Using a data-driven approach to support the design of energy-efficient buildings

With increasing interest in sustainable design, the issue of energy-efficiency in the building design process is receiving ever more attention from designers and researchers. Greater access to building performance analysis results has led designers and researchers to increasingly address energy-efficiency concerns. However, the huge amount of performance analysis data that may be generated during the design process cannot easily be handled by traditional data analysis methods. The goal of this research is to develop a data-driven approach for the integrated design process, in order to help to improve the accuracy of performance analyses and also reduce the time required to complete such design iterations. We propose our method to include five step: 1) Requirement identification; 2) Building modelling; 3) Workflow implementation; 4) Simulation and data mining; 5) Evaluation and refinement. A case study demonstrates our data-driven workflowOs ability to guide the design process with high precision. Our approach can also be extended and applied to discover useful patterns in the building design process.

[1]  Nam H. Kim,et al.  Options for Prognostics Methods: A review of data-driven and physics-based prognostics , 2013 .

[2]  Truong Nghiem,et al.  MLE+: a tool for integrated design and deployment of energy efficient building controls , 2012, SIGBED.

[3]  Matthias W. Seeger,et al.  Gaussian Processes For Machine Learning , 2004, Int. J. Neural Syst..

[4]  Prabir Barooah,et al.  Agent-based and graphical modelling of building occupancy , 2012 .

[5]  D. Mackay,et al.  Introduction to Gaussian processes , 1998 .

[6]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery: An Overview , 1996, Advances in Knowledge Discovery and Data Mining.

[7]  Michael Wetter,et al.  Co-simulation of building energy and control systems with the Building Controls Virtual Test Bed , 2011 .

[8]  Philip Haves,et al.  Systems Approach to Energy Efficient Building Operation: Case Studies and Lessons Learned in a University Campus , 2010 .

[9]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[10]  David M. Auslander,et al.  A Distributed Intelligent Automated Demand Response Building Management System , 2013 .

[11]  A. Krogh.  What are artificial neural networks? , 2008, Nature Biotechnology.

[12]  Hyunjoo Kim,et al.  Analysis of an energy efficient building design through data mining approach , 2011 .

[13]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[14]  Enrico Zio,et al.  A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system , 2010, Reliab. Eng. Syst. Saf..

[15]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.