Energy and Buildings最新文献

{"title":"Day-ahead demand response potential prediction in residential buildings with HITSKAN: A fusion of Kolmogorov-Arnold networks and N-HiTS","authors":"Ali Muqtadir ,&nbsp;Bin Li ,&nbsp;Zhou Ying ,&nbsp;Chen Songsong ,&nbsp;Sadia Nishat Kazmi","doi":"10.1016/j.enbuild.2025.115455","DOIUrl":"10.1016/j.enbuild.2025.115455","url":null,"abstract":"<div><div>Accurate forecasting of Demand Response (DR) is vital for optimizing resource allocation in power systems, especially in markets where Load Aggregators (LAs) bid based on predicted DR potential. Traditional models struggle to capture the nonlinear dependencies of consumer behavior and the temporal patterns in energy consumption. This study aims to overcome these limitations by introducing HITSKAN, a hybrid approach which is a fusion of Kolmogorov-Arnold Networks (KANs) and Neural Hierarchical Interpolation (N-HiTS) to improve day-ahead DR potential forecasting. HITSKAN is able to solve the challenges faced by LAs by integrating the ability of KANs to model complex multivariate functions for nonlinearity together with the strength of N-HiTS in handling temporal dependencies. The methodology employs real-world residential load data from 114 apartments to capture historical demand response potential through thermal response modeling, which does not require appliance-level data and then applies the HITSKAN forecasting model to predict day-ahead DR potential. The performance of model is evaluated on all key metrics which include Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and systematic Mean Absolute Percentage Error (sMAPE) along with variance, standard deviation and computation time. Results demonstrate that HITSKAN outperforms state-of-the-art forecasting models in both winter and summer seasons. By incorporating KANs into a time series forecasting framework, HITSKAN offers a scalable and effective solution for DR potential forecasting, significantly enhancing grid management and resource optimization in residential settings.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115455"},"PeriodicalIF":6.6,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-model real-time energy consumption anomaly detection for office buildings based on circuit classification","authors":"Kuixing Liu,&nbsp;Jiale Tang,&nbsp;Lixin Xue","doi":"10.1016/j.enbuild.2025.115406","DOIUrl":"10.1016/j.enbuild.2025.115406","url":null,"abstract":"<div><div>With the widespread adoption of office building electricity consumption monitoring platforms, ample data are available for diagnosing energy anomalies, increasing interest in data-driven approaches. However, whole-building energy evaluation often fails to identify anomalies in specific sub-circuits. Additionally, the complexity of building energy systems has led research to focus mainly on data-driven methods, with limited exploration of individual sub-circuit characteristics. To address these issues, this study proposes a classification procedure based on physical attributes and data features of office building power circuits, categorizing energy-consumption circuits into four types. Subsequently, a multi-model real-time diagnostic framework was developed, which utilizes anomaly detection models tailored to specific circuits for precise identification of anomalies. The framework was experimentally validated using real-world data from a commercial office building in Haidian District, Beijing. The results demonstrated that the proposed method effectively performed hourly monitoring of energy consumption in lighting, chiller, and cooling tower circuits, and successfully identified multiple time periods during which energy consumption deviated from the normal range due to improper operations by facility management personnel. These findings highlight the benefit of integrating sub-metering with data mining, providing building operators with a novel approach to swiftly detect circuit-level abnormalities and optimize energy management strategies.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115406"},"PeriodicalIF":6.6,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Specific metrics for direct adiabatic cooling of industrial buildings and climate adaptation","authors":"Antoine Breteau ,&nbsp;Emmanuel Bozonnet ,&nbsp;Patrick Salagnac ,&nbsp;Jean-Marie Caous","doi":"10.1016/j.enbuild.2025.115472","DOIUrl":"10.1016/j.enbuild.2025.115472","url":null,"abstract":"<div><div>This paper presents an analysis of the performance of a direct evaporative cooling system incorporated into an industrial building, evaluated in various climates and weather conditions. This system is a simple and economical cooling solution widely used in industrial buildings that combines ventilation and water evaporation cooling. We characterized the system operation through the development of a coupled numerical model of the system and a typical industrial building, in a Mediterranean climate, in the mid-term horizon of 2050. A comparison without any system showed a 74 % reduction in degree-hours of thermal discomfort. Analysis of the building operation shows a predominance of nighttime free