance in complex terrain , 2009 .

[13]  J. Kurnitski,et al.  Performance of EN ISO 13790 utilisation factor heat demand calculation method in a cold climate , 2007 .

[14]  Wen-Jing Hsu,et al.  Predictability of individuals' mobility with high-resolution positioning data , 2012, UbiComp.

[15]  D. Gática-Pérez,et al.  Towards rich mobile phone datasets: Lausanne data collection campaign , 2010 .

[16]  José A. Orosa,et al.  Implementation of a method in EN ISO 13790 for calculating the utilisation factor taking into account different permeability levels of internal coverings , 2010 .

[17]  Gregor P. Henze,et al.  The performance of occupancy-based lighting control systems: A review , 2010 .

[18]  Gregor P. Henze,et al.  Building occupancy detection through sensor belief networks , 2006 .

[19]  John Krumm,et al.  Learning Time-Based Presence Probabilities , 2011, Pervasive.

[20]  Xing Xie,et al.  Mining Individual Life Pattern Based on Location History , 2009, 2009 Tenth International Conference on Mobile Data Management: Systems, Services and Middleware.

[21]  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.

[22]  Silvia Santini,et al.  The influence of temporal and spatial features on the performance of next-place prediction algorithms , 2013, UbiComp.

[23]  John Ingersoll,et al.  Heating energy use management in residential buildings by temperature control , 1985 .

[24]  C. L. Gupta,et al.  A systematic approach to optimum thermal design , 1970 .

[25]  Gail Brager,et al.  Comport control for short-term occupancy , 1994 .

[26]  Eric Horvitz,et al.  Predestination: Inferring Destinations from Partial Trajectories , 2006, UbiComp.

[27]  T. Agami Reddy,et al.  Applied Data Analysis and Modeling for Energy Engineers and Scientists , 2011 .

[28]  Kamin Whitehouse,et al.  The smart thermostat: using occupancy sensors to save energy in homes , 2010, SenSys '10.

[29]  Wolfgang Kastner,et al.  Clustering methods for occupancy prediction in smart home control , 2011, 2011 IEEE International Symposium on Industrial Electronics.

[30]  Masamichi Shimosaka,et al.  A Unified Framework for Modeling and Predicting Going-Out Behavior , 2012, Pervasive.

[31]  Michael C. Mozer,et al.  The Neurothermostat: Predictive Optimal Control of Residential Heating Systems , 1996, NIPS.

[32]  Friedemann Mattern,et al.  Simulating the energy savings potential in domestic heating scenarios in Switzerland , 2014 .

[33]  John Krumm,et al.  PreHeat: controlling home heating using occupancy prediction , 2011, UbiComp '11.

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

[35]  Anind K. Dey,et al.  TherML: occupancy prediction for thermostat control , 2013, UbiComp.

[36]  Tuan Anh Nguyen,et al.  Energy intelligent buildings based on user activity: A survey , 2013 .

[37]  Miguel Á. Carreira-Perpiñán,et al.  OBSERVE: Occupancy-based system for efficient reduction of HVAC energy , 2011, Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks.

[38]  John A. Stankovic,et al.  Empath: a continuous remote emotional health monitoring system for depressive illness , 2011, Wireless Health.

[39]  Albert-László Barabási,et al.  Limits of Predictability in Human Mobility , 2010, Science.