Energy and Buildings最新文献_第10页

Optimization of a photovoltaic-thermal-dual-source heat pump system using day-ahead forecasting and time-of-use pricing 利用日前预测和分时定价优化光伏-热-双源热泵系统

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-20 DOI: 10.1016/j.enbuild.2026.117034

Minglu Qu, Junhan Chen, Yusen Bai, Jiajie Chen

Solar energy, as a renewable energy source, offers significant potential in the field of building heating. However, the intermittency and misalignment with grid demand periods limit its effective utilization in building heating applications. Whereas prior investigations have examined either time-of-use (TOU) electricity tariffs or energy forecasting as standalone problems, a research gap persists in synergistically integrating day-ahead forecasts with real-time price signals to co-optimize the operation of integrated photovoltaic-thermal heat pump (PV/T-HP) systems with energy storage. To address this gap, this study proposes a photovoltaic-thermal dual-source heat pump with electricity energy storage (PV/T-DSHP-EES) system, optimized through TOU pricing-based charging and discharging strategies. Three operational strategies, i.e., self-consumption maximization (SCM) strategy, TOU and day-ahead forecasting TOU (DA-TOU), are developed and simulated using TRNSYS and MATLAB for an office building in Shanghai. Results indicate that DA-TOU strategy achieves the lowest comprehensive cost (considering both operational and environmental treatment costs) in both daily (1.31 CNY) and monthly (97.39 CNY) winter simulations, demonstrating its superiority in balancing economic and environmental performance. Furthermore, an enhanced particle swarm optimization (PSO) algorithm, improved to avoid local optima and enhance global search capability, is applied to refine the DA-TOU strategy. This optimization reduced the total grid electricity supplementation by 9.4% to 3.10 kWh and the comprehensive cost by 8.0% to 3.33 CNY. The proposed system and optimized control framework provide a replicable methodology for enhancing the economic and environmental performance of building-integrated renewable energy systems, offering a viable pathway for low-carbon heating in urban environments.

太阳能作为一种可再生能源，在建筑供暖领域具有巨大的潜力。然而，它的间歇性和与电网需求周期的不一致性限制了它在建筑供暖应用中的有效利用。尽管之前的研究已经将分时电价（TOU）或能源预测作为独立的问题进行了研究，但在将日前预测与实时价格信号协同整合以共同优化集成光伏-热热泵（PV/T-HP）系统与储能系统的运行方面，研究差距仍然存在。为了解决这一差距，本研究提出了一种具有电力储能的光伏-热双源热泵（PV/T-DSHP-EES）系统，通过基于分时电价的充放电策略进行优化。以上海某办公楼为例，利用TRNSYS软件和MATLAB软件，对自耗最大化（SCM）、分时电价（TOU）和日前预测分时电价（DA-TOU）三种运营策略进行了仿真研究。结果表明，在冬季日模拟（1.31 CNY）和月模拟（97.39 CNY）中，大输水分时电价策略的综合成本（综合运行和环境处理成本）最低，体现了大输水分时电价策略在平衡经济和环境绩效方面的优势。在此基础上，提出了一种改进的粒子群优化算法（PSO），避免了局部最优，增强了全局搜索能力，对DA-TOU策略进行了改进。优化后电网总补电量为3.10 kWh，降低9.4%；综合成本为3.33元，降低8.0%。提出的系统和优化的控制框架为提高建筑集成可再生能源系统的经济和环境性能提供了一种可复制的方法，为城市环境中的低碳供暖提供了一条可行的途径。

