Creating a Large-Scale National Residential Building Energy Dataset Using a Two-Stage Machine Learning Approach DOI
Sorena Vosoughkhosravi, Amirhosein Jafari

Construction Research Congress 2022, Journal Year: 2024, Volume and Issue: unknown, P. 305 - 315

Published: March 18, 2024

Buildings account for 40% of total energy demand in the US. Consequently, there is a pressing need dataset that provides comprehensive information on consumption household units The current practice large-scale simulations may not reflect actual patterns. Additionally, existing national building datasets, such as RECS, have limited number datapoint and do social aspects households. This study aimed to create residential using two-stage machine learning approach, combining two datasets RECS AHS. outcome this contains about well their detailed features. Three algorithms, including artificial neural networks (ANN), random forest (RF), gradient boosting regression (GBR), were used develop data-integration framework. results showed RF had best performance predicting end-use consumption. predicted generated an accuracy over 80%. These findings significant implications energy-efficient design operation.

Language: Английский

Potential of Explainable Artificial Intelligence in Advancing Renewable Energy: Challenges and Prospects DOI
Van Nhanh Nguyen, W. Tarełko, Prabhakar Sharma

et al.

Energy & Fuels, Journal Year: 2024, Volume and Issue: 38(3), P. 1692 - 1712

Published: Jan. 19, 2024

Modern machine learning (ML) techniques are making inroads in every aspect of renewable energy for optimization and model prediction. The effective utilization ML the development scaling up systems needs a high degree accountability. However, most approaches currently use termed black box since their work is difficult to comprehend. Explainable artificial intelligence (XAI) an attractive option solve issue poor interoperability black-box methods. This review investigates relationship between (RE) XAI. It emphasizes potential advantages XAI improving performance efficacy RE systems. realized that although integration with has enormous alter how produced consumed, possible hazards barriers remain be overcome, particularly concerning transparency, accountability, fairness. Thus, extensive research required address societal ethical implications using create standardized data sets evaluation metrics. In summary, this paper shows potential, perspectives, opportunities, challenges application system management operation aiming target efficient energy-use goals more sustainable trustworthy future.

Language: Английский

Citations

46
Energy consumption prediction and household feature analysis for different residential building types using machine learning and SHAP: Toward energy-efficient buildings DOI
Xuerong Cui, Minhyun Lee, Choongwan Koo

et al.

Energy and Buildings, Journal Year: 2024, Volume and Issue: 309, P. 113997 - 113997

Published: Feb. 19, 2024

Language: Английский

Citations

41
An interpretable multi-stage forecasting framework for energy consumption and CO2 emissions for the transportation sector DOI Creative Commons
Qingyao Qiao, Hamidreza Eskandari, Hassan Saadatmand

et al.

Energy, Journal Year: 2023, Volume and Issue: 286, P. 129499 - 129499

Published: Nov. 6, 2023

The transportation sector is deemed one of the primary sources energy consumption and greenhouse gases throughout world. To realise design sustainable transport, it imperative to comprehend relationships evaluate interactions among a set variables, which may influence transport CO2 emissions. Unlike recent published papers, this study strives achieve balance between machine learning (ML) model accuracy interpretability using Shapley additive explanation (SHAP) method for forecasting emissions in UK's sector. end, paper proposes an interpretable multi-stage framework simultaneously maximise ML determine relationship predictions influential variables by revealing contribution each variable predictions. For sector, experimental results indicate that road carbon intensity found be most contributing both other studies, population GDP per capita are uninfluential variables. proposed assist policymakers making more informed decisions establishing accurate investment.

Language: Английский

Citations

20
Development of advanced machine learning for prognostic analysis of drying parameters for banana slices using indirect solar dryer DOI Creative Commons
Van Giao Nguyen, Prabhu Paramasivam, Marek Dzida

et al.

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: 60, P. 104743 - 104743

Published: June 24, 2024

In this study, eXtreme Gradient Boosting (XGBoost) and Light (LightGBM) algorithms were used to model-predict the drying characteristics of banana slices with an indirect solar drier. The relationships between independent variables (temperature, moisture, product type, water flow rate, mass product) dependent (energy consumption size reduction) established. For energy consumption, XGBoost demonstrates superior performance R2 0.9957 during training 0.9971 testing, alongside minimal MSE 0.0034 0.0008 testing phase indicating high predictive accuracy low error rates. Conversely, LGBM shows lower values (0.9061 training, 0.8809 testing) higher 0.0747 0.0337 reflecting poorer performance. Similarly, for shrinkage prediction, outperforms LGBM, evidenced by (0.9887 0.9975 (0.2527 0.4878 testing). comparative statistics showed that regularly outperformed LightGBM. game theory-based Shapley functions revealed temperature types most influential features model. These findings illustrate practical applicability LightGBM models in food operations towards optimizing conditions, improving quality, reducing consumption.