cooling, while the adiabatic operates during the occupancy hours. We compared the performance in four different locations, taking into account future weather and heatwaves. The system performed better in hot and dry climates if we consider only the thermal discomfort based on degree-hours, with a 48 % reduction in Abu Dhabi, compared to 41 % in Singapore. However, we observed very different tendencies with water consumption and cooling efficiency: with a cooling efficiency ratio to water use of 22.46 °Ch/m³ in the equatorial climate, which is almost double that obtained in the dry and arid climate. Arid climates were the most appropriate in terms of energy consumption. In Abu Dhabi, the performance (0.24 °Ch/kWh) was 13 % higher than in an equatorial climate such as Singapore. The results also show that the system performs better under future weather conditions for all the locations studied. Under future conditions, the cooling gain per unit of water consumed rose to 1.48 °Ch/m³, while the thermal escalation factor decreased by 0.054 points. These results highlight the ability of the system to effectively reduce thermal discomfort, while revealing trade-offs between thermal efficiency, energy consumption and use of water resources. This analysis underlines the relevance of the system to current and future climate challenges.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115472"},"PeriodicalIF":6.6,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-objective optimization of thermochromic glazing: Evaluating useful daylight illuminance, circadian stimulus, and energy performance with implications for sleep quality improvement","authors":"Lai Fan ,&nbsp;Liang Xie ,&nbsp;Qikang Zhong","doi":"10.1016/j.enbuild.2025.115460","DOIUrl":"10.1016/j.enbuild.2025.115460","url":null,"abstract":"<div><div>This study explores the application of thermochromic (TC) glazing to improve energy efficiency, Useful Daylight Illuminance (UDI), and Circadian Stimulus (CS) in a typical slab-style elderly apartment in Changsha. A multi-objective optimization approach was utilized, integrating GA-BP neural networks for predictive modeling and the Multi-Objective Grey Wolf Optimizer (MOGWO) to evaluate and balance the impacts of different outcomes on the indoor environment. The results demonstrate that TC glazing reduces energy consumption by up to 40 % compared to conventional glazing while stabilizing indoor temperatures and enhancing daylighting conditions, with a 27 % increase in UDI and a 15 % improvement in CS alignment. These enhancements support circadian rhythm regulation and contribute to a more comfortable indoor environment, ultimately improving sleep quality.</div><div>These findings underscore the effectiveness of TC glazing in retrofitting elderly apartments, offering significant energy savings and health-related benefits, providing a scalable framework for developing sustainable, health-supportive indoor environments applicable to similar climates and residential building types.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"333 ","pages":"Article 115460"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transfer learning with unsupervised domain adaptation for personal thermal comfort prediction","authors":"Chuangkang Yang,&nbsp;Keiichiro Taniguchi,&nbsp;Yasunori Akashi","doi":"10.1016/j.enbuild.2025.115449","DOIUrl":"10.1016/j.enbuild.2025.115449","url":null,"abstract":"<div><div>Maintaining comfortable indoor environments is essential for occupant well-being and energy efficiency. However, predicting personalized thermal comfort remains challenging owing to the limited availability of labeled data. This study presents a novel approach to personalized thermal comfort prediction by applying unsupervised domain adaptation techniques. We leverage ASHRAE Global Thermal Comfort Database II as the source domain and the BCA testbed dataset as the target domain to address the challenge of adapting the models to new subjects with no labeled data. Specifically, we compare three domain adaptation methods: Correlation alignment (CORAL), Deep subdomain adaptation network (DSAN), and Dynamic adversarial adaptation network (DAAN). Our results demonstrate that applying deep domain adaptation (DSAN and DAAN) significantly enhances the prediction accuracy for both thermal preference and thermal acceptability tasks, with improvements of up to 12—15% compared with the base (CNN-LSTM) model. Furthermore, our proposed method maintains a high prediction performance, even when the available training dataset is substantially reduced. The maximum reduction in accuracy is at most 2.28% with approximately 10% of the unlabeled training dataset, demonstrating its robustness in real-world scenarios with limited environmental features. This study underscores the potential of unsupervised deep domain adaptation for improving personalized thermal comfort predictions and contributes to more efficient indoor climate control and a comfortable environment.