.png){kind=icon}
返回
Calibrating building simulation models using multi-source datasets and meta-learned Bayesian optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.enbuild.2022.112278.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reliable building simulation models are key to optimizing building performance and reducing green-house gas emissions. Informed decision making requires simulation models to be accurate, extrapolat-able, and interpretable, all of which require calibrating model simulations to ground truth. Complicated building dynamics and highly uncertain exogenous disturbances make the model calibra-tion process challenging and expensive; hence, a scalable and efficient calibration approach is needed to enable actual application. Current automatic calibration algorithms do not leverage data collected from multiple sources: for example, data obtained from previous calibration tasks on other buildings. In this paper, we employ probabilistic deep learning to meta-learn a distribution using multi-source data acquired during previous calibration. Subsequently, the meta-learned Bayesian optimizer accelerates cal-ibration of new, unseen tasks. The few-shot (that is, requiring few model simulations) nature of the pro-posed algorithm is demonstrated on a Modelica library of residential buildings validated by the United States Department of Energy (USDoE). The proposed algorithm is compared against classical Bayesian optimization-based calibration, and it is shown that ANP significantly sped up the calibration procedure: the optimal model parameters are identified with 40-60% less simulations compared to the baseline.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Meta learning
Deep learning
Parameter estimation
Probabilistic machine learning
Bayesian methods
Digital twin
期刊
IF:
7.1
论文数:
1.5W
被引数:
6.8W
机构
引用论文
Data-driven predictive control for unlocking building energy flexibility: A review数据驱动的预测控制，用于释放建筑能源灵活性: 综述
OAAI
OAAI分享收藏Bayesian calibration of building energy models with large datasets基于大数据集的建筑能耗模型的贝叶斯校准.png)
ENERGY AND BUILDINGSOAAI
ENERGY AND BUILDINGSIF7.1
OAAI分享收藏Occupancy data at different spatial resolutions: Building energy performance and model calibration不同空间分辨率下的occupancy数据：建筑能源性能与模型校准APPLIED ENERGY
APPLIED ENERGYIF11
PREAI
分享收藏A meta-model-based optimization approach for fast and reliable calibration of building energy modelsENERGY
ENERGYIF9.4
PREAI
分享收藏Evaluation of Autotune calibration against manual calibration of building energy models对建筑能量模型的手动校准进行自动调谐校准的评估APPLIED ENERGYOAAI
APPLIED ENERGYIF11
OAAI分享收藏Guidelines for the Bayesian calibration of building energy models建筑能源模型的贝叶斯校准指南ENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
分享收藏
查看更多内容