Improved calibration of building models using approximate Bayesian calibration and neural networks

被引:12
作者
Cant, Kevin [1 ]
Evins, Ralph [1 ]
机构
[1] Univ Victoria, Dept Civil Engn, Energy & Cities Grp, 3800 Finnerty Rd, Victoria, BC V8P 5C2, Canada
关键词
Building energy simulation; approximate Bayesian calibration; existing building retrofit; ENERGY MODELS; INFERENCE; UNCERTAINTY;
D O I
10.1080/19401493.2022.2137236
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Deep energy retrofits of buildings are crucial to meeting climate targets and depend on calibrated energy models for investor confidence. Bayesian inference can improve the rigour in standard practice and improve confidence in calibrated energy models. Approximate Bayesian computation (ABC) methods using neural networks present an opportunity to calibrate energy models while inherently accounting for parameter uncertainty, and face less computational burden than the current standard process for Bayesian calibration. A case study for a large, complex building is presented to demonstrate the applicability of ABC and parameter sensitivity screening is found to result in over-confidence in the resulting inference by between 14% and 85%. Finally, the presentation of posterior distributions as independent distributions may be misleading, which can misattribute the true likelihood of parameters.
引用
收藏
页码:291 / 307
页数:17
相关论文
共 53 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
Ardehali M.M., 2003, ASHRAE Trans., V109, P111
[3]   Building energy model calibration using automated optimization-based algorithm [J].
Asadi, Somayeh ;
Mostavi, Ehsan ;
Boussaa, Djamel ;
Indaganti, Madhavi .
ENERGY AND BUILDINGS, 2019, 198 :106-114
[4]  
ASHRAE, 2018, 211 ASHRAE
[5]  
Cant K., 2021, Optimizing VAV Terminal Box Minimum Positions using Dynamic Simulations to Improve Energy and Ventilation Performance, DOI DOI 10.26868/25222708.2021.30439
[6]   Evaluation of "Autotune" calibration against manual calibration of building energy models [J].
Chaudhary, Gaurav ;
New, Joshua ;
Sanyal, Jibonananda ;
Im, Piljae ;
O'Neill, Zheng ;
Garg, Vishal .
APPLIED ENERGY, 2016, 182 :115-134
[7]   Calibrating building energy simulation models: A review of the basics to guide future work [J].
Chong, Adrian ;
Gu, Yaonan ;
Jia, Hongyuan .
ENERGY AND BUILDINGS, 2021, 253
[8]   Guidelines for the Bayesian calibration of building energy models [J].
Chong, Adrian ;
Menberg, Kathrin .
ENERGY AND BUILDINGS, 2018, 174 :527-547
[9]   A review of methods to match building energy simulation models to measured data [J].
Coakley, Daniel ;
Raftery, Paul ;
Keane, Marcus .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2014, 37 :123-141
[10]   EnergyPlus: creating a new-generation building energy simulation program [J].
Crawley, DB ;
Lawrie, LK ;
Winkelmann, FC ;
Buhl, WF ;
Huang, YJ ;
Pedersen, CO ;
Strand, RK ;
Liesen, RJ ;
Fisher, DE ;
Witte, MJ ;
Glazer, J .
ENERGY AND BUILDINGS, 2001, 33 (04) :319-331