{"title":"In-depth sensitivity analysis of heating demand and overheating in Dutch terraced houses using interpretable machine learning","authors":"Alexis Cvetkov-Iliev , Vasilis Soulios , Luyi Xu , Günsu Merin Abbas , Evangelos Kyrou , Lisanne Havinga , Pieter Jan Hoes , Roel Loonen , Joaquin Vanschoren","doi":"10.1016/j.enbuild.2025.115611","DOIUrl":"10.1016/j.enbuild.2025.115611","url":null,"abstract":"<div><div>Sensitivity analyses are often performed to facilitate the design or modeling of complex building systems by focusing on the most influential parameters. However, the insights they produce are generally limited to a ranking of the parameters’ impact. Instead, many applications could benefit from more advanced insights, such as how these impacts vary across different parameter values and scenarios. In addition, sensitivity analysis results should be easily interpretable to facilitate subsequent decision making. With these goals in mind, this paper introduces a novel sensitivity analysis method based on partial dependence (PD) plots. PD plots are further combined with dictionary learning, advanced visualizations, and surrogate models to facilitate their analysis and reduce their computational cost. Using this method, the effect of 26 parameters on heating demand and overheating in Dutch terraced houses is investigated. Two surrogate models are trained on 66,000 EnergyPlus simulations to predict the annual heating demand and percentage of overheating hours with excellent precision (<span><math><mrow><mo>≈</mo><mn>3</mn></mrow></math></span>–4 % of percentage error). The benefits of our approach are demonstrated through 3 use cases: 1) a comparison of the impact and energy-overheating trade-off of insulation measures across various scenarios, 2) improving the design of parametric simulations by eliminating redundant parameter values, and 3) uncovering complex behaviors in simulation or surrogate models, to build trust in them and diagnose potential modeling or training errors. Finally, our results suggest that surrogate models can be trained on much less data (1000–3000) without compromising sensitivity analysis results.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115611"},"PeriodicalIF":6.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725623","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":"Explaining building energy efficiency prediction through architectural and engineering solutions considering environmental impacts using a hybrid model","authors":"Semi Emrah Aslay","doi":"10.1016/j.enbuild.2025.115614","DOIUrl":"10.1016/j.enbuild.2025.115614","url":null,"abstract":"<div><div>The aim of this study is to investigate building energy efficiency by integrating hybrid modelling approaches and interpretable models into architectural design processes and engineering solutions while considering environmental impacts. At the same time, it is aimed to achieve the most efficient building design possible. Separate analyses were carried out using a total of 6,913 data from Rutland (185) and Salford (6718) cities. The data were grouped into carbon emission information, architectural information, lighting information, personal heating information, and main heating system information to form a dataset. Light Gradient Boosting Machine (LightGBM) was preferred as the base model and Particle Swarm Optimisation (PSO) method was applied for hyperparameter optimisation. The hybrid model created in this way is called PSO-LightGBM. The optimization process was carried out using software in both R Studio and Python environments, utilizing seven different hyperparameters. Apart from the hybrid model used as a method, 2 different SHAP analyses, neural network based, and tree based, were performed to clearly explain the parameter relationships. The PSO-LightGBM hybrid model provided more successful predictions compared to the basic LightGBM model. While R<sup>2</sup> values improved between 0.82 and 0.90 in the Rutland dataset, this value increased from 0.8687 to 0.8901 for test data and from 0.8538 to 0.9091 for training data in the Salford dataset. R<sup>2</sup> values show an improvement of 7% in the Rutland dataset and maximum 6% in the Salford dataset. When the reduction in error rates is evaluated, it is found that the greatest improvement is in the Mean Squared Error (MSE) metric. MSE decreased by 17% in the Rutland dataset and by 4% in the Salford dataset. According to the SHAP Analysis results, CO<sub>2</sub> emissions have the largest impact on energy consumption, while primary fuel types, number heated rooms and individual heating systems are other important parameters. While the tree-based SHAP model is more sensitive to physical parameters, the neural network model is more sensitive to indirect relationships. In both analyses, the communal heating system type has the lowest impact. In order to improve building energy efficiency, high efficiency individual boiler systems should be preferred, architectural approaches that optimise the number of heated rooms and smart heating solutions should be used, and central heating systems should be modernised. The results highlight the effectiveness of hybrid modelling approaches with SHAP analyses based on different baselines to ensure the integration of environmental impacts, architectural design processes and engineering solutions in terms of building energy efficiency. Furthermore, the findings contribute to the importance of interdisciplinary work in buildings to improve energy efficiency. Future studies can focus on the development of building energy performance prediction models","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115614"},"PeriodicalIF":6.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714516","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}
