Data-driven modeling of building thermal dynamics: Methodology and state of the art

Abstract Data-driven approach is essential to the modeling of building thermal dynamics. It has been widely applied in building operation optimization, energy management, system performance evaluation, and so on. This present paper describes common concepts and fundamental theories of data-driven modeling within the context of building applications. Three types of data-driven models, namely transfer-function (TF) based, resistor-capacitor (RC) based, and artificial-intelligence (AI) based, are critically reviewed, including their formulations, interpretability of physical meanings, and prediction accuracy. Considerations on input and output variables are discussed. Conventional methods and techniques for model training and selection are also presented. Then, the three different models are illustrated through a case study of a real house using on-site monitored data. The case study suggests that the AI model generally outperforms the TF and RC models in predicting indoor temperatures while the RC model is the most appropriate for interpreting the physical behaviours of a building.

[1]  Clara Verhelst,et al.  Building models for model predictive control of office buildings with concrete core activation , 2013 .

[2]  Ting Wu,et al.  Electric load forecasting for large office building based on radial basis function neural network , 2014, 2014 IEEE PES General Meeting | Conference & Exposition.

[3]  Sirish L. Shah,et al.  MPC relevant identification––tuning the noise model , 2004 .

[4]  David J. C. MacKay,et al.  BAYESIAN NON-LINEAR MODELING FOR THE PREDICTION COMPETITION , 1996 .

[5]  José A. Candanedo,et al.  Model-based predictive control of an ice storage device in a building cooling system , 2013 .

[6]  Sirish L. Shah,et al.  Bias distribution in MPC relevant identification , 2002 .

[7]  Henrik Madsen,et al.  Estimation of continuous-time models for the heat dynamics of a building , 1995 .

[8]  Petru-Daniel Morosan,et al.  Building temperature regulation using a distributed model predictive control , 2010 .

[9]  Jie Chen,et al.  Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural n , 2011 .

[10]  Jesús M. Zamarreño,et al.  Prediction of hourly energy consumption in buildings based on a feedback artificial neural network , 2005 .

[11]  Nathan Mendes,et al.  Predictive controllers for thermal comfort optimization and energy savings , 2008 .

[12]  Xinhua Xu,et al.  A grey‐box model of next‐day building thermal load prediction for energy‐efficient control , 2008 .

[13]  J. M. Penman,et al.  Second order system identification in the thermal response of a working school , 1990 .

[14]  Luis M. Candanedo,et al.  Data driven prediction models of energy use of appliances in a low-energy house , 2017 .

[15]  Jiejin Cai,et al.  Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks , 2009 .

[16]  Gene F. Franklin,et al.  Digital control of dynamic systems , 1980 .

[17]  Andreas K. Athienitis,et al.  A Study of Temperature Set Point Strategies for Peak Power Reduction in Residential Buildings , 2015 .

[18]  Karl Johan Åström.  Maximum likelihood and prediction error methods , 1980, Autom..

[19]  Biswajit Basu,et al.  Residential HVAC fault detection using a system identification approach , 2017 .

[20]  Andreas K. Athienitis,et al.  Modeling approaches for the characterization of building thermal dynamics and model-based control: A case study , 2015 .

[21]  P. H. Baker,et al.  PASLINK and dynamic outdoor testing of building components , 2008 .

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

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

[24]  Jeff Haberl,et al.  The Great Energy Predictor Shootout II : Measuring Retriofit Savings-Overview and Discussion of Results , 1996 .

[25]  H. Madsen,et al.  Short-term heat load forecasting for single family houses , 2013 .

[26]  G. J. Rios-Moreno,et al.  Modelling temperature in intelligent buildings by means of autoregressive models , 2007 .

[27]  R. Sonderegger.  Diagnostic tests determining the thermal response of a house , 1977 .

[28]  Dirk Saelens,et al.  Quality of grey-box models and identified parameters as function of the accuracy of input and observation signals , 2014 .

[29]  David Coley,et al.  Second order system identification in the thermal response of real buildings. Paper II: Recursive formulation for on-line building energy management and control , 1992 .

[30]  Petre Stoica,et al.  Some properties of the output error method , 1982, Autom..

[31]  Andrea Gasparella,et al.  Building performance evaluation through a novel feature selection algorithm for automated arx model identification procedures , 2017 .

[32]  T. Y. Chen,et al.  Investigation of practical issues in building thermal parameter estimation , 2003 .

[33]  J. Braun,et al.  Model-based demand-limiting control of building thermal mass , 2008 .

[34]  P. V. D. Hof,et al.  Equation error versus output error methods , 1992 .

[35]  Yuxiang Chen,et al.  Modeling, design and thermal performance of a BIPV/T system thermally coupled with a ventilated concrete slab in a low energy solar house: Part 1, BIPV/T system and house energy concept , 2010 .

