DECISION SUPPORT SYSTEMS FOR DOMESTIC RETROFIT PROVISION USING SMART HOME DATA STREAMS

The scope of this paper is a study of the potential of decision support systems for retrofit provision in domestic buildings, using monitoring technologies and performance-based analysis. The key research question is: in the age of proliferation of cheap, mobile and networked sensing equipment, how can measured energy and performance data from multiple in-home sensors be utilised to accelerate building retrofit measures and energy demand reduction? Over the coming decade there will be a significant increase in the amount of measured data available from households, from national Smart Meter rollouts to personal Smart Home systems, which will provide unparalleled insights into how our homes are performing and how households are behaving. The new data streams from Smart Homes will challenge the prevailing research and policy initiatives for understanding and promoting energy-saving building retrofits. This work is part of a £1.5m UK Research Council funded project ‘REFIT: Personalised Retrofit Decision Support Tools for UK Homes using Smart Home Technology’ (www.refitsmarthomes.org). Three methods are combined to give multiple perspectives of the research challenge: 1) A literature review on Smart Homes with a focus on academic progress to date in this area; 2) Results from actual Smart Home monitored data streams, as measured in an on-going study of UK-based Smart Homes; and 3) a discussion of performance-based analysis leading to insights in decision support system provision for Smart Building owners. The approach outlined in this work will be of significant interest to national governments when promoting Smart Meter roll-outs, to energy companies in promoting new services using Smart Home data and to the academic community in providing a foundation for future studies to meet the domestic building retrofit challenge.

[1]  Sajal K. Das,et al.  LeZi-update: an information-theoretic approach to track mobile users in PCS networks , 1999, MobiCom.

[2]  Gregory D. Abowd,et al.  The Aware Home: A Living Laboratory for Ubiquitous Computing Research , 1999, CoBuild.

[3]  Michael Nye,et al.  Making energy visible: A qualitative field study of how householders interact with feedback from smart energy monitors , 2010 .

[4]  Diane J. Cook,et al.  The role of prediction algorithms in the MavHome smart home architecture , 2002, IEEE Wirel. Commun..

[5]  M. Pavel,et al.  Unobtrusive monitoring of sleep patterns , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[6]  William C. Mann,et al.  Enabling location-aware pervasive computing applications for the elderly , 2003, Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003)..

[7]  Bryan Horling,et al.  The Intelligent Home Testbed , 2004 .

[8]  Michael C. Mozer,et al.  The Neural Network House: An Environment that Adapts to its Inhabitants , 1998 .

[9]  J. Krumm,et al.  Multi-camera multi-person tracking for EasyLiving , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.