Comparative Analysis of White-, Gray- and Black-box Models for Thermal Simulation of Indoor Environment: Teaching Building Case Study

This study presents a performance comparison between selected white-, grayand black-box models for indoor temperature prediction in a university building located at the SDU Campus Odense. It was found that the blackbox models outperform the grayand white-box models in most cases, but the accuracy highly depends on the training data in terms of both period and modes of heat transfer covered by the data set. The average mean absolute error for the best performing black-box model was 0.4◦C as compared to 1.0◦C and 0.7◦C for the gray-box and whitebox models, respectively. In terms of accuracy, the graybox models are a reasonable alternative for black-box only in case of short-term predictions, in which their error decreases to around 0.3-0.8◦C , depending on the room.

[1]  Mikkel Baun Kjærgaard,et al.  PLCount: A Probabilistic Fusion Algorithm for Accurately Estimating Occupancy from 3D Camera Counts , 2016, BuildSys@SenSys.

[2]  Mikkel Baun Kjærgaard,et al.  A World Class Energy Efficient University Building by Danish 2020 Standards , 2017 .

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

[4]  Mikkel Baun Kjærgaard,et al.  A Building Model Framework for a Genetic Algorithm Multi-objective Model Predictive Control , 2016 .

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

[6]  Farrokh Janabi-Sharifi,et al.  Supervisory model predictive controller (MPC) for residential HVAC systems: Implementation and experimentation on archetype sustainable house in Toronto , 2017 .

[7]  Gabriele Comodi,et al.  The role of data sample size and dimensionality in neural network based forecasting of building heating related variables , 2016 .

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

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

[10]  Tanveer Ahmad,et al.  Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches , 2018 .

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

[12]  Bo Nørregaard Jørgensen,et al.  A dynamic energy performance-driven approach for assessment of buildings energy Renovation—Danish case studies , 2018 .

[13]  Ian Beausoleil-Morrison,et al.  Control-oriented inverse modeling of the thermal characteristics in an office , 2016 .

[14]  Farrokh Janabi-Sharifi,et al.  Black-box modeling of residential HVAC system and comparison of gray-box and black-box modeling methods , 2015 .

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

[16]  Geert Van Ham,et al.  Model selection for continuous commissioning of HVAC-systems in office buildings: a review Renewable & Sustainable Energy Reviews , 2017 .

[17]  Mikkel Baun Kjærgaard,et al.  Performance comparison of occupancy count estimation and prediction with common versus dedicated sensors for building model predictive control , 2017 .

[18]  Yacine Rezgui,et al.  A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control , 2018 .

[19]  Tianzhen Hong,et al.  Modeling of HVAC operational faults in building performance simulation , 2017 .

[20]  O. M. Brastein,et al.  Parameter estimation for grey-box models of building thermal behaviour , 2018, Energy and Buildings.