Amine Jarraya , Tim Diller , Himanshu Nagpal , Anton Soppelsa , Federico Trentin , Gregor Henze , Roberto Fedrizzi
{"title":"On-Site temperature and irradiance forecast tuning for improved load prediction in buildings","authors":"Amine Jarraya , Tim Diller , Himanshu Nagpal , Anton Soppelsa , Federico Trentin , Gregor Henze , Roberto Fedrizzi","doi":"10.1016/j.enbuild.2025.115642","DOIUrl":"10.1016/j.enbuild.2025.115642","url":null,"abstract":"<div><div>Building management systems (BMSs) with predictive control strategies rely on accurate weather forecasts to optimise heating and cooling operations. These strategies depend on precise climatic inputs to adjust system operations dynamically. Typically, weather forecast data is sourced from the internet and is generated by numerical weather prediction (NWP) models using advanced mathematical simulations. However, these models fail to account for localised nano-climatic variations, such as significant temperature and irradiance differences between the north and south sides of a building or the actual environmental conditions around the on-site sensors. These nano-climatic effects directly influence the calculation of the future thermal load of the building, which is crucial for predictive control approaches. To address this challenge, we propose a hybrid methodology that integrates NWP forecasts with local measurements from on-site sensors, improving NWP forecast accuracy. Our approach employs Inverse Distance Weighting (IDW) to interpolate NWP outputs to a specific geographical position and applies exponential smoothing for further finetuning by using historical error patterns. This methodology enhances the predictive accuracy of temperature and irradiance forecasts, achieving reductions of up to 60% to 80% in temperature errors and up to 20% to 30% in irradiance errors. Based on the finetuned weather forecast, the accuracy of building’s thermal load prediction is improved up to 86% compared to the predictions with IDW weather forecast.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115642"},"PeriodicalIF":6.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714515","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}
Wenqiang Li , Xin Jin , Pei Peng , Zaiyi Liao , Min Wu , Huahua Xu , Jiashun Feng
{"title":"Is it necessary to calibrate existing decision-making results based on real option analysis during the process of climate change? A case study from Xiamen, China","authors":"Wenqiang Li , Xin Jin , Pei Peng , Zaiyi Liao , Min Wu , Huahua Xu , Jiashun Feng","doi":"10.1016/j.enbuild.2025.115658","DOIUrl":"10.1016/j.enbuild.2025.115658","url":null,"abstract":"<div><div>Previous studies have rarely examined how well Representative Concentration Pathways (RCP) scenarios fit with real weather data making climate change related decision-makings. This paper proposes a real option analysis (ROA) decision-making calibration method based on RCP (learning) scenarios uncertainty caused by the gap between the simulated and real weather conditions. Firstly, EnergyPlus is used to predict the energy consumption of a case building based on future climatic conditions, and the learning scenarios uncertainty is quantified. Secondly, a ROA decision-making calibration model (ROACM) is established through optimization to minimize the learning scenarios uncertainty. Finally, the ROACM is applied to a case study of an office building located in Xiamen, China, aiming to calibrate individual and sequential investment decisions for three retrofitting measures (<span><math><msub><mi>R</mi><mn>1</mn></msub></math></span>: horizontal shading, <span><math><msub><mi>R</mi><mn>2</mn></msub></math></span>: low-e windows, <span><math><msub><mi>R</mi><mn>3</mn></msub></math></span>: improving COP of chiller). The accuracy of ROACM is assessed through a sensitivity analysis. The results indicate that the learning scenarios uncertainty leads to annual energy consumption differences of approximately 8,451 kW <span><math><mo>∙</mo></math></span>h to 17,545 kW<span><math><mo>∙</mo></math></span>h in the case study. After calibration, the optimal timing for both individual and sequential investment has advanced by at least 4 years, significantly boosting returns. The optimal individual investment <span><math><msub><mi>R</mi><mn>3</mn></msub></math></span> generated an additional return of up to $52,744, while the sequential investment <span><math><mrow><msub><mi>R</mi><mn>1</mn></msub><mo>+</mo><msub><mi>R</mi><mn>13</mn></msub></mrow></math></span> (shading first, and improving COP of chiller later), increased by $175,017. The proposed ROACM demonstrated high performance during model validation in a case study, and could also aid governments or investors in ROA-based mitigation strategies analysis and increasing the reliability of the results.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115658"},"PeriodicalIF":6.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739822","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}
Tian Wang , Qinfeng Zhao , Weijun Gao , Jialu Dai , Mengyuan Zhou , Yi Yu
