Building performance evaluation through a novel feature selection algorithm for automated arx model identification procedures

Abstract ARX models are an effective instrument to evaluate continuous building performance from insufficient monitoring data. However, selecting the right model features is NP-hard. The problem of finding a minimal subset of informative inputs has been studied extensively in various fields but automatic, fast, and reliable procedures for finding optimal models for building performance evaluation are still missing. We propose a novel feature selection algorithm named Greedy Correlation Screening (GCS), which identifies a possible solution at a time by greedily maximizing the correlation between inputs and output and minimizing cross-correlations between inputs. These two objectives are competing, thus leading to best tradeoffs. Among these, the best model is automatically selected by applying filters and quality criteria such as the adjusted coefficient of correlation and non-correlation of residuals. The performance of the proposed heuristic method is compared to two of the best algorithms used in the field, such as GRASP for feature selection and NSGA-II (Non-dominated Sorting Genetic Algorithm). The application on a real case study demonstrates that the proposed method solves the problem of feature selection in building performance estimation efficiently and reliably. Moreover, the model creation is automatic, making it ideal for integration into a Building Management System (BMS) in order to detect faults and perform short-term predictive control.

[1]  Gerardo Maria Mauro,et al.  Artificial neural networks to predict energy performance and retrofit scenarios for any member of a building category: A novel approach , 2017 .

[2]  D. N. Kashid,et al.  Subset selection in multiple linear regression in the presence of outlier and multicollinearity , 2014 .

[3]  A. Atkinson.  Subset Selection in Regression , 1992 .

[4]  Andrea Costa,et al.  Building operation and energy performance: Monitoring, analysis and optimisation toolkit , 2013 .

[5]  Junbin Gao,et al.  Group subset selection for linear regression , 2014, Comput. Stat. Data Anal..

[6]  M. A. Fayazbakhsh,et al.  Gray-box model for energy-efficient selection of set point hysteresis in heating, ventilation, air conditioning, and refrigeration controllers , 2015 .

[7]  Rita Streblow,et al.  Development and validation of grey-box models for forecasting the thermal response of occupied buildings , 2016 .

[8]  M. A. Rafe Biswas,et al.  Regression analysis for prediction of residential energy consumption , 2015 .

[9]  David A. Belsley,et al.  Regression Analysis and its Application: A Data-Oriented Approach.@@@Applied Linear Regression.@@@Regression Diagnostics: Identifying Influential Data and Sources of Collinearity , 1981 .

[10]  Timothy M. Chan.  Optimal output-sensitive convex hull algorithms in two and three dimensions , 1996, Discret. Comput. Geom..

[11]  Paul Fazio,et al.  Development of an energy rating system for existing houses , 1999 .

[12]  Joseph C. Lam,et al.  Multiple regression models for energy use in air-conditioned office buildings in different climates , 2010 .

[13]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[14]  Chiara Aghemo,et al.  Building automation and control systems: A case study to evaluate the energy and environmental performances of a lighting control system in offices , 2014 .

[15]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognit. Lett..

[16]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[17]  Gregor P. Henze,et al.  A model predictive control optimization environment for real-time commercial building application , 2013 .

[18]  H. Hasan Örkcü.  Subset selection in multiple linear regression models: A hybrid of genetic and simulated annealing algorithms , 2013, Appl. Math. Comput..

[19]  Silvia Casado Yusta,et al.  Different metaheuristic strategies to solve the feature selection problem , 2009, Pattern Recognit. Lett..

[20]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[21]  Baozong Yuan,et al.  A more efficient branch and bound algorithm for feature selection , 1993, Pattern Recognit..

[22]  Dirk Saelens,et al.  Impact of the Heat Emission System on the Identification of Grey-box Models for Residential Buildings , 2015 .

[23]  David E. Claridge,et al.  Development and testing of an Automated Building Commissioning Analysis Tool (ABCAT) , 2012 .

