Data-driven approach to predicting the energy performance of residential buildings using minimal input data

Seo, Ji-Hyun; Kim, Seohoon; Lee, Sung‐Jin; Jeong, Hakgeun; Kim, Taeyeon; Kim, Jonghun

doi:10.1016/j.buildenv.2022.108911

Cited by 32 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to UBEM based on physical simulation, early data-driven approaches often necessitated a plethora of input parameters to ensure model prediction accuracy. However, recent advancements have seen interpretable analysis employed to identify the most impactful features on building energy use, thereby reducing the required feature inputs for data-driven models (Seo et al, 2022;L. Zhang, 2021).…”

Section: Data-driven Building Energy Predictionmentioning

confidence: 99%

Predicting building energy consumption in urban neighborhoods using machine learning algorithms

Jiang,

Huang,

et al. 2024

FURP

View full text Add to dashboard Cite

Assessing building energy consumption in urban neighborhoods at the early stages of urban planning assists decision-makers in developing detailed urban renewal plans and sustainable development strategies. At the city-level, the use of physical simulation-based urban building energy modeling (UBEM) is too costly, and data-driven approaches often are hampered by a lack of available building energy monitoring data. This paper combines a simulation-based approach with a data-driven approach, using UBEM to provide a dataset for machine learning and deploying the trained model for large-scale urban building energy consumption prediction. Firstly, we collected 18,789 neighborhoods containing 248,938 buildings in the Shanghai central area, of which 2,702 neighborhoods were used for UBEM. Simultaneously, building functions were defined by POI data and land use data. We used 14 impact factors related to land use and building morphology to define each neighborhood. Next, we compared the performance of six ensemble learning methods modeling impact factors with building energy consumption and used SHAP to explain the best model; we also filtered out the features that contributed the most to the model output to reduce the model complexity. Finally, the balanced regressor that had the best prediction accuracy with the minimum number of features was used to predict the remaining urban neighborhoods in the Shanghai central area. The results show that XGBoost achieves the best performance. The balanced regressor, constructed with the 9 most contributing features, predicted the building rooftop photovoltaics potential, total load, cooling load, and heating load with test set accuracies of 0.956, 0.674, 0.608, and 0.762, respectively. Our method offers an 85.5%-time advantage over traditional methods, with only a maximum of 22.75% of error.

show abstract

Section: Data-driven Building Energy Predictionmentioning

confidence: 99%

Predicting building energy consumption in urban neighborhoods using machine learning algorithms

Jiang,

Huang,

et al. 2024

FURP

View full text Add to dashboard Cite

show abstract

“…Fundamentally, building energy prediction belongs to the time series forecasting or regression problem, and data-driven methods have drawn more attention recently due to their powerful ability to model complex relationships without expert knowledge. Among those methods, ANNs have proven to be one of the most suitable and potential approaches [21], [22]. ANNs are a subset of Machine Learning (ML) The first step in the implementation of an ANN model is the selection of meaningful features.…”

Section: Predicting Post-retrofit Energy Performancesmentioning

confidence: 99%

Data driven economic scenarios for retrofitting residential buildings in a northern Italian region

Cecconi

Rampini

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

European directives and strategies, such as the ‘European Green Deal’ and the ‘Ren-ovation Wave’, point out the importance of the building sector in achieving the climate goals set by the European Union for 2050. However, a higher renovation rate for the existing buildings is required to achieve these goals. Many barriers prevent the renovation rate from growing. Regarding financial barriers, the long payback times of renovation interventions and the high risk perceived by the potential investors make the renovation rate remain low. Based on data from energy performance certificates, this research proposes a data-driven method to create economic retrofit scenarios for residential buildings using Artificial Intelligence techniques and Monte Carlo simulations. Namely, energy savings have been predicted using an Artificial Neural Network on clusters of residential buildings and the Life Cycle Costs forecasted by Monte Carlo simulations taking into account the uncertainty in many of the inputs. Results obtained by applying the method to a region in northern Italy illustrate two scenarios for the energy retrofit of the built environment, one assuming a payback time of fifteen years and the other of twenty-five years. In both cases, the maximum allowable investment, which varies according to the specific characteristics of the buildings, is much lower than the retrofit costs recorded in the same area in recent years.

show abstract

“…However, this task becomes more challenging due to changes during maintenance, extensions, and replacements (Opher et al 2021a). Furthermore, the lack of standardization in building construction complicates data gathering (Seo et al 2022). To avoid unintended shifts in burden, decarbonization plans should consider and assess the potential impacts and trade-offs at different stages (Memarzadeh andGolparvar-Fard 2012, Peña et al 2021).…”

Section: Lcamentioning

confidence: 99%

Net zero emission buildings: a review of academic literature and national roadmaps

Þórólfsdóttir,

Árnadóttir,

Heinonen

2023

Environ. Res.: Infrastruct. Sustain.

View full text Add to dashboard Cite

Addressing the growing issue of climate change demands active measures. With its significant carbon footprint, the building industry needs to make immediate efforts contributing to achieving the Paris Agreement’s objective of restricting global warming to 1.5 °C. This review focuses on net zero emission buildings (NZEBs) which are claimed to offer a viable option to significantly reduce greenhouse gas emissions from the built environment. The review covers both the recent academic literature on NZEBs, and the NZEB roadmaps from the member organizations of the World Green Building Council, focusing on those Green Building Councils actively working to implement NZEBs in their local contexts. By synthesizing a broad range of viewpoints and practices derived from academic literature and roadmaps, this review provides a holistic overview of the different perspectives to the current state of NZEBs and to their future. The review shows that NZEBs have the potential to provide significant environmental, economic, and social advantages, improving the built environment’s overall sustainability. The review also promotes a more thorough understanding over NZEBs that can facilitate collaborative policymaking and action amongst stakeholders.

show abstract

Data-driven approach to predicting the energy performance of residential buildings using minimal input data

Cited by 32 publications

References 38 publications

Predicting building energy consumption in urban neighborhoods using machine learning algorithms

Predicting building energy consumption in urban neighborhoods using machine learning algorithms

Data driven economic scenarios for retrofitting residential buildings in a northern Italian region

Net zero emission buildings: a review of academic literature and national roadmaps

Contact Info

Product

Resources

About