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115449"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A peer-to-peer energy bidding and transaction framework for prosumers based on blockchain consensus mechanism and smart contract","authors":"Yi Shang ,&nbsp;Xiaolan Li ,&nbsp;Tianqi Xu ,&nbsp;Lin Cui","doi":"10.1016/j.enbuild.2025.115447","DOIUrl":"10.1016/j.enbuild.2025.115447","url":null,"abstract":"<div><div>The deepening of electricity market reform and the increasing popularity of distributed energy resources (DERs) have led to significant challenges for the decentralized bidding and transaction mechanism for DERs to participate in the electricity market. Blockchain, as a distributed ledger, has emerged as one of the solutions for decentralized transactions, but blockchain-based peer-to-peer (P2P) transactions suffer from output uncertainty that cannot be effectively quantified and higher default rates. This study proposes a energy P2P bidding and transaction mechanism based on blockchain consensus and smart contracts, which effectively expands the extensibility of energy trading. Firstly, a strategy-varying auction mechanism is established, which considers the credibility and release time for prosumers. Secondly, a three-person non-cooperative P2P transaction process based on the uncertainty of photovoltaic (PV) is designed to improve the profit and stability of electricity transactions. Thirdly, a blockchain consensus mechanism based on credibility is designed. The fairness of the trading process is effectively enhanced. Finally, the transaction process is simulated on smart contracts. The proposed model is validated by theoretical and experimental analyses. The experimental results demonstrate that this study effectively reduces the transaction default rate to 1.4% and amplifies the profits of prosumers.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115447"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping indoor overheating exposure rate at city scale: A data-driven method based on building typologies and surrogate-modelling","authors":"Obaidullah Yaqubi ,&nbsp;Sihem Guernouti ,&nbsp;Auline Rodler ,&nbsp;Marjorie Musy","doi":"10.1016/j.enbuild.2025.115441","DOIUrl":"10.1016/j.enbuild.2025.115441","url":null,"abstract":"<div><div>Evaluation of urban-scale indoor overheating in buildings has become a critical area of research due to the combined effects of global warming and the Urban Heat Island (UHI) phenomenon, which have significantly impacted indoor comfort during summer and are projected to intensify. This study presents a comprehensive workflow for assessing urban-scale indoor overheating vulnerability, designed to support strategic decision-making in urban planning and climate-change adaptation policies. By reviewing literature on building typology construction methods and surrogate modeling, we propose a two-step method to estimate indoor overheating in residential buildings at a city scale, comprising a reductive stage and an extrapolative process.</div><div>In the reductive stage, residential buildings are aggregated into clusters with similar characteristics, and a representative building from each cluster undergoes a detailed characterization. The extrapolative process compensates for the loss of information diversity from the reductive stage through model parametrization. This involves performing parametric simulations on each representative building to create a new database, training a machine-learning-based surrogate model, and using it to estimate the performance of other buildings in the same cluster. Three indices were used to measure indoor overheating, and future typical weather data were applied to demonstrate the approach.</div><div>This methodology was used to create an indoor overheating exposure map for Nantes City. The procedures for training, testing, and validation are described in detail for two groups of buildings, providing a robust framework for urban planners and policymakers to develop effective climate-change adaptation strategies.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"332 ","pages":"Article 115441"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From energy-intensive buildings to NetPlus targets: An innovative solar exoskeleton for the energy retrofitting of existing buildings","authors":"Roberto Stasi,&nbsp;Francesco Ruggiero,&nbsp;Umberto Berardi","doi":"10.1016/j.enbuild.2025.115416","DOIUrl":"10.1016/j.enbuild.2025.115416","url":null,"abstract":"<div><div>The retrofitting of existing buildings is a challenging strategic objective towards achieving the European climate neutrality target by 2050. According to the Renovation Wave plan, the European Union aims to renovate around 35 million existing inefficient buildings to the highest energy efficiency level by 2030, requiring innovative technological solutions to succeed in this ambitious goal. Along this line, this paper proposes a prototype of a novel solar exoskeleton for the energy and architectural retrofitting of existing buildings, called “en-SʘLEX”. The system comprises a self-supporting external steel frame that envelops buildings like a double skin. It combines passive solar gain control, such as shading and greening, with high-efficiency active solar systems, including PV panels. The