[24]  Stefan Van Aelst,et al.  Building a robust linear model with forward selection and stepwise procedures , 2007, Comput. Stat. Data Anal..

[25]  Pedro J. Mago,et al.  Building hourly thermal load prediction using an indexed ARX model , 2012 .

[26]  Josef Kittler,et al.  An analysis of the Max-Min approach to feature selection and ordering , 1993, Pattern Recognit. Lett..

[27]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Feature Subset Selection , 1977, IEEE Transactions on Computers.

[28]  D. N. Kashid,et al.  A MORE GENERAL CRITERION FOR SUBSET SELECTION IN MULTIPLE LINEAR REGRESSION , 2002 .

[29]  Vittorio Cesarotti,et al.  Energy consumption control automation using Artificial Neural Networks and adaptive algorithms: Proposal of a new methodology and case study , 2016 .

[30]  Magali Bodart,et al.  Lighting energy savings in offices using different control systems and their real consumption , 2008 .

[31]  Celso C. Ribeiro,et al.  Greedy Randomized Adaptive Search Procedures , 2003, Handbook of Metaheuristics.

[32]  Mauricio G. C. Resende,et al.  Greedy Randomized Adaptive Search Procedures , 1995, J. Glob. Optim..

[33]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[34]  Jin Wen,et al.  Review of building energy modeling for control and operation , 2014 .

[35]  Gaetano Zizzo,et al.  Impact of building automation control systems and technical building management systems on the energy performance class of residential buildings: An Italian case study , 2014 .

[36]  Jose Miguel Puerta,et al.  A GRASP algorithm for fast hybrid (filter-wrapper) feature subset selection in high-dimensional datasets , 2011, Pattern Recognit. Lett..

[37]  David E. Claridge,et al.  Continuous Commissioningsm of building energy systems , 2003 .

[38]  Sebastian Herkel,et al.  Black-box models for fault detection and performance monitoring of buildings , 2010 .

[39]  Ignacio Zabalza Bribián,et al.  Information and Communications Technologies (ICTs) for energy efficiency in buildings: Review and analysis of results from EU pilot projects , 2016 .

[40]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[41]  Farrokh Janabi-Sharifi,et al.  Gray-box modeling and validation of residential HVAC system for control system design , 2015 .

[42]  M. J. Jiménez,et al.  Application of multi-output ARX models for estimation of the U and g values of building components in outdoor testing , 2005 .

[43]  Rossano Scoccia,et al.  A Continuous Commissioning Analysis and its Application to a New Installed Solar Driven DEC System Coupled with Heat Pump , 2015 .

[44]  Dennis L. Loveday,et al.  Practical stochastic multivariable identification for buildings , 1995 .

[45]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[46]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[47]  Xiufeng Pang,et al.  Monitoring-based HVAC commissioning of an existing office building for energy efficiency , 2013 .

[48]  U. Berardi.  Building Energy Consumption in US, EU, and BRIC Countries☆ , 2015 .

[49]  Shideh Shams Amiri,et al.  Using multiple regression analysis to develop energy consumption indicators for commercial buildings in the U.S. , 2015 .

[50]  Riza Demirer,et al.  Subset selection in multiple linear regression: a new mathematical programming approach , 2005, Comput. Ind. Eng..

[51]  Wil L. Kling,et al.  Pseudo Dynamic Transitional Modeling of Building Heating Energy Demand Using Artificial Neural Network , 2014, ArXiv.

[52]  C. Ghiaus.  Experimental estimation of building energy performance by robust regression , 2006 .

[53]  Bing Dong,et al.  A holistic utility bill analysis method for baselining whole commercial building energy consumption in Singapore , 2005 .

[54]  Pedro Larrañaga,et al.  Feature subset selection by genetic algorithms and estimation of distribution algorithms - A case study in the survival of cirrhotic patients treated with TIPS , 2001, Artif. Intell. Medicine.