Agent-based system identification for control-oriented building models

The paper presents a general agent-based system identification framework as potential solution for data-driven models of building systems that can be developed and integrated with improved efficiency, flexibility and scalability, compared to centralized approaches. The proposed method introduces building sub-system agents, which are optimized independently, by solving locally a maximum likelihood estimation problem. Several models are considered for the sub-system agents and a systematic selection approach is established considering the root mean square error, the parameter sensitivity to output trajectory and the parameter correlation. The final model is integrated from selected models for each agent. Two different approaches are developed for the integration; the negotiated-shared parameter model, which is a distributed method, and the free-shared parameter model based on a decentralized method. The results from a case-study for a high performance building indicate that the model prediction accuracy of the new approach is fairly good for implementation in predictive control.

[1]  Maizura Mokhtar,et al.  Intelligent multi-agent system for building heat distribution control with combined gas boilers and ground source heat pump , 2013 .

[2]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[3]  Nader Sadegh,et al.  Calibration of a lumped simulation model for double-skin façade systems , 2004 .

[4]  Ion Necoara,et al.  Parallel and distributed optimization methods for estimation and control in networks , 2011, 1302.3103.

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

[6]  Bruce H. Krogh,et al.  Parameter identifiability for multi-zone building models , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[7]  Lao Juan,et al.  Development and Validation of a Scale for Measuring Instructors' Attitudes toward Concept-Based or Reform-Oriented Teaching of Introductory Statistics in the Health and Behavioral Sciences , 2010, 1007.3219.

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

[9]  James E. Braun,et al.  An inverse hygrothermal model for multi-zone buildings , 2016 .

[10]  Thierry Talbert,et al.  A procedure for modeling buildings and their thermal zones using co-simulation and system identification , 2014 .

[11]  Francesco Borrelli,et al.  Stochastic Model Predictive Control for Building HVAC Systems: Complexity and Conservatism , 2015, IEEE Transactions on Control Systems Technology.

[12]  Dominique Marchio,et al.  Development and validation of a gray box model to predict thermal behavior of occupied office buildings , 2014 .

[13]  Lingfeng Wang,et al.  Multi-zone building energy management using intelligent control and optimization , 2013 .

[14]  James E. Braun,et al.  Multi-agent control for centralized air conditioning systems serving multi-zone buildings , 2015, 2015 American Control Conference (ACC).

[15]  Petru-Daniel Morosan,et al.  Distributed model predictive control based on Benders' decomposition applied to multisource multizone building temperature regulation , 2010, 49th IEEE Conference on Decision and Control (CDC).

[16]  Stephen Treado,et al.  Agent-Based Approaches for Adaptive Building HVAC System Control , 2010 .

[17]  George J. Pappas,et al.  Green scheduling for radiant systems in buildings , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[18]  Francesco Borrelli,et al.  Predictive Control for Energy Efficient Buildings with Thermal Storage: Modeling, Stimulation, and Experiments , 2012, IEEE Control Systems.

[19]  Rp Rick Kramer,et al.  Inverse modeling of simplified hygrothermal building models to predict and characterize indoor climates , 2013 .

[20]  Paul Davidsson,et al.  Distributed monitoring and control of office buildings by embedded agents , 2005, Inf. Sci..

[21]  Bruce H. Krogh,et al.  Distributed model predictive control , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

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

[23]  Jianjun Hu,et al.  System identification and model-predictive control of office buildings with integrated photovoltaic-thermal collectors, radiant floor heating and active thermal storage , 2015 .

[24]  Nicholas R. Jennings,et al.  Agent-based control systems: Why are they suited to engineering complex systems? , 2003 .

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

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

[27]  Francesco Borrelli,et al.  A distributed predictive control approach to building temperature regulation , 2011, Proceedings of the 2011 American Control Conference.

[28]  Marcelo Godoy Simões,et al.  Multi agent based energy management control for commercial buildings , 2011, 2011 IEEE Industry Applications Society Annual Meeting.

[29]  Josh Wall,et al.  Trial results from a model predictive control and optimisation system for commercial building HVAC , 2014 .

[30]  Eva Žáčeková,et al.  Towards the real-life implementation of MPC for an office building: Identification issues , 2014 .