{"title":"Optimization of a photovoltaic-thermal-dual-source heat pump system using day-ahead forecasting and time-of-use pricing","authors":"Minglu Qu, Junhan Chen, Yusen Bai, Jiajie Chen","doi":"10.1016/j.enbuild.2026.117034","DOIUrl":"10.1016/j.enbuild.2026.117034","url":null,"abstract":"<div><div>Solar energy, as a renewable energy source, offers significant potential in the field of building heating. However, the intermittency and misalignment with grid demand periods limit its effective utilization in building heating applications. Whereas prior investigations have examined either time-of-use (TOU) electricity tariffs or energy forecasting as standalone problems, a research gap persists in synergistically integrating day-ahead forecasts with real-time price signals to co-optimize the operation of integrated photovoltaic-thermal heat pump (PV/T-HP) systems with energy storage. To address this gap, this study proposes a photovoltaic-thermal dual-source heat pump with electricity energy storage (PV/T-DSHP-EES) system, optimized through TOU pricing-based charging and discharging strategies. Three operational strategies, i.e., self-consumption maximization (SCM) strategy, TOU and day-ahead forecasting TOU (DA-TOU), are developed and simulated using TRNSYS and MATLAB for an office building in Shanghai. Results indicate that DA-TOU strategy achieves the lowest comprehensive cost (considering both operational and environmental treatment costs) in both daily (1.31 CNY) and monthly (97.39 CNY) winter simulations, demonstrating its superiority in balancing economic and environmental performance. Furthermore, an enhanced particle swarm optimization (PSO) algorithm, improved to avoid local optima and enhance global search capability, is applied to refine the DA-TOU strategy. This optimization reduced the total grid electricity supplementation by 9.4% to 3.10 kWh and the comprehensive cost by 8.0% to 3.33 CNY. The proposed system and optimized control framework provide a replicable methodology for enhancing the economic and environmental performance of building-integrated renewable energy systems, offering a viable pathway for low-carbon heating in urban environments.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117034"},"PeriodicalIF":7.1,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014910","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}

引用次数: 0

Adaptive thermostat preference learning using behaviour nudging and multi-armed bandits: A field implementation 自适应恒温偏好学习使用行为轻推和多武装强盗：现场实施

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-19 DOI: 10.1016/j.enbuild.2026.117030

Hussein Elehwany , Andre Markus , Burak Gunay , Mohamed Ouf , Nunzio Cotrufo , Jean-Simon Venne , Junfeng Wen

Occupant behaviour (OB) centric controls have significant potential in advancing next-generation HVAC systems. Many OB-centric control studies solicit feedback from occupants to tackle the thermal preference learning problem. Behaviour nudging was also implemented in various systems to influence occupant behaviour to be more energy efficient. This study addresses the gap of using behaviour nudging and unsolicited occupant thermostat overrides to learn their thermal preferences. A multi-armed bandit (MAB) reinforcement learning (RL) was used to learn occupant thermal preferences from their thermostat interactions. The reward signal of the algorithm was designed to reward energy savings and penalize discomfort. The occupants were continuously nudged by slowly reducing the zone setpoint during the heating season, to encourage them to override the thermostats. The algorithm was implemented in two zones with multiple occupants in an academic facility in Ottawa, Canada, achieving energy savings of up to 12.7% compared to static setpoints.

以乘员行为（OB）为中心的控制在推进下一代HVAC系统中具有巨大的潜力。许多以ob为中心的控制研究征求居住者的反馈，以解决热偏好学习问题。在各种系统中也实施了行为推动，以影响乘员的行为，从而提高能源效率。本研究解决了使用行为轻推和未经请求的乘员恒温器覆盖来了解他们的热偏好的差距。使用多臂强盗（MAB）强化学习（RL）从他们的恒温器相互作用中学习乘员的热偏好。该算法的奖励信号被设计为奖励节能和惩罚不适。在供暖季节，通过缓慢降低区域设定值来不断推动居住者，以鼓励他们超越恒温器。该算法在加拿大渥太华的一个学术设施的两个区域中实施，与静态设定值相比，节能高达12.7%。

{"title":"Adaptive thermostat preference learning using behaviour nudging and multi-armed bandits: A field implementation","authors":"Hussein Elehwany , Andre Markus , Burak Gunay , Mohamed Ouf , Nunzio Cotrufo , Jean-Simon Venne , Junfeng Wen","doi":"10.1016/j.enbuild.2026.117030","DOIUrl":"10.1016/j.enbuild.2026.117030","url":null,"abstract":"<div><div>Occupant behaviour (OB) centric controls have significant potential in advancing next-generation HVAC systems. Many OB-centric control studies solicit feedback from occupants to tackle the thermal preference learning problem. Behaviour nudging was also implemented in various systems to influence occupant behaviour to be more energy efficient. This study addresses the gap of using behaviour nudging and unsolicited occupant thermostat overrides to learn their thermal preferences. A multi-armed bandit (MAB) reinforcement learning (RL) was used to learn occupant thermal preferences from their thermostat interactions. The reward signal of the algorithm was designed to reward energy savings and penalize discomfort. The occupants were continuously nudged by slowly reducing the zone setpoint during the heating season, to encourage them to override the thermostats. The algorithm was implemented in two zones with multiple occupants in an academic facility in Ottawa, Canada, achieving energy savings of up to 12.7% compared to static setpoints.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117030"},"PeriodicalIF":7.1,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001008","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}