{"title":"Influence of social and economic aspects on end-use energy consumption in Chinese urban households","authors":"Tian Wang , Qinfeng Zhao , Weijun Gao , Jialu Dai , Mengyuan Zhou , Yi Yu","doi":"10.1016/j.enbuild.2025.115645","DOIUrl":"10.1016/j.enbuild.2025.115645","url":null,"abstract":"<div><div>Reducing household energy consumption is essential for China’s implementation of its “dual-carbon” commitment. This study established an accounting framework to analyze urban Household End-use Energy Consumption (HEEC) across 30 Chinese provinces. The framework links five types of household activities to five energy sources through appliance functionality. The Logarithmic Mean Divisia Index (LMDI) method was used to quantify the social and economic factors affecting HEEC. The results show that HEEC increased by approximately 30% from 2010 to 2019, with provincial disparities decreasing. Kitchen/hot water and heating were the primary drivers of this growth, contributing 38.5% and 33.8%, respectively. Meanwhile, energy consumption for cooling and power grew rapidly at annual rates of 5.6% and 4.8%, respectively. Decomposition analysis revealed that income growth and urban expansion were major drivers of HEEC growth. The rise in single-person households, which reduces economies of scale in household activities, has also increased HEEC. However, energy consumption intensity and behavioral habits played key roles in curbing the HEEC growth. These insights underline the significant impact of social and economic development on HEEC and underscore the need for continued appliance upgrades and energy reforms in China.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115645"},"PeriodicalIF":6.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725343","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":"Unsupervised domain adaptation for HVAC fault diagnosis using contrastive adaptation network","authors":"Naghmeh Ghalamsiah , Jin Wen , K.Selcuk Candan , Teresa Wu , Zheng O’Neill , Asra Aghaei","doi":"10.1016/j.enbuild.2025.115659","DOIUrl":"10.1016/j.enbuild.2025.115659","url":null,"abstract":"<div><div>Data-driven methods have shown great promise for heating, ventilation, and air conditioning (HVAC) systems’ fault diagnosis, but their reliance on well-labeled datasets poses challenges in real-world applications where such data may not be readily available. Meanwhile, well-labeled data might exist from virtual testbeds or laboratory systems. Domain adaptation could provide a solution to utilize labeled data from a source domain (such as a virtual or laboratory testbed) to diagnose faults in an unlabeled target domain, such as faults in a real building system. This paper utilizes the contrastive adaptation network (CAN) algorithm, originally successful in image classification, to overcome the specific challenges faced by current domain adaptation algorithms in HVAC systems. Furthermore, temporal causal discovery framework (TCDF), a causality-based framework for discovering causal relationships in time series data, is implemented in the data processing step to meet the requirements of convolutional networks, where spatially closer features are more likely to be correlated. The results on air handling unit (AHU) datasets demonstrate that the CAN algorithm effectively facilitates domain adaptation in the absence of target labels and that the feature reordering process reduces the training time and the number of loops required for convergence.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115659"},"PeriodicalIF":6.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714513","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}
Mohammad Hosseini , Silvia Erba , Ahmad Mazaheri , Amin Moazami , Vahid M. Nik
{"title":"From flexible building to resilient energy communities: A scalable decentralized energy management scheme based on collaborative agents","authors":"Mohammad Hosseini , Silvia Erba , Ahmad Mazaheri , Amin Moazami , Vahid M. Nik","doi":"10.1016/j.enbuild.2025.115651","DOIUrl":"10.1016/j.enbuild.2025.115651","url":null,"abstract":"<div><div>Extreme conditions caused by climate change and other crises call for enhancing the resilience of buildings and urban energy systems. This paper investigates the role of collaborative decision-making to improve the performance of single buildings and the unified whole in the form of a cohesive cluster of energy consumers to enhance resilience. CIRLEM, the previously developed energy management approach, provides flexibility in energy systems through collective behavior of entities and deploying a lightweight Reinforcement Learning algorithm. This research contributes to developing a novel signal generation structure including price- and demand-based function to stimulate the cohesion attribute. Extended thermal comfort margins are introduced to broaden the flexibility potential, and reward function includes thermal zones categories. The energy management approach and extended comfort constraints is tested under an extreme cold winter in a pilot ecosystem located in Norway made of several buildings characterized by different sizes, use types, performance and energy systems. Acting individually, buildings could save 28 % and 13 % energy and cost, while acting as a collaborative cluster, energy use and cost are reduced by 42 % and 40 %. Through collaboration between buildings, high-performance buildings could help others under high energy demand periods to keep their functionality toward the cluster’s goal.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115651"},"PeriodicalIF":6.