Bayesian calibration of building energy models with large datasets

Chong, Adrian; Lam, Khee Poh; Pozzi, Matteo; Yang, Junjing

doi:10.1016/j.enbuild.2017.08.069

Cited by 97 publications

(25 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model calibration is commonly defined as an inverse approximation because of the need to tune necessary inputs to reconcile the outputs by a simulation program as closely as possible to the measured energy data (Yang and Becerik-Gerber, 2015 (O'Neill and Eisenhower, 2013;Yang et al, 2016), pattern-based methods (Sun et al, 2016), and Bayesian calibration methods (Chong et al, 2017;Lim and Zhai, 2017). Although those automated calibration methods can be directly applied to calibrate UBEM, the number of simulations required to calibrate the UBEM is proportional to the number of buildings.…”

Section: Question 7: How Can Results From Ubem Be Calibrated?mentioning

confidence: 99%

Ten questions on urban building energy modeling

Hong

Chen

Luo

et al. 2020

Building and Environment

295

121

View full text Add to dashboard Cite

Buildings in cities consume up to 70% of all primary energy. To achieve cities' energy and climate goals, it is necessary to reduce energy use and associated greenhouse gas emissions in buildings through energy conservation and efficiency improvements. Computational tools empowered with rich urban datasets can model performance of buildings at the urban scale to provide quantitative insights for stakeholders and inform their decision making on urban energy planning, as well as building energy retrofits at scale, to achieve efficiency, sustainability, and resilience of urban buildings. Designing and operating urban buildings as a group (from a city block to a district to an entire city) rather than as single individuals requires simulation and optimization to account for interactions among buildings and between buildings and their surrounding urban environment, and for district energy systems serving multiple buildings with diverse thermal loads across space and time. When hundreds or more buildings are involved in typical urban building energy modeling (UBEM) to estimate annual energy demand, evaluate design or retrofit options, and quantify impacts of extreme weather events or climate change, it is crucial to integrate urban datasets and UBEM tools in a seamless automatic workflow with cloud or high-performance computing for users including urban planners, designers and researchers. This paper presents ten questions that highlight significant UBEM research and applications. The proposed answers aim to stimulate discussion and provide insights into the current and future research on UBEM, and more importantly, to inspire new and important questions from young researchers in the field.

show abstract

Section: Question 7: How Can Results From Ubem Be Calibrated?mentioning

confidence: 99%

Ten questions on urban building energy modeling

Hong

Chen

Luo

et al. 2020

Building and Environment

295

121

View full text Add to dashboard Cite

show abstract

“…The R 2 values for SS, COD, BOD, TN, and TP in the type 4 MLR of pollutant load were fairly high (0.614 < R 2 < 0.741), as indicated in Table 7. The performance evaluation by CV(RMSE) [35] shows that the SS model was the best and that the other models of the water quality variables were also acceptable. The range of RSR for SS, COD, BOD, and TP in the MLR models of pollutant load (Table 7) was from 0.509 to 0.559, and the performance of the MLR for these variables was good [34].…”

Section: Mlr Analysismentioning

confidence: 99%

Multiple Linear Regression Models for Predicting Nonpoint-Source Pollutant Discharge from a Highland Agricultural Region

Cho

Lee

2018

Water

View full text Add to dashboard Cite

Sediment runoff from dense highland field areas greatly affects the quality of downstream lakes and drinking water sources. In this study, multiple linear regression (MLR) models were built to predict diffuse pollutant discharge using the environmental parameters of a basin. Explanatory variables that influence the sediment and pollutant discharge can be identified with the model, and such research could play an important role in limiting sediment erosion in the dense highland field area. Pollutant load per event, event mean concentration (EMC), and pollutant load per area were estimated from stormwater survey data from the Lake Soyang basin. During the wet season, heavy rains cause large amounts of suspended sediment and the occurrence of such rains is increasing due to climate change. The explanatory variables used in the MLR models are the percentage of fields, subbasin area, and mean slope of subbasin as topographic parameters, and the number of preceding dry days, rainfall intensity, rainfall depth, and rainfall duration as rainfall parameters. In the MLR modeling process, four types of regression equations with and without log transformation of the explanatory and response variables were examined to identify the best performing regression model. The performance of the MLR models was evaluated using the coefficient of determination (R2), root mean square error (RMSE), coefficient of variation of the root mean square error (CV(RMSE)), the ratio of the RMSE to the standard deviation of the observed data (RSR) and the Nash–Sutcliffe model efficiency (NSE). The performance of the MLR models of pollutant load except total nitrogen (TN) was good under the condition of RSR, and satisfactory for the NSE and R2. In the EMC and load/area models, the performance for suspended solids (SS) and total phosphorus (TP) was good for the RSR, and satisfactory for the NSE and R2. The standardized coefficients for the models were analyzed to identify the influential explanatory variables in the models. In the final performance evaluation, the results of jackknife validation indicate that the MLR models are robust.

show abstract

“…The thermodynamic and heat transfer characteristics contained in those simulation input files could enhance with prediction capability of data-driven methods. The field of Bayesian calibration of simulation models provides the foundation for this effort [50].…”

Section: Integration Of Data-driven Modeling With Physics-based Whitementioning

confidence: 99%

More Buildings Make More Generalizable Models—Benchmarking Prediction Methods on Open Electrical Meter Data

Miller

2019

MAKE

View full text Add to dashboard Cite

Prediction is a common machine learning (ML) technique used on building energy consumption data. This process is valuable for anomaly detection, load profile-based building control and measurement and verification procedures. Hundreds of building energy prediction techniques have been developed over the last three decades, yet there is still no consensus on which techniques are the most effective for various building types. In addition, many of the techniques developed are not publicly available to the general research community. This paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project. The results illustrate that there are several techniques, notably decision tree-based models, that perform well on two-thirds of the total cohort of buildings. However, over one-third of the buildings, specifically primary schools, performed poorly. This example implementation shows that there is no one size-fits-all modeling solution and that various types of temporal behavior are difficult to capture using machine learning. An analysis of the generalizability of the models tested motivates the need for the application of future techniques to a board range of building types and behaviors. The importance of this type of scalability analysis is discussed in the context of the growth of energy meter and other Internet-of-Things (IoT) data streams in the built environment. This framework is designed to be an example baseline implementation for other building energy data prediction methods as applied to a larger population of buildings. For reproducibility, the entire code base and data sets are found on Github.

show abstract

Bayesian calibration of building energy models with large datasets

Cited by 97 publications

References 47 publications

Ten questions on urban building energy modeling

Ten questions on urban building energy modeling

Multiple Linear Regression Models for Predicting Nonpoint-Source Pollutant Discharge from a Highland Agricultural Region

More Buildings Make More Generalizable Models—Benchmarking Prediction Methods on Open Electrical Meter Data

Contact Info

Product

Resources

About