引用次数: 0

Federated neuro-symbolic rule learning for lightweight smart building operations 轻量级智能建筑操作的联邦神经符号规则学习

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-19 DOI: 10.1016/j.enbuild.2026.117025

Fatimah Faiza Farrukh, Manar Amayri

Smart building automation helps by enhancing occupant comfort, cost-efficiency and reduces energy waste. However, correctly utilizing these benefits depends on accurately understanding occupant behavior, such as occupancy patterns, activities, and appliance usage. But to collect such sensitive data raises serious privacy concerns, such as data leakages and breaches. In addition, deep learning models often require large amounts of data and high computational resources, leading to increased bandwidth usage and processing delays that make sensor-based systems inefficient. To address these challenges, we propose a federated neuro-symbolic rule learning framework that combines privacy-preserving federated learning with explainable symbolic rule generation. The generated rules are lightweight and edge-deployable, and make our framework the first federated neuro-symbolic approach designed for smart building operations. Our method allows clients to collaboratively train a Transformer-based rule generator via reinforcement learning and supervised fine-tuning without sharing raw data. Results showed that our model outperformed both deep and rule-based baselines, achieving up to 25–45% higher test accuracy, while being 2–3 ×  smaller and running in half the time as rule based models such as Apriori and FP-Growth, and about 200 ×  faster and 60 ×  smaller than deep learning baselines. The model also demonstrated strong generalizability by achieving 94.3% test accuracy on unseen data compared to an average of 74.6% for traditional and deep baselines — reflecting approximately 20% improvement in generalization performance on unseen data. The code for the proposed model is available at https://github.com/ffaizaf/FedNSRL

智能楼宇自动化有助于提高居住者的舒适度、成本效益和减少能源浪费。然而，正确利用这些好处取决于准确理解居住者的行为，如使用模式、活动和设备使用情况。但收集如此敏感的数据会引发严重的隐私问题，比如数据泄露和数据泄露。此外，深度学习模型通常需要大量数据和高计算资源，导致带宽使用增加和处理延迟，从而使基于传感器的系统效率低下。为了解决这些挑战，我们提出了一个联邦神经符号规则学习框架，该框架将隐私保护联邦学习与可解释的符号规则生成相结合。生成的规则是轻量级和边缘可部署的，并使我们的框架成为第一个为智能建筑操作设计的联合神经符号方法。我们的方法允许客户通过强化学习和监督微调来协作训练基于transformer的规则生成器，而无需共享原始数据。结果表明，我们的模型优于深度基线和基于规则的基线，测试精度提高了25-45%，同时比基于规则的模型（如Apriori和FP-Growth）小2-3 × ，运行时间缩短了一半，比深度学习基线快200 × ，小60 × 。该模型还显示出强大的泛化能力，在未见数据上达到94.3%的测试准确率，而传统和深度基线的平均准确率为74.6%，反映出在未见数据上的泛化性能提高了约20%。所建议模型的代码可在https://github.com/ffaizaf/FedNSRL上获得