[36]  Soteris A. Kalogirou,et al.  Artificial neural networks for the prediction of the energy consumption of a passive solar building , 2000 .

[37]  Jin Woo Moon,et al.  Comparative study of artificial intelligence-based building thermal control methods – Application of fuzzy, adaptive neuro-fuzzy inference system, and artificial neural network , 2011 .

[38]  Nam-Ho Kyong,et al.  Subsystem level fault diagnosis of a building's air-handling unit using general regression neural networks , 2004 .

[39]  Jun Zhao,et al.  Identification of k-step-ahead prediction error model and MPC control , 2014 .

[40]  C. Park,et al.  Fault detection in an air-handling unit using residual and recursive parameter identification methods , 1996 .

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

[42]  M. J. Jiménez,et al.  Estimation of building component UA and gA from outdoor tests in warm and moderate weather conditions , 2008 .

[43]  T. McKelvey.  Identification of State-Space Models from Time and Frequency Data , 1995 .

[44]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[45]  Henrik Madsen,et al.  Characterization of heat dynamics of an arctic low-energy house with floor heating , 2014, Building Simulation.

[46]  James E. Braun,et al.  An Inverse Gray-Box Model for Transient Building Load Prediction , 2002 .

[47]  Pedro A. Gonzalez Lanza,et al.  A short-term temperature forecaster based on a state space neural network , 2002 .

[48]  Khaled Galal,et al.  Modeling, design and thermal performance of a BIPV/T system thermally coupled with a ventilated concrete slab in a low energy solar house: Part 2, ventilated concrete slab , 2010 .

[49]  Jinhua Wang,et al.  Online model-based fault detection and diagnosis strategy for VAV air handling units , 2012 .

[50]  Christian Ghiaus,et al.  Order selection of thermal models by frequency analysis of measurements for building energy efficiency estimation , 2015 .

[51]  John Mitchell,et al.  Transfer Functions for Efficient Calculation of Multidimensional Transient Heat Transfer , 1989 .

[52]  H. Madsen,et al.  Modelling the heat consumption in district heating systems using a grey-box approach , 2006 .

[53]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

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

[55]  Joshua N. Cooper,et al.  Parameter identification and model based predictive control of temperature inside a house , 2011 .

[56]  V. Geros,et al.  Modeling and predicting building's energy use with artificial neural networks: Methods and results , 2006 .

[57]  Melek Yalcintas,et al.  Energy-savings predictions for building-equipment retrofits , 2008 .

[58]  Bart De Moor,et al.  Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .

[59]  Jiejin Cai,et al.  Applying support vector machine to predict hourly cooling load in the building , 2009 .

[60]  Sten Bay Jørgensen,et al.  Parameter estimation in stochastic grey-box models , 2004, Autom..

[61]  Huibert Kwakernaak,et al.  Linear Optimal Control Systems , 1972 .

[62]  Christian Ghiaus,et al.  Optimal temperature control of intermittently heated buildings using Model Predictive Control: Part , 2012 .

[63]  Henrik Madsen,et al.  Identifying suitable models for the heat dynamics of buildings , 2011 .

[64]  T. Söderström,et al.  Least squares parameter estimation of continuous-time ARX models from discrete-time data , 1997, IEEE Trans. Autom. Control..

[65]  Frauke Oldewurtel,et al.  Use of partial least squares within the control relevant identification for buildings , 2013 .

[66]  Rogelio Lozano,et al.  Adaptive Control: Algorithms, Analysis and Applications , 2011 .

[67]  Si-Zhao Joe Qin,et al.  An overview of subspace identification , 2006, Comput. Chem. Eng..

[68]  Jianjun Hu,et al.  A state space modeling approach and subspace identification method for predictive control of multi-zone buildings with mixed mode cooling. , 2014 .

[69]  Nadia Ghrab-Morcos,et al.  Energy performance assessment of occupied buildings using model identification techniques , 2011 .

[70]  Lino Guzzella,et al.  EKF based self-adaptive thermal model for a passive house , 2014 .

[71]  J. F. Kreider.  Prediction Hourly Building Energy Use : The Great Energy Predictor Shootout - Overview and Discussion of Results , 1994 .

[72]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[73]  Karel J. Keesman,et al.  System Identification: An Introduction , 2011 .

[74]  Christian Ghiaus,et al.  Optimal temperature control of intermittently heated buildings using Model Predictive Control: Part I – Building modeling , 2012 .

[75]  Henrik Madsen,et al.  Identification of the main thermal characteristics of building components using MATLAB , 2008 .

[76]  José A. Candanedo,et al.  Control-oriented Modelling of Thermal Zones in a House: a Multi-level Approach , 2016 .

[77]  Rasmus Elbæk Hedegaard,et al.  Evaluation of Grey-Box Model Parameter Estimates Intended for Thermal Characterization of Buildings , 2017 .

