A data-driven framework for energy-conscious design of building facade systems

Abstract A building facade system plays a critical role in building energy conservation since it has a large impact on the heat transfer between the outdoor and indoor environments. Considering complex interactions between building facade design parameters and building context is essential for evaluating the energy performance of building facade systems. Building energy simulations (BESs) can help designers to acquire necessary information about the energy performance of facade systems. However, many design firms do not have the capability of performance-based design due to the lack of trained personnel and technical resources, such as simulation tools and devices. Even with all the required resources, it is computationally expensive to analyze different facade design alternatives to compare their energy performance. The main objective of this paper is to develop a data-driven framework to extract hidden information and underlying structure from the thermal behavior of facade systems in a set of scenarios and provide recommendations for designers to select energy-efficient facade systems. In the proposed framework, clustering analysis was used to partition simulated data into different subsets with distinct patterns. Then, the association rule mining (ARM) technique was applied to each dataset to extract rules as recommendations for positive, negative, and neutral energy saving in favor of a selected facade panel. This framework provides simple recommendations on the energy performance of facade systems for different building types in different climate zones. The applicability of the proposed framework was tested on an innovative ultra-high-performance fiber-reinforced-concrete (UHP-FRC) facade panel. The extracted recommendations were validated using four different building models in different locations, which were not previously included in the building energy simulations. Results highlight the applicability of the proposed methodology in facilitating the energy performance analysis of different facade systems in different building contexts. This methodology can be used by designers as a decision support system to provide simple recommendations in the early stages of building envelope designs to obtain high-performance buildings.

[1]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[2]  Paul Strachan,et al.  Practical application of uncertainty analysis , 2001 .

[3]  Fu Xiao,et al.  Data mining in building automation system for improving building operational performance , 2014 .

[4]  M. F. Jentsch,et al.  Sensitivity And Uncertainty Analysis of Models for Determining Energy Consumption in the Residential Sector , 2015, Building Simulation Conference Proceedings.

[5]  Alberto Hernandez Neto,et al.  Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption , 2008 .

[6]  Balazs Feil,et al.  Cluster Analysis for Data Mining and System Identification , 2007 .

[7]  Benjamin C. M. Fung,et al.  Development of building energy saving advisory: A data mining approach , 2018, Energy and Buildings.

[8]  Mohammed Al-Maolegi,et al.  An Improved Apriori Algorithm for Association Rules , 2014, ArXiv.

[9]  Fu Xiao,et al.  Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review , 2018 .

[10]  David Infield,et al.  Thermal modelling of a building with an integrated ventilated PV façade , 2003 .

[11]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[12]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[13]  S. M. Shahandashti,et al.  Building energy performance analysis of ultra-high-performance fiber-reinforced concrete (UHP-FRC) façade systems , 2018, Energy and Buildings.

[14]  Paul Raftery,et al.  A review of methods to match building energy simulation models to measured data , 2014 .

[15]  Ali GhaffarianHoseini,et al.  A review on energy conscious designs of building façades in hot and humid climates: Lessons for (and from) Kuala Lumpur and Darwin , 2018 .

[16]  George S. Stavrakakis,et al.  On the Application of Clustering Techniques for Office Buildings' Energy and Thermal Comfort Classification , 2012, IEEE Transactions on Smart Grid.

[17]  Ratko Orlandic,et al.  Clustering high-dimensional data using an efficient and effective data space reduction , 2005, CIKM '05.

[18]  Hamidreza Zareipour,et al.  Data association mining for identifying lighting energy waste patterns in educational institutes , 2013 .

[19]  Fariborz Haghighat,et al.  Energy performance assessment of double-skin façade with thermal mass , 2010 .

[20]  Ali M. Malkawi,et al.  A new methodology for building energy performance benchmarking: An approach based on intelligent clustering algorithm , 2014 .

[21]  Godfried Augenbroe,et al.  Analysis of uncertainty in building design evaluations and its implications , 2002 .

[22]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[23]  Christina J. Hopfe,et al.  Uncertainty and sensitivity analysis for detailed design support , 2007 .

[24]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[25]  Athanasios Tsanas,et al.  Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools , 2012 .

[26]  Justin Zhijun Zhan,et al.  Data mining in distributed environment: a survey , 2017, WIREs Data Mining Knowl. Discov..

[27]  Moncef Krarti,et al.  Energy performance analysis of variable thermal resistance envelopes in residential buildings , 2015 .

[28]  Swarup Roy,et al.  Trends in quantitative association rule mining techniques , 2015, 2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS).

[29]  Ansaf Salleb-Aouissi,et al.  QuantMiner: A Genetic Algorithm for Mining Quantitative Association Rules , 2007, IJCAI.

[30]  Jian Zhang,et al.  ANSI/ASHRAE/IES Standard 90.1-2013 Determination of Energy Savings: Qualitative Analysis , 2014 .

[31]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[32]  Lin Lu,et al.  Investigation on the annual thermal performance of a photovoltaic wall mounted on a multi-layer façade , 2013 .

[33]  Nilanjan Banerjee,et al.  Using rule mining to understand appliance energy consumption patterns , 2014, 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[34]  Ansaf Salleb-Aouissi,et al.  QuantMiner for mining quantitative association rules , 2013, J. Mach. Learn. Res..

[35]  Ergo Pikas,et al.  Facade design principles for nearly zero energy buildings in a cold climate , 2013 .

[36]  Fang-Yie Leu,et al.  Data Preprocessing Quality Management Procedure for Improving Big Data Applications Efficiency and Practicality , 2016, BWCCA.