{"title":"Federated neuro-symbolic rule learning for lightweight smart building operations","authors":"Fatimah Faiza Farrukh, Manar Amayri","doi":"10.1016/j.enbuild.2026.117025","DOIUrl":"10.1016/j.enbuild.2026.117025","url":null,"abstract":"<div><div>Smart building automation helps by enhancing occupant comfort, cost-efficiency and reduces energy waste. However, correctly utilizing these benefits depends on accurately understanding occupant behavior, such as occupancy patterns, activities, and appliance usage. But to collect such sensitive data raises serious privacy concerns, such as data leakages and breaches. In addition, deep learning models often require large amounts of data and high computational resources, leading to increased bandwidth usage and processing delays that make sensor-based systems inefficient. To address these challenges, we propose a federated neuro-symbolic rule learning framework that combines privacy-preserving federated learning with explainable symbolic rule generation. The generated rules are lightweight and edge-deployable, and make our framework the first federated neuro-symbolic approach designed for smart building operations. Our method allows clients to collaboratively train a Transformer-based rule generator via reinforcement learning and supervised fine-tuning without sharing raw data. Results showed that our model outperformed both deep and rule-based baselines, achieving up to 25–45% higher test accuracy, while being 2–3 ×  smaller and running in half the time as rule based models such as Apriori and FP-Growth, and about 200 ×  faster and 60 ×  smaller than deep learning baselines. The model also demonstrated strong generalizability by achieving 94.3% test accuracy on unseen data compared to an average of 74.6% for traditional and deep baselines — reflecting approximately 20% improvement in generalization performance on unseen data. The code for the proposed model is available at <span><span>https://github.com/ffaizaf/FedNSRL</span><svg><path></path></svg></span></div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117025"},"PeriodicalIF":7.1,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146000927","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}

引用次数: 0

Quantifying electricity-related carbon emission factors of low-emission neighborhoods: A comparison of different methods 低排放社区用电相关碳排放因子的量化：不同方法的比较

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-19 DOI: 10.1016/j.enbuild.2026.117032

Petry Kristine Nøttum Haaland, Viviane Aubin, Magnus Korpås

Buildings currently account for over 30% of final energy use and 19% of European energy-related greenhouse gas (GHG) emissions, making reductions in this sector highly significant. Zero Emission Buildings (ZEBs) and Zero Emission Neighborhoods (ZENs) have emerged as a potential solution. They aim to achieve net-zero emissions by offsetting embodied emissions through power export from local renewable energy sources (RES), typically solar photovoltaic (PV). While accounting for material-related emissions follows well-established standards, emissions caused by electricity demand remain challenging to quantify. This paper investigates various methods for quantifying emissions linked to energy consumption and local production in a ZEN. We also examine how different time resolutions and geographical scopes impact the final outcomes. We test these calculation approaches on a ZEN case study, exploring how they influence the required investments in local RES. Our results indicate very large variations across emission factor methods and the potential for biases towards specific technologies depending on the methodological choices. In order to ensure that ZENs actually contribute to limiting GHG emissions, we recommend that the approach for calculating emission factors be region-specific and adjustable over time.

目前，建筑占最终能源使用量的30%以上，占欧洲能源相关温室气体（GHG）排放量的19%，因此在这一领域的减排意义重大。零排放建筑（zeb）和零排放社区（ZENs）已经成为潜在的解决方案。他们的目标是通过从当地可再生能源（RES），通常是太阳能光伏（PV）出口电力来抵消隐含排放，从而实现净零排放。虽然材料相关排放的核算遵循既定的标准，但电力需求造成的排放仍然难以量化。本文研究了在ZEN中量化与能源消耗和当地生产相关的排放的各种方法。我们还研究了不同的时间分辨率和地理范围如何影响最终结果。我们在ZEN案例研究中测试了这些计算方法，探讨了它们如何影响当地res所需的投资。我们的结果表明，排放因子方法之间存在很大差异，并且根据方法选择，可能会对特定技术产生偏差。为了确保ZENs确实有助于限制温室气体排放，我们建议计算排放因子的方法应具有区域特异性，并随时间进行调整。

{"title":"Quantifying electricity-related carbon emission factors of low-emission neighborhoods: A comparison of different methods","authors":"Petry Kristine Nøttum Haaland, Viviane Aubin, Magnus Korpås","doi":"10.1016/j.enbuild.2026.117032","DOIUrl":"10.1016/j.enbuild.2026.117032","url":null,"abstract":"<div><div>Buildings currently account for over 30% of final energy use and 19% of European energy-related greenhouse gas (GHG) emissions, making reductions in this sector highly significant. Zero Emission Buildings (ZEBs) and Zero Emission Neighborhoods (ZENs) have emerged as a potential solution. They aim to achieve net-zero emissions by offsetting embodied emissions through power export from local renewable energy sources (RES), typically solar photovoltaic (PV). While accounting for material-related emissions follows well-established standards, emissions caused by electricity demand remain challenging to quantify. This paper investigates various methods for quantifying emissions linked to energy consumption and local production in a ZEN. We also examine how different time resolutions and geographical scopes impact the final outcomes. We test these calculation approaches on a ZEN case study, exploring how they influence the required investments in local RES. Our results indicate very large variations across emission factor methods and the potential for biases towards specific technologies depending on the methodological choices. In order to ensure that ZENs actually contribute to limiting GHG emissions, we recommend that the approach for calculating emission factors be region-specific and adjustable over time.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117032"},"PeriodicalIF":7.1,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001006","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}

