Intelligent occupancy-driven thermostat by dynamic user profiling

Matching system functionality and user needs by learning from user behaviour enables a significant reduction in energy consumption. Habits and routine behaviour are exploited and captured in user profiles to automatically create customized heating schedules. However, over time the user conduct can change either gradually or abruptly and old occupancy patterns could become obsolete. Hence, a self-learning system should be able to cope with these changes and adapt the identified user profiles accordingly. An approach to track changing behaviour and update the corresponding user profiles, and hence heating schedules, is presented. The proposed strategy is evaluated by comparing prediction accuracy and potential energy savings to the case where learning is static and to incremental learning strategies. The results are illustrated by means of a real-life dataset of a single-user office.

[1]  Geoffrey I. Webb,et al.  # 2001 Kluwer Academic Publishers. Printed in the Netherlands. Machine Learning for User Modeling , 1999 .

[2]  Michalis Vazirgiannis,et al.  Clustering validity checking methods: part II , 2002, SGMD.

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

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

[5]  João Gama,et al.  A framework to monitor clusters evolution applied to economy and finance problems , 2012, Intell. Data Anal..

[6]  Therese Peffer,et al.  How people use thermostats in homes: A review , 2011, Building and Environment.

[7]  Antonio Capone,et al.  Home energy saving through a user profiling system based on wireless sensors , 2009, BuildSys '09.

[8]  Joris Vertommen.  Construction and Maintenance of User Profiles for Knowledge Management Systems (Constructie en onderhoud van gebruikersprofielen voor kennisbeheersystemen) , 2009 .

[9]  Ming-Syan Chen,et al.  Catching the Trend: A Framework for Clustering Concept-Drifting Categorical Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[10]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  OLINDDA: a cluster-based approach for detecting novelty and concept drift in data streams , 2007, SAC '07.

[11]  Silvia Santini,et al.  Predicting household occupancy for smart heating control: A comparative performance analysis of state-of-the-art approaches , 2014 .

[12]  Myra Spiliopoulou,et al.  MONIC: modeling and monitoring cluster transitions , 2006, KDD '06.

[13]  Michal Wozniak,et al.  Concept Drift Detection and Model Selection with Simulated Recurrence and Ensembles of Statistical Detectors , 2013, J. Univers. Comput. Sci..

[14]  Grigorios Tsoumakas,et al.  Incremental Clustering for the Classification of Concept-Drifting Data Streams , 2008 .

[15]  Kitsana Waiyamai,et al.  E-Stream: Evolution-Based Technique for Stream Clustering , 2007, ADMA.

[16]  Abdelhamid Bouchachia,et al.  Fuzzy classification in dynamic environments , 2011, Soft Comput..

[17]  Abdelhamid Bouchachia,et al.  GT2FC: An Online Growing Interval Type-2 Self-Learning Fuzzy Classifier , 2014, IEEE Transactions on Fuzzy Systems.

[18]  Joost Duflou,et al.  User Adapting System Design for Improved Energy Efficiency During the Use Phase of Products: Case Study of an Occupancy-Driven, Self-Learning Thermostat , 2015 .

[19]  Wolfgang Kastner,et al.  Usage profiles for sustainable buildings , 2010, 2010 IEEE 15th Conference on Emerging Technologies & Factory Automation (ETFA 2010).

[20]  Hussein Mouftah,et al.  An adaptable system for energy management in intelligent buildings , 2011, 2011 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings.

[21]  Analía Amandi,et al.  User profiling in personal information agents: a survey , 2005, The Knowledge Engineering Review.

[22]  Ivan Koychev,et al.  Adaptation to Drifting User's Interests , 2000 .

[23]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Data stream clustering: A survey , 2013, CSUR.

[24]  Mark W. Newman,et al.  Learning from a learning thermostat: lessons for intelligent systems for the home , 2013, UbiComp.

[25]  Ngoc Thanh Nguyen,et al.  Tuning user profiles based on analyzing dynamic preference in document retrieval systems , 2013, Multimedia Tools and Applications.

[26]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[27]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Novelty detection in data streams , 2015, Artificial Intelligence Review.

[28]  Yong Tang,et al.  A Concept Drifting Based Clustering Framework for Data Streams , 2013, 2013 Fourth International Conference on Emerging Intelligent Data and Web Technologies.