Language: Английский

Citations

7
Predicting the Energy Consumption of Commercial Buildings Based on Deep Forest Model and Its Interpretability DOI Creative Commons

Guangfa Zheng,

Zao Feng, Mingkai Jiang

et al.

Buildings, Journal Year: 2023, Volume and Issue: 13(9), P. 2162 - 2162

Published: Aug. 25, 2023

Building energy assessment models are considered to be one of the most informative methods in building efficiency design, and current have been developed based on machine learning algorithms. Deep proved their effectiveness fields such as image fault detection. This paper proposes a deep framework with interpretability support design. The proposed is validated using Commercial Energy Consumption Survey dataset, results show that wrapper feature selection method (Sequential Forward Generation) significantly improves performance compared filtered (Mutual Information) embedded (Least Absolute Shrinkage Selection Operator) Moreover, Forest model has an R2 0.90 outperforms Multilayer Perceptron, Convolutional Neural Network, Backpropagation Radial Basis Function Network terms prediction performance. In addition, reveal how features affect contribution consumption single sample. study helps designers assess new buildings develop improvement measures.

Language: Английский

Citations

12
A Decision-Making Tool for Sustainable Energy Planning and Retrofitting in Danish Communities and Districts DOI Creative Commons
Muhyiddine Jradi

Energies, Journal Year: 2025, Volume and Issue: 18(3), P. 692 - 692

Published: Feb. 2, 2025

This study presents a novel framework for city-level energy planning and retrofitting, tailored to Danish cities neighborhoods. The addresses the challenges of large-scale urban modeling by integrating automated processes data collection, demand prediction, renewable integration. It combines open-source simulation tools validated datasets, enabling efficient scalable predictions performance across areas, including streets, districts, entire cities, with minimal user input. key components include collection modeling, resource estimation, gap evaluation, design retrofitting strategies DanCTPlan tool, developed based on this framework, was applied two case studies in Denmark: single street 101 buildings district comprising five streets 1284 buildings. In single-street case, all meet current regulations resulted 60.8% reduction heat 5.8% electricity demand, significant decreases peak demands. district-level measures led 29.5% 2.4% demand. Renewable scenarios demonstrated that photovoltaic systems supplying 30% solar thermal meeting 10% heating would require capacities 2218 kW 3540 kW, respectively. framework’s predictive capabilities flexibility position it as robust tool support decision-makers developing sustainable cost-effective strategies, paving way toward establishing energy-efficient positive districts.

Language: Английский

Citations

0
A review of the influencing factors of building energy consumption and the prediction and optimization of energy consumption DOI Creative Commons

Zhongjiao Ma,

Z. Yan,

M. He

et al.

AIMS energy, Journal Year: 2025, Volume and Issue: 13(1), P. 35 - 85

Published: Jan. 1, 2025

<p>Concomitant with the expeditious growth of construction industry, challenge building energy consumption has become increasingly pronounced. A multitude factors influence operations, thereby underscoring paramount importance monitoring and predicting such consumption. The advent big data engendered a diversification in methodologies employed to predict Against backdrop influencing operation consumption, we reviewed advancements research pertaining supervision prediction deliberated on more energy-efficient low-carbon strategies for buildings within dual-carbon context, synthesized relevant progress across four dimensions: contemporary state supervision, determinants optimization Building upon investigation three predictive were examined: (ⅰ) Physical methods, (ⅱ) data-driven (ⅲ) mixed methods. An analysis accuracy these revealed that methods exhibited superior precision actual Furthermore, predicated this foundation identified determinants, also explored prediction. Through an in-depth examination prediction, distilled pertinent accurate forecasting offering insights guidance pursuit conservation emission reduction.</p>

Language: Английский

Citations

0
Carbon emission assessment and interpretability improvement empowered by machine learning: A case study in four cities, China DOI
Zhan Jin, Wenjing He, Eugenia Gasparri

et al.

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115530 - 115530

Published: Feb. 1, 2025

Language: Английский

Citations

0
Machine learning application in building energy consumption prediction: A comprehensive review DOI

Jingsong Ji,

Hao Yu, Xudong Wang

et al.

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 112295 - 112295

Published: March 1, 2025

Language: Английский

Citations

0
Pathways to urban net zero energy buildings in Canada: A comprehensive GIS-based framework using open data DOI Creative Commons
Yang Li, Yang Li

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: 122, P. 106263 - 106263

Published: March 1, 2025

Language: Английский

Citations

0