引用次数: 0

Optimal operation of dual-source direct-expansion heat pumps under irradiance-temperature coupling 辐照-温度耦合下双源直扩式热泵的优化运行

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-18 DOI: 10.1016/j.enbuild.2026.117028

Linyang Zhang , Yongzhao Yin , Xinran Yu , Jianxiang Guo , Jijin Wang , Yuxing Li , Zhangxing Chen

In the context of the global transformation of the energy structure, the active promotion of energy conservation, emissions reduction, and large-scale deployment of renewable energy has become an inevitable trend. To address the limitations of heating performance exhibited by single-source heat pumps under low-temperature conditions, this study developed a novel dual-mode direct-expansion photovoltaic/Thermal-air source heat pump (PVT-ASHP) system. This system is designed to leverage the complementary advantages of solar and air-source heat pumps in cold climates. Orthogonal experiments were conducted during the heating season in Qingdao, China, to systematically investigate the system’s dynamic performance under coupled variations of solar irradiance and ambient temperature. The results demonstrate that, at irradiance levels exceeding 300 W/m2, the PVT Mode—benefiting from photovoltaic cooling and photo-thermal synergy—achieves an improvement of up to 11.9 % in the comprehensive system performance coefficient (COP_s) relative to the Air-Source Mode. Conversely, under conditions of low irradiance (≤150 W/m2) or relatively high ambient temperatures (≥6 °C), the Air-Source Mode exhibits superior energy efficiency. Utilizing the experimental data, a high-precision linear regression model for predicting COP_s was developed, and an optimal mode-switching boundary equation based on environmental parameters was proposed. The orthogonal experimental design, performance modeling, and boundary analysis methodologies established in this study not only provide an optimized control strategy for the current system but also offer a replicable analytical framework applicable to other climatic zones and multi-source coupled systems. Consequently, this research contributes viable solutions for enhancing the energy efficiency and reliability of renewable energy heating systems in cold regions.

在全球能源结构转型的大背景下，积极推进节能减排，大规模部署可再生能源已成为必然趋势。为了解决单源热泵在低温条件下供热性能的局限性，本研究开发了一种新型的双模直扩式光伏/热空气源热泵（PVT-ASHP）系统。该系统旨在利用太阳能和空气源热泵在寒冷气候下的互补优势。在青岛采暖季进行正交试验，系统研究了太阳辐照度和环境温度耦合变化下系统的动态性能。结果表明，当辐照度超过300 W/m2时，受益于光伏冷却和光热协同作用的PVT模式相对于空气源模式的综合系统性能系数（cop）提高了11.9%。相反，在低辐照度（≤150w /m2）或相对较高的环境温度（≥6℃）下，空气源模式表现出优越的能效。利用实验数据，建立了预测cop的高精度线性回归模型，并提出了基于环境参数的最优模式切换边界方程。本研究建立的正交实验设计、性能建模和边界分析方法不仅为当前系统提供了优化的控制策略，而且为其他气候带和多源耦合系统提供了可复制的分析框架。因此，本研究为提高寒冷地区可再生能源供暖系统的能源效率和可靠性提供了可行的解决方案。

