A methodology for calibration of building energy models at district scale using clustering and surrogate techniques

Abstract Prediction of building energy use, when performed at urban scale, is influenced by the choice of modelling approach, as well as the quality of available data. In the case of data scarcity, one of the main limitations of current urban scale building energy simulation models, is the use of deterministic approaches to specify modelling inputs for entire classes of buildings. This modelling approach is characterised by three major shortcomings: first, data uncertainties are not comprehensively considered; second, a rigorous method of identification of groups of buildings to be populated by similar modelling parameters is not specified; and third, strategies to calibrate the developed energy models are missing. Considering these challenges, the current paper presents a non-deterministic calibration method for groups of buildings. The methodology utilises four techniques: (i) the use of clustering to identify building groups and associated representative buildings within the urban context; (ii) the application of an automatic building energy modelling approach to simulate buildings within these groups; (iii) the application of data-driven models, used as emulators of the dynamic simulation engine, in a computationally efficient manner; and (iv) the exploitation of a non-deterministic Bayesian calibration framework to identify sets of representative parameters for the building clusters. Datasets, based on 2646 buildings from the city of Geneva, Switzerland, are used as a case study. Validation with measured data, shows that energy consumption and energy intensity predictions when considered at an aggregated scale, are within +/– 5%. On an individual building basis, the validation error is within +/– 20% for approximately 70% of the buildings.

[1]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[2]  N. Nagelkerke,et al.  A note on a general definition of the coefficient of determination , 1991 .

[3]  Moncef Krarti,et al.  Bayesian-Emulator based parameter identification for calibrating energy models for existing buildings , 2016 .

[4]  Thomas H. Kolbe,et al.  Simulation-Based Total Energy Demand Estimation of Buildings using Semantic 3D City Models , 2014, Int. J. 3 D Inf. Model..

[5]  P. A. Mirzaei,et al.  Recent challenges in modeling of urban heat island , 2015 .

[6]  Burcin Becerik-Gerber,et al.  A model calibration framework for simultaneous multi-level building energy simulation , 2015 .

[7]  Gang Liu,et al.  Modeling of district load forecasting for distributed energy system , 2017 .

[8]  Joseph Andrew Clarke,et al.  Using simulation to formulate domestic sector upgrading strategies for Scotland , 2004 .

[9]  Tao Lu,et al.  Modeling and forecasting energy consumption for heterogeneous buildings using a physical -statistical approach , 2015 .

[10]  Liping Wang,et al.  Improving High-Dimensional Physics Models Through Bayesian Calibration With Uncertain Data , 2012 .

[11]  Wei Tian,et al.  Uncertainty and sensitivity analysis of building performance using probabilistic climate projections: A UK case study , 2011 .

[12]  Arno Schlueter,et al.  Integrated model for characterization of spatiotemporal building energy consumption patterns in neighborhoods and city districts , 2015 .

[13]  Rishee K. Jain,et al.  Data-driven Urban Energy Simulation (DUE-S): A framework for integrating engineering simulation and machine learning methods in a multi-scale urban energy modeling workflow , 2018, Applied Energy.

[14]  Chirag Deb,et al.  Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks , 2016 .

[15]  Jason Brown,et al.  Assessment of linear emulators in lightweight Bayesian calibration of dynamic building energy models for parameter estimation and performance prediction , 2016 .

[16]  J. Beall,et al.  Cities and Development , 2009 .

[17]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[18]  Sylvia Richardson,et al.  Markov Chain Monte Carlo in Practice , 1997 .

[19]  George K. Karagiannidis,et al.  Big Data Analytics for Dynamic Energy Management in Smart Grids , 2015, Big Data Res..

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

[21]  Christoph F. Reinhart,et al.  Modeling Boston: A workflow for the efficient generation and maintenance of urban building energy models from existing geospatial datasets , 2016 .

[22]  Parham A. Mirzaei,et al.  A review and critique of UK housing stock energy models, modelling approaches and data sources , 2017 .

[23]  Massimiliano Manfren,et al.  Paradigm shift in urban energy systems through distributed generation: Methods and models , 2011 .

[24]  F. Stazi,et al.  Estimating energy savings for the residential building stock of an entire city: A GIS-based statistical downscaling approach applied to Rotterdam , 2014 .