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

[79]  Prabir Barooah,et al.  Issues in identification of control-oriented thermal models of zones in multi-zone buildings , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[80]  Tadj Oreszczyn,et al.  Inferring the thermal resistance and effective thermal mass of a wall using frequent temperature and heat flux measurements , 2014 .

[81]  Ryohei Yokoyama,et al.  Prediction of energy demands using neural network with model identification by global optimization , 2009 .

[82]  Steven B. Leeb,et al.  Control with building mass-Part II: Simulation , 2006 .

[83]  Diego Eckhard,et al.  Cost function shaping of the output error criterion , 2017, Autom..

[84]  Abbas Khosravi,et al.  A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings , 2015 .

[85]  Mohammad Yusri Hassan,et al.  Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review , 2017 .

[86]  Bo Fan,et al.  Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks , 2014 .

[87]  Zhiwei Lian,et al.  Hourly cooling load prediction by a combined forecasting model based on Analytic Hierarchy Process , 2004 .

[88]  Irena Koprinska,et al.  Forecasting electricity load with advanced wavelet neural networks , 2016, Neurocomputing.

[89]  Thierry Talbert,et al.  Black-box modeling of buildings thermal behavior using system identification , 2014 .

[90]  António E. Ruano,et al.  Prediction of building's temperature using neural networks models , 2006 .

[91]  T. Y. Chen,et al.  Application of adaptive predictive control to a floor heating system with a large thermal lag , 2002 .

[92]  Lennart Ljung,et al.  Some Classical and Some New Ideas for Identification of Linear Systems , 2013 .

[93]  Fan Zhang,et al.  A review on time series forecasting techniques for building energy consumption , 2017 .

[94]  Samuel Prívara,et al.  Building modeling: Selection of the most appropriate model for predictive control , 2012 .

[95]  Steven B. Leeb,et al.  Control with building mass-Part I: Thermal response model , 2006 .

[96]  Devendra K. Chaturvedi,et al.  Short term load forecast using fuzzy logic and wavelet transform integrated generalized neural network , 2015 .

[97]  G. Mustafaraj,et al.  Development of room temperature and relative humidity linear parametric models for an open office using BMS data , 2010 .

[98]  Moncef Krarti,et al.  Building Energy Use Prediction and System Identification Using Recurrent Neural Networks , 1995 .

[99]  Ari Rabl,et al.  Parameter estimation in buildings: Methods for dynamic analysis of measured energy use , 1988 .

[100]  Lukas Ferkl,et al.  Model predictive control of a building heating system: The first experience , 2011 .

[101]  T. Funabashi,et al.  Next day load curve forecasting using hybrid correction method , 2005, IEEE Transactions on Power Systems.

[102]  Jin Yang,et al.  On-line building energy prediction using adaptive artificial neural networks , 2005 .

[103]  Christian Inard,et al.  Grey-box identification of air-handling unit elements , 2007 .

[104]  Luis Pérez-Lombard,et al.  A review on buildings energy consumption information , 2008 .

[105]  Jianzhou Wang,et al.  Short-term load forecasting using a kernel-based support vector regression combination model , 2014 .

[106]  Grzegorz Dudek,et al.  Artificial Immune System for Short-Term Electric Load Forecasting , 2006, ICAISC.

[107]  Vladimir Havlena,et al.  Grey-box model identification - control relevant approach , 2010, ALCOSP.

[108]  Gregor P. Henze,et al.  Statistical Analysis of Neural Networks as Applied to Building Energy Prediction , 2004 .

[109]  António E. Ruano,et al.  Neural networks based predictive control for thermal comfort and energy savings in public buildings , 2012 .

[110]  Shengwei Wang,et al.  Simplified building model for transient thermal performance estimation using GA-based parameter identification , 2006 .

[111]  T. Agami Reddy,et al.  Applied Data Analysis and Modeling for Energy Engineers and Scientists , 2011 .

[112]  Manfred Morari,et al.  Importance of occupancy information for building climate control , 2013 .

[113]  Arthur L. Dexter,et al.  A simplified physical model for estimating the average air temperature in multi-zone heating systems , 2004 .

[114]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[115]  Frauke Oldewurtel,et al.  Experimental analysis of model predictive control for an energy efficient building heating system , 2011 .

[116]  Mohamed Mohandes,et al.  Support vector machines for short‐term electrical load forecasting , 2002 .

[117]  Kody M. Powell,et al.  Reduced-order residential home modeling for model predictive control , 2014 .

[118]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[119]  Paulo Carreira,et al.  Context-based thermodynamic modeling of buildings spaces , 2016 .

[120]  Sander M. Bohte,et al.  Editorial: Artificial Neural Networks as Models of Neural Information Processing , 2017, Front. Comput. Neurosci..

[121]  T. Y. Chen,et al.  Real-time predictive supervisory operation of building thermal systems with thermal mass , 2001 .