system’s modular and flexible design makes it easy to install, allowing for retrofitting from the outside without affecting occupancy, reducing the time and cost of its implementation. The energy-saving potential of the system, thermal and daylight comfort, and payback period with different façade configurations were evaluated on a multi-family residential building in a Mediterranean climate. The energy simulations demonstrate that the proposed solution can significantly reduce the energy required for space heating and cooling, by 33.4% and 25.5% respectively. A maximum reduction of 80.7% and 60.5% for heating and cooling is achieved by integrating the “en-SʘLEX” system with generator replacement. The integration of renewable energy sources leads to surplus electricity generation, which causes the building to exceed its average annual electricity demand regardless of the building orientation, thus transforming the existing building into a NetPlus one.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"333 ","pages":"Article 115416"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing urban building energy models with Vision Transformers: A Case study in material classification from Google street view","authors":"Yingjie Liu,&nbsp;Narjes Abbasabadi","doi":"10.1016/j.enbuild.2025.115457","DOIUrl":"10.1016/j.enbuild.2025.115457","url":null,"abstract":"<div><div>The growing urbanization and increased urban energy consumption highlight the need for energy use and greenhouse gas emissions reduction strategies. Urban Building Energy Modeling (UBEM) emerged as a valuable tool for managing and optimizing energy consumption at the neighborhood and city scales to support carbon reduction goals. However, the accuracy of the UBEM is often limited by the lack of large-scale building façade material dataset. This study introduces a new approach to enhance UBEM by integrating an automatic deep learning material classification pipeline. The pipeline leverages multiple views of Google Street View Images (SVIs) to extract building façade material information, utilizing two Swin Vision Transformer (ViT) models to capture both global and local features from the SVIs. The pipeline achieved a main material classification accuracy reached 97.08%, and the sub-category accuracy reached 91.56% in a multi-class classification task. As the first study to apply a deep learning model for material classification to enhance the UBEM framework, this work was tested on the University of Washington campus, which features diverse facade materials. The model demonstrated its effectiveness by achieving an overall accuracy increase of 11.4% in year-round total operational energy simulations. The scalability of this material classification pipeline enables a more accurate and cost-effective application of UBEM at broader urban scales.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"333 ","pages":"Article 115457"},"PeriodicalIF":6.6,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing energy consumption in centralized and distributed cloud architectures with a comparative study to increase stability and efficiency","authors":"Tangsen Huang,&nbsp;Weiguo Huang,&nbsp;Bin Zhang,&nbsp;Wenzhi Chen,&nbsp;Xuewen Pan","doi":"10.1016/j.enbuild.2025.115454","DOIUrl":"10.1016/j.enbuild.2025.115454","url":null,"abstract":"<div><div>Cloud computing serves as the backbone of modern digital infrastructure, supporting everything from basic data storage and processing to real-time big data analytics. However, the expanding scale and complexity of cloud systems have significantly increased energy consumption, posing serious environmental and economic concerns. This study explores an extended energy model that transitions from fully centralized to fully distributed architectures across diverse cloud-related configurations. The experimental results reveal that fully centralized architectures exhibit the highest energy consumption, with static energy usage from physical machines and switches accounting for approximately 1.4 MWh. In contrast, fully decentralized architectures demonstrated energy efficiency improvements, reducing energy consumption by 19% to 28%. An important observation was that static energy consumption remained consistent across all architectures, while dynamic energy consumption varied depending on traffic loads and system configurations. In fully distributed systems with central controllers, the dynamic energy consumption of physical machines remained below 0.1 MWh, and switches and routers consumed less than 0.05 MWh. These findings highlight the potential of decentralized architectures in achieving substantial energy savings, especially in edge computing and Internet of Things (IoT) applications. By reducing energy consumption, these architectures contribute to both environmental sustainability and cost efficiency. This study offers valuable insights for cloud service providers aiming to optimize energy efficiency across different architectural models.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"333 ","pages":"Article 115454"},"PeriodicalIF":6.6,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}