[25]  Ardeshir Mahdavi,et al.  Reductive bottom-up urban energy computing supported by multivariate cluster analysis , 2017 .

[26]  Paola Caputo,et al.  A Methodology for Defining Electricity Demand in Energy Simulations Referred to the Italian Context , 2013 .

[27]  R. Kitchin,et al.  The real-time city? Big data and smart urbanism , 2013, GeoJournal.

[28]  Maria Kolokotroni,et al.  A GIS-based bottom-up space heating demand model of the London domestic stock , 2009 .

[29]  Ruth Kerrigan,et al.  Identification of representative buildings and building groups in urban datasets using a novel pre-processing, classification, clustering and predictive modelling approach , 2018, Building and Environment.

[30]  Andrea Zanella,et al.  Internet of Things for Smart Cities , 2014, IEEE Internet of Things Journal.

[31]  Mary Ann Piette,et al.  A pattern-based automated approach to building energy model calibration , 2016 .

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

[33]  Y. Shimoda,et al.  DEVELOPMENT OF RESIDENTIAL ENERGY END-USE SIMULATION MODEL AT CITY SCALE , 2003 .

[34]  M. Perino,et al.  Energy demand profile generation with detailed time resolution at an urban district scale: A reference building approach and case study , 2017 .

[35]  Benjamin M. Jones,et al.  An open-source simulation platform to support the formulation of housing stock decarbonisation strategies , 2018 .

[36]  René M.J. Benders,et al.  New approaches for household energy conservation--In search of personal household energy budgets and energy reduction options , 2006 .

[37]  Michael Batty,et al.  Big data, smart cities and city planning , 2013, Dialogues in human geography.

[38]  Volker Coors,et al.  Combining GIS-based statistical and engineering urban heat consumption models: Towards a new framework for multi-scale policy support , 2015 .

[39]  Yeonsook Heo,et al.  Quantitative risk management for energy retrofit projects , 2013 .

[40]  B. De Moor,et al.  Short-term load forecasting, profile identification, and customer segmentation: a methodology based on periodic time series , 2005, IEEE Transactions on Power Systems.

[41]  Enrique Kremers,et al.  Towards a 3d Spatial Urban Energy Modelling Approach , 2013 .

[42]  François Maréchal,et al.  City Energy Analyst (CEA): Integrated framework for analysis and optimization of building energy systems in neighborhoods and city districts , 2016 .

[43]  David C. Miller,et al.  Bayesian calibration of thermodynamic models for the uptake of CO2 in supported amine sorbents using ab initio priors. , 2013, Physical chemistry chemical physics : PCCP.

[44]  Young-Jin Kim,et al.  Stepwise deterministic and stochastic calibration of an energy simulation model for an existing building , 2016 .

[45]  Zheng O'Neill,et al.  Evaluation of “Autotune” calibration against manual calibration of building energy models , 2016 .

[46]  Dave Higdon,et al.  Combining Field Data and Computer Simulations for Calibration and Prediction , 2005, SIAM J. Sci. Comput..

[47]  Joaquim Melendez,et al.  Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes , 2016 .

[48]  Jan Hensen,et al.  Integrated building performance simulation: Progress, prospects and requirements , 2015 .

[49]  Awais Ahmad,et al.  Urban planning and building smart cities based on the Internet of Things using Big Data analytics , 2016, Comput. Networks.

[50]  Jan Carmeliet,et al.  Towards an energy sustainable community: An energy system analysis for a village in Switzerland , 2014 .

[51]  Rita Streblow,et al.  Demand side management for city districts , 2015 .

[52]  R. Britter,et al.  A resistance-capacitance network model for the analysis of the interactions between the energy performance of buildings and the urban climate , 2012 .

[53]  Miriam A. M. Capretz,et al.  An ensemble learning framework for anomaly detection in building energy consumption , 2017 .

[54]  Nor Badrul Anuar,et al.  The role of big data in smart city , 2016, Int. J. Inf. Manag..

[55]  J. Tinsley Oden,et al.  Bayesian calibration, validation, and uncertainty quantification of diffuse interface models of tumor growth , 2012, Journal of Mathematical Biology.