[31]  Peter B. Luh,et al.  An integrated control of shading blinds, natural ventilation, and HVAC systems for energy saving and human comfort , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[32]  Mohammad H. Hosni,et al.  Plug Load Design Factors , 2011 .

[33]  Gregor P. Henze.  Model predictive control for buildings: a quantum leap? , 2013 .

[34]  Steven T. Bushby,et al.  Are intelligent agents the key to optimizing building HVAC system performance? , 2012, HVAC&R Research.

[35]  Peng Zhao,et al.  An Energy Management System for Building Structures Using a Multi-Agent Decision-Making Control Methodology , 2010, 2010 IEEE Industry Applications Society Annual Meeting.

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

[37]  Ardeshir Mahdavi,et al.  An agent-based simulation-assisted approach to bi-lateral building systems control , 2003 .

[38]  Manfred Morari,et al.  Use of model predictive control and weather forecasts for energy efficient building climate control , 2012 .

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

[40]  M. H. Hosni,et al.  Experimental results for heat gain and radiant/convective split from equipment in buildings , 1999 .

[41]  Jianjun Hu,et al.  A state-space modeling approach and multi-level optimization algorithm for predictive control of multi-zone buildings with mixed-mode cooling , 2014 .

[42]  Frauke Oldewurtel,et al.  Building modeling as a crucial part for building predictive control , 2013 .

[43]  Asuman Ozdaglar,et al.  Cooperative distributed multi-agent optimization , 2010, Convex Optimization in Signal Processing and Communications.

[44]  Philip Haves,et al.  Model predictive control for the operation of building cooling systems , 2010, Proceedings of the 2010 American Control Conference.

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

[46]  Lukas Ferkl,et al.  Optimization of Predicted Mean Vote index within Model Predictive Control framework: Computationally tractable solution , 2012 .

[47]  Stephen P. Boyd,et al.  Distributed estimation via dual decomposition , 2007, 2007 European Control Conference (ECC).

[48]  J. M. Maestre,et al.  Distributed Model Predictive Control: An Overview and Roadmap of Future Research Opportunities , 2014, IEEE Control Systems.

[49]  Johan Åkesson,et al.  Toolbox for development and validation of grey-box building models for forecasting and control , 2014 .

[50]  James E. Braun,et al.  Optimizing zone temperature setpoint excitation to minimize training data for data-driven dynamic building models , 2016, 2016 American Control Conference (ACC).

[51]  Gilles Guyon,et al.  Application of parameters space analysis tools for empirical model validation , 2004 .

[52]  James E. Braun,et al.  Distributed Model Predictive Control for Building HVAC systems: A Case Study , 2014 .

[53]  Sippe G. Douma,et al.  Identifiability: from qualitative analysis to model structure approximation , 2009 .

[54]  Lieve Helsen,et al.  Practical implementation and evaluation of model predictive control for an office building in Brussels , 2016 .

[55]  Francesco Borrelli,et al.  Model predictive control of radiant slab systems with evaporative cooling sources , 2015 .

[56]  Francesco Borrelli,et al.  Implementation of model predictive control for an HVAC system in a mid-size commercial building , 2014 .

[57]  Xiwang Li,et al.  Building energy consumption on-line forecasting using physics based system identification , 2014 .

[58]  Gilles Guyon,et al.  Theoretical basis for empirical model validation using parameters space analysis tools , 2003 .

[59]  George J. Pappas,et al.  Event-based Green scheduling of radiant systems in buildings , 2013, 2013 American Control Conference.

[60]  James E. Braun,et al.  Evaluating the Performance of Building Thermal Mass Control Strategies , 2001 .

[61]  Graham Clarke,et al.  A Multi-Agent Architecture For Intelligent Building Sensing and Control , 1999 .

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

[63]  Humberto E. Garcia,et al.  Sensor configuration selection for discrete-event systems under unreliable observations , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[64]  Jianmin Duan,et al.  Research of intelligent building control using an agent-based approach , 2008, 2008 6th IEEE International Conference on Industrial Informatics.

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

[66]  Dimitrios Gyalistras,et al.  Intermediate complexity model for Model Predictive Control of Integrated Room Automation , 2013 .