Online transfer learning for climate control in residential buildings

This paper presents an online transfer learning framework for improving temperature predictions in residential buildings. In transfer learning, prediction models trained under a set of available data from a target domain (e.g., house with limited data) can be improved through the use of data generated from similar source domains (e.g., houses with rich data). Given also the need for prediction models that can be trained online (e.g., as part of a model-predictive-control implementation), this paper introduces the generalized online transfer learning algorithm (GOTL). It employs a weighted combination of the available predictors (i.e., the target and source predictors) and guarantees convergence to the best weighted predictor. We further validate our results through experiments in climate control for residential buildings.

[1]  Manfred K. Warmuth,et al.  The Weighted Majority Algorithm , 1994, Inf. Comput..

[2]  Paulo Sergio Ramirez,et al.  Fundamentals of Adaptive Filtering , 2002 .

[3]  Hao Hu,et al.  Transfer learning for WiFi-based indoor localization , 2008, AAAI 2008.

[4]  Jorge Martínez Gil,et al.  Realistic User Behavior Modeling for Energy Saving in Residential Buildings , 2014, 2014 25th International Workshop on Database and Expert Systems Applications.

[5]  Bin Li,et al.  Online Transfer Learning , 2014, Artif. Intell..

[6]  Bernhard Schölkopf,et al.  Domain Generalization via Invariant Feature Representation , 2013, ICML.

[7]  Massimiliano Pontil,et al.  Multi-Task Feature Learning , 2006, NIPS.

[8]  Bo Wahlberg,et al.  Physics-based modeling and identification for HVAC systems? , 2013, 2013 European Control Conference (ECC).

[9]  Nicolas Petit,et al.  Thermal building model identification using time-scaled identification methods , 2010, 49th IEEE Conference on Decision and Control (CDC).

[10]  Steven C. H. Hoi,et al.  OTL: A Framework of Online Transfer Learning , 2010, ICML.

[11]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[12]  Manfred Morari,et al.  Use of model predictive control and weather forecasts for energy efficient building climate control , 2012 .

[13]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[14]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[15]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[16]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[17]  Michael Baldea,et al.  Model reduction and nonlinear MPC for energy management in buildings , 2013, 2013 American Control Conference.

[18]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[19]  Kenneth G. Henshall.  Bibliography of References , 2012 .

[20]  Gilles Blanchard,et al.  Generalizing from Several Related Classification Tasks to a New Unlabeled Sample , 2011, NIPS.

[21]  George J. Pappas,et al.  Receding-horizon supervisory control of green buildings , 2011, Proceedings of the 2011 American Control Conference.

[22]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[23]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[24]  Philip M. Long,et al.  Online Learning of Multiple Tasks with a Shared Loss , 2007, J. Mach. Learn. Res..

[25]  Thomas Natschläger,et al.  Generalized Online Transfer Learning for Climate Control in Residential Buildings , 2016, ArXiv.

[26]  Thomas Natschläger,et al.  Nonlinear system identification of thermal dynamics in buildings , 2014, 2014 European Control Conference (ECC).

[27]  Thomas Natschläger,et al.  Regression Models for Output Prediction of Thermal Dynamics in Buildings , 2016, ArXiv.

[28]  Tom Heskes,et al.  Domain Generalization Based on Transfer Component Analysis , 2015, IWANN.

[29]  Robert Givan,et al.  Online Ensemble Learning: An Empirical Study , 2000, Machine Learning.

[30]  Shengwei Wang,et al.  Multiple ARMAX modeling scheme for forecasting air conditioning system performance , 2007 .

[31]  H. Young,et al.  The Evolution of Conventions , 1993 .

[32]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[33]  Jie Chen,et al.  Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural n , 2011 .

[34]  Salvatore J. Stolfo,et al.  The application of AdaBoost for distributed, scalable and on-line learning , 1999, KDD '99.

[35]  Geoffrey E. Hinton,et al.  Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes , 2007, NIPS.

[36]  Alex Simpkins,et al.  System Identification: Theory for the User, 2nd Edition (Ljung, L.; 1999) [On the Shelf] , 2012, IEEE Robotics & Automation Magazine.