[56]  Laura Uusitalo,et al.  An overview of methods to evaluate uncertainty of deterministic models in decision support , 2015, Environ. Model. Softw..

[57]  Pierluigi Mancarella,et al.  Distributed multi-generation: A comprehensive view , 2009 .

[58]  Enedir Ghisi,et al.  Method for obtaining reference buildings , 2016 .

[59]  Shen Wei,et al.  Identifying informative energy data in Bayesian calibration of building energy models , 2016 .

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

[61]  Am Aidan Melia,et al.  INDICATE: TOWARDS THE DEVELOPMENT OF A VIRTUAL CITY MODEL, USING A 3D MODEL OF DUNDALK CITY , 2015 .

[62]  Ruchi Choudhary,et al.  Decision making under uncertainty in the retrofit analysis of the UK housing stock: Implications for the Green Deal , 2013 .

[63]  Michael D. Lepech,et al.  Modeling and optimization of building mix and energy supply technology for urban districts , 2015 .

[64]  Nils Brandt,et al.  Smart Urban Metabolism: Towards a Real-Time Understanding of the Energy and Material Flows of a City and Its Citizens , 2015 .

[65]  Shanlin Yang,et al.  Understanding household energy consumption behavior: The contribution of energy big data analytics , 2016 .

[66]  Diane J. Graziano,et al.  Evaluation of calibration efficacy under different levels of uncertainty , 2013, Building Simulation Conference Proceedings.

[67]  Wei Tian,et al.  A probabilistic energy model for non-domestic building sectors applied to analysis of school buildings in greater London , 2012 .

[68]  Ertuğrul Çam,et al.  Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines , 2015 .

[69]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[70]  Darren Robinson,et al.  Energy performance of decentralized solar thermal feed-in to district heating networks , 2017 .

[71]  Rita Streblow,et al.  Low order thermal network models for dynamic simulations of buildings on city district scale , 2014 .

[72]  Jérôme Henri Kämpf,et al.  Urban Area Energy Flow Microsimulation for Planning Support: a Calibration and Verification Study , 2013 .

[73]  Dejan Mumovic,et al.  Uncertainty and modeling energy consumption: Sensitivity analysis for a city-scale domestic energy model , 2013 .

[74]  S. Kitazawa,et al.  Bayesian Calibration of Simultaneity in Audiovisual Temporal Order Judgments , 2012, PloS one.

[75]  Shem Heiple,et al.  Using building energy simulation and geospatial modeling techniques to determine high resolution building sector energy consumption profiles , 2008 .

[76]  Fan Zhang,et al.  Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique , 2016 .

[77]  Victor Nian,et al.  A simultaneous calibration and parameter ranking method for building energy models , 2017 .

[78]  Joseph Virgone,et al.  Development and validation of regression models to predict monthly heating demand for residential buildings , 2008 .

[79]  Manuel Alcázar-Ortega,et al.  New artificial neural network prediction method for electrical consumption forecasting based on buil , 2011 .

[80]  Enrico Benetto,et al.  Global sensitivity analysis as a support for the generation of simplified building stock energy models , 2017 .

[81]  Andrew Kusiak,et al.  A data-driven approach for steam load prediction in buildings , 2010 .

[82]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

[83]  Christoph F. Reinhart,et al.  Urban building energy modeling – A review of a nascent field , 2015 .

[84]  Wei-Peng Chen,et al.  Neural network model ensembles for building-level electricity load forecasts , 2014 .

[85]  Mohammad Yusri Hassan,et al.  A review on applications of ANN and SVM for building electrical energy consumption forecasting , 2014 .

[86]  Enrico Fabrizio,et al.  Reference buildings for cost optimal analysis: Method of definition and application , 2013 .

[87]  Taehoon Hong,et al.  Automatic calibration model of a building energy simulation using optimization algorithm , 2017 .

[88]  Enrico Fabrizio,et al.  Methodologies and Advancements in the Calibration of Building Energy Models , 2015 .

[89]  Yeonsook Heo,et al.  Sensitivity analysis methods for building energy models: Comparing computational costs and extractable information , 2016 .

[90]  Scott J. Moura,et al.  Gated ensemble learning method for demand-side electricity load forecasting , 2015 .

[91]  Sang Hoon Lee,et al.  Reconstructing building stock to replicate energy consumption data , 2016 .

