Approximation of simulation-derived visual comfort indicators in office spaces: a comparative study in machine learning

In performance-oriented architectural design, the use of advanced computational simulation tools may provide valuable insight during design. However, the use of such tools is often a bottleneck in the design process, given that computational requirements are usually high. This is a fact that mostly affects the early conceptual stage of design, where crucial decisions mainly occur, and available time is limited. In order to deal with this, decision-makers frequently resort to drawing conclusions from experience, and, as such, valuable insight that advanced computational methods have to offer is lost. This paper explores an alternative approach, which builds on machine-learning algorithms that inductively learn from simulation-derived data, yielding models that approximate to a good degree and are orders of magnitude faster. We focus on visual comfort of office spaces. This is a type of space that specifically requires visual comfort more than others. Three machine-learning methods are compared with respect to applicability in approximating daylight autonomy and daylight glare probability. The comparison focuses on accuracy and time cost of training and estimation. Results demonstrate that machine-learning-based approaches achieve a favourable trade-off between accuracy and computational cost, and provide a worthwhile alternative for performance evaluations during architectural conceptual design.

[1]  S.C-Y. Lu,et al.  Integration of Simulation, Learning and Optimization to Support Engineering Design , 1991 .

[2]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[3]  D. Basak,et al.  Support Vector Regression , 2008 .

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  Tuğçe Kazanasmaz,et al.  Artificial neural networks to predict daylight illuminance in office buildings , 2009 .

[6]  E. Rea.  The IESNA lighting handbook , 2013 .

[7]  Misha Denil,et al.  Narrowing the Gap: Random Forests In Theory and In Practice , 2013, ICML.

[8]  Dejan Mumovic,et al.  Applying artificial neural networks to estimate building energy use in the early stages of architectural design , 2012 .

[9]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[10]  Jens Christoffersen.  Evalglare. A new RADIANCE-based tool to evaluate glare in office spaces , 2004 .

[11]  Johannes Gehrke,et al.  Data Mining with Decision Trees , 2000, ICDE.

[12]  Christina Gloeckner,et al.  Modern Applied Statistics With S , 2003 .

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[15]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[16]  Sean Hanna,et al.  Inductive Aerodynamics , 2013 .

[17]  Betul Bektas Ekici,et al.  Prediction of building energy consumption by using artificial neural networks , 2009, Adv. Eng. Softw..

[18]  Claudia Perlich.  Learning Curves in Machine Learning , 2017, Encyclopedia of Machine Learning and Data Mining.

[19]  Shinichi Morishita,et al.  On Classification and Regression , 1998, Discovery Science.

[20]  Christoph F. Reinhart,et al.  Validation of dynamic RADIANCE-based daylight simulations for a test office with external blinds , 2001 .

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

[22]  Jens Christoffersen,et al.  Towards a new daylight glare rating , 2005 .

[23]  Luc Van Gool,et al.  Real Time Head Pose Estimation from Consumer Depth Cameras , 2011, DAGM-Symposium.

[24]  Jean-Louis Scartezzini,et al.  Daylight in Buildings - A source book on daylighting systems and components , 2000 .

[25]  Ashok K Gupta,et al.  Neural Networks as Decision Support System for Energy Efficient Building Design , 1997 .

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

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  Max Kuhn,et al.  caret: Classification and Regression Training , 2015 .

[29]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[30]  John Mardaljevic,et al.  Dynamic Daylight Performance Metrics for Sustainable Building Design , 2006 .

[31]  Gregory J. Ward,et al.  The RADIANCE lighting simulation and rendering system , 1994, SIGGRAPH.