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725342","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":"Thermal design of quadratic segmental precast concrete driven energy piles","authors":"Habibollah Sadeghi , Olai Stensland Lillevold , Mohammad Liravi , Rao Martand Singh","doi":"10.1016/j.enbuild.2025.115652","DOIUrl":"10.1016/j.enbuild.2025.115652","url":null,"abstract":"<div><div>This paper introduces a novel thermal design methodology for segmental quadratic precast concrete energy piles. While thermal analysis methods for energy piles have been extensively studied, no previous research has specifically focused on long segmental quadratic concrete driven energy piles. Additionally, previous studies have applied fixed temperature boundary condition at the pile/ground top surface, which is the incorrect representation of the interface between the pile/ground surface and the building at the top. The main contributions of the present study are the development of semi-empirical G-function design charts, using a heat flux boundary at the pile/ground surface, and covering a wider range of energy pile lengths and soil and concrete material properties. A 3D finite element model was validated with thermal response tests on quadratic energy piles, and later employed to produce G-functions, applicable to longer segmental quadratic piles. The G-function design charts simplify the thermal design for practicing engineers and require minimum computational effort for long-term analysis. The results reveal that the pile/ground surface boundary conditions can affect long-term thermal performance by approximately 20%, though their influence is negligible in short-term analyses. The developed G-functions were employed to investigate two case studies in terms of ground temperature prediction for a quadratic driven energy pile under apartment blocks located in Oslo and Røros, respectively. The case studies showed that quadratic driven energy piles can cover 60%, and 48% of the heating demand for well insulated buildings in Oslo and Røros, during the design life of the buildings without adversely affecting the ground temperature.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115652"},"PeriodicalIF":6.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747379","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":"Development of representative city region models for south China’s Pearl River Delta: Data statistics and model definition","authors":"Siwei Lou , Chunguang Huang , Yukai Zou , Yu Huang","doi":"10.1016/j.enbuild.2025.115653","DOIUrl":"10.1016/j.enbuild.2025.115653","url":null,"abstract":"<div><div>Urban energy planning is essential for sustainable city development, especially with the rising energy demand driven by dense urbanization and increased reliance on renewable energy systems. This study proposes a methodology for defining representative city regions for energy planning by analyzing building morphology and energy consumption patterns in Shenzhen, China. Residential and commercial regions were identified using a combination of Point of Interest (POI) analysis and morphological clustering based on building coverage ratio, floor area ratio, and average building height. Representative regions were then populated with simplified building models to simulate energy demand, accounting for spatial distribution and inter-shading effects. The results reveal distinct energy consumption patterns between residential and commercial regions, with compact commercial areas exhibiting significantly higher cooling energy demand, particularly during peak summer months. These findings highlight the importance of considering urban morphology and building usage in regional energy planning to optimize energy production and distribution. The methodology and insights derived from this study provide a scalable framework for improving the efficiency and sustainability of urban energy systems.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115653"},"PeriodicalIF":6.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714514","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":"Lessons learnt from embodied GHG emission calculations in zero emission neighbourhoods (ZENs) from the Norwegian ZEN research centre","authors":"Marianne Rose Kjendseth Wiik","doi":"10.1016/j.enbuild.2025.115655","DOIUrl":"10.1016/j.enbuild.2025.115655","url":null,"abstract":"<div><div>This article presents, evaluates, discusses, and extracts lessons learnt on the calculation methodologies and design choices relating to embodied greenhouse gas (GHG) emission calculations from zero emission neighbourhood (ZEN) case studies from the Norwegian ZEN research centre. In all, eight case studies are assessed, varying in size, phase of development, typology, and location. The embodied GHG emission results show life cycle modules B8 operational transport (24 – 75 %), B6 operational energy (12 – 57 %), and A1 − A3 material production (20 – 38 %) contribute the most to total GHG emissions, as well as the main building (24 – 91 %), heating, ventilation and air conditioning (HVAC) installations (15 – 30 %), and electric power (4 – 22 %). In summary, more consistent calculation methodologies and system boundaries are required at the neighbourhood level to improve transparency, and further climate mitigation strategies are required to achieve a net zero GHG emission balance.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"336 ","pages":"Article 115655"},"PeriodicalIF":6.6,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697069","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}