[92]  Yoshiyuki Shimoda,et al.  District-scale simulation for multi-purpose evaluation of urban energy systems , 2010 .

[93]  Fabio Polonara,et al.  Domestic demand-side management (DSM): Role of heat pumps and thermal energy storage (TES) systems , 2013 .

[94]  C. Robert.  The Metropolis–Hastings Algorithm , 2015, 1504.01896.

[95]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[96]  Rui Neves-Silva,et al.  Stochastic models for building energy prediction based on occupant behavior assessment , 2012 .

[97]  Weiming Shen,et al.  Inverse blackbox modeling of the heating and cooling load in office buildings , 2017 .

[98]  Tony Roskilly,et al.  This Work Is Licensed under a Creative Commons Attribution 4.0 International License Royapoor M, Roskilly T. Building Model Calibration Using Energy and Environmental Data. Energy and Buildings Building Model Calibration Using Energy and Environmental Data Keywords: Model Calibration Measured Energy , 2022 .

[99]  Edward Morofsky,et al.  A screening methodology for implementing cost effective energy retrofit measures in Canadian office , 2011 .

[100]  B. Polly,et al.  Evaluation of Automated Model Calibration Techniques for Residential Building Energy Simulation , 2013 .

[101]  Zhiqiang John Zhai,et al.  Review on stochastic modeling methods for building stock energy prediction , 2017 .

[102]  F. Creutzig,et al.  Global typology of urban energy use and potentials for an urbanization mitigation wedge , 2015, Proceedings of the National Academy of Sciences.

[103]  Jack Chin Pang Cheng,et al.  Identifying the influential features on the regional energy use intensity of residential buildings based on Random Forests , 2016 .

[104]  Milind R. Naphade,et al.  The dubuque electricity portal: evaluation of a city-scale residential electricity consumption feedback system , 2013, CHI.

[105]  David J. Spiegelhalter,et al.  Handling uncertainty in housing stock models , 2012 .

[106]  Andreas Ziegler,et al.  ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R , 2015, 1508.04409.

[107]  Shanlin Yang,et al.  Big data driven smart energy management: From big data to big insights , 2016 .

[108]  Andrea Costa,et al.  Model calibration for building energy efficiency simulation , 2014 .

[109]  Y. Shimoda,et al.  Residential end-use energy simulation at city scale , 2004 .

[110]  Daniel Macumber,et al.  Demonstration of reduced-order urban scale building energy models , 2017 .

[111]  Juan D. Gomez,et al.  Predicting future monthly residential energy consumption using building characteristics and climate data: A statistical learning approach , 2016 .

[112]  Raffaele de Amicis,et al.  Large-Scale Assessment and Visualization of the Energy Performance of Buildings with Ecomaps - Project SUNSHINE: Smart Urban Services for Higher Energy Efficiency , 2014, DATA.

[113]  Vijay Modi,et al.  Spatial distribution of urban building energy consumption by end use , 2012 .

[114]  Junjing Yang,et al.  Bayesian calibration of building energy models with large datasets , 2017 .

[115]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[116]  Jlm Jan Hensen,et al.  Uncertainty analysis in building performance simulation for design support , 2011 .

[117]  Yusuke Kishita,et al.  Determinant factors of residential consumption and perception of energy conservation: Time-series analysis by large-scale questionnaire in Suita, Japan , 2015 .

[118]  Christoph F. Reinhart,et al.  Validation of a Bayesian-based method for defining residential archetypes in urban building energy models , 2017 .

[119]  Steffen Petersen,et al.  Choosing the appropriate sensitivity analysis method for building energy model-based investigations , 2016 .

[120]  A. Mäkelä,et al.  Bayesian calibration, comparison and averaging of six forest models, using data from Scots pine stands across Europe , 2013 .

[121]  Juha Jokisalo,et al.  Calculation method and tool for assessing energy consumption in the building stock , 2014 .

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

[123]  Ruth Kerrigan,et al.  A Data-Driven Modelling Approach for Large Scale Demand Profiling of Residential Buildings , 2017 .

[124]  Rubén Béjar,et al.  Multi-scale urban data models for early-stage suitability assessment of energy conservation measures in historic urban areas , 2018 .