{"title":"Optimal operation of dual-source direct-expansion heat pumps under irradiance-temperature coupling","authors":"Linyang Zhang , Yongzhao Yin , Xinran Yu , Jianxiang Guo , Jijin Wang , Yuxing Li , Zhangxing Chen","doi":"10.1016/j.enbuild.2026.117028","DOIUrl":"10.1016/j.enbuild.2026.117028","url":null,"abstract":"<div><div>In the context of the global transformation of the energy structure, the active promotion of energy conservation, emissions reduction, and large-scale deployment of renewable energy has become an inevitable trend. To address the limitations of heating performance exhibited by single-source heat pumps under low-temperature conditions, this study developed a novel dual-mode direct-expansion photovoltaic/Thermal-air source heat pump (PVT-ASHP) system. This system is designed to leverage the complementary advantages of solar and air-source heat pumps in cold climates. Orthogonal experiments were conducted during the heating season in Qingdao, China, to systematically investigate the system’s dynamic performance under coupled variations of solar irradiance and ambient temperature. The results demonstrate that, at irradiance levels exceeding 300 W/m2, the PVT Mode—benefiting from photovoltaic cooling and photo-thermal synergy—achieves an improvement of up to 11.9 % in the comprehensive system performance coefficient (COP<sub>s</sub>) relative to the Air-Source Mode. Conversely, under conditions of low irradiance (≤150 W/m2) or relatively high ambient temperatures (≥6 °C), the Air-Source Mode exhibits superior energy efficiency. Utilizing the experimental data, a high-precision linear regression model for predicting COP<sub>s</sub> was developed, and an optimal mode-switching boundary equation based on environmental parameters was proposed. The orthogonal experimental design, performance modeling, and boundary analysis methodologies established in this study not only provide an optimized control strategy for the current system but also offer a replicable analytical framework applicable to other climatic zones and multi-source coupled systems. Consequently, this research contributes viable solutions for enhancing the energy efficiency and reliability of renewable energy heating systems in cold regions.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117028"},"PeriodicalIF":7.1,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995554","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}

引用次数: 0

Two-stage MLP-lookup table model for predicting heat pump power in greenhouses 预测温室热泵功率的两阶段mlp查找表模型

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-18 DOI: 10.1016/j.enbuild.2026.117027

Eun Jung Choi , Doyun Lee , Sang Min Lee , Sungil Lim

Energy costs account for a significant proportion of greenhouse operating expenses; thus, high-fidelity predictive tools are increasingly important for optimizing energy consumption. Although machine learning models demonstrate high accuracy within training ranges, their applicability to diverse operational conditions remains limited. This study developed and compared two prediction approaches: a two-stage multilayer perceptron-lookup table (MLP-LUT) model and a standalone multilayer perceptron (s-MLP) model for forecasting electrical heat pumps (EHP) energy consumption. The MLP-LUT model first predicts greenhouse temperature and humidity and then estimates power consumption through manufacturer performance mapping, whereas the s-MLP model directly predicts consumption. Bayesian optimization was used for hyperparameter tuning.

The robust generalization performance of both models underwent evaluation across diverse operating conditions, including variations in the setpoint temperature, location, control strategies, and equipment model. At baseline, both models achieved comparable accuracy, with

C V {(R M S E)}_{h r}

values of 4.05% and 4.04%, respectively, satisfying the American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE) criteria. For generalization testing across various setpoint temperatures, locations, and control strategies, both models retained stable prediction accuracy. However, when the EHP units are replaced, the s-MLP model exhibits severe degradation, whereas the MLP-LUT model maintains

C V {(R M S E)}_{h r}

of less than 4.0%. The MLP-LUT framework offers resilience to hardware substitution by separating environmental predictions from equipment-specific performance mapping. In contrast, the s-MLP approach is constrained to static configurations. The present work establishes practical guidelines for the system selection and provides a foundation for the development of optimal greenhouse control strategies.

能源成本占温室运营费用的很大比例；因此，高保真度预测工具对于优化能源消耗越来越重要。尽管机器学习模型在训练范围内显示出很高的准确性，但它们对不同操作条件的适用性仍然有限。本研究开发并比较了两种预测方法：用于预测电热泵（EHP）能耗的两阶段多层感知器查找表（MLP-LUT）模型和独立多层感知器（s-MLP）模型。MLP-LUT模型首先预测温室温度和湿度，然后通过制造商性能映射估计功耗，而s-MLP模型直接预测功耗。采用贝叶斯优化进行超参数整定。两种模型的鲁棒泛化性能在不同的操作条件下进行了评估，包括设定值温度、位置、控制策略和设备模型的变化。在基线时，两种模型都达到了相当的精度，CVRMSEhr值分别为4.05%和4.04%，满足美国供暖、制冷和空调工程师协会（ASHRAE）的标准。对于各种设定值温度、位置和控制策略的泛化测试，两个模型都保持了稳定的预测精度。然而，当更换EHP单元时，s-MLP模型表现出严重的退化，而MLP-LUT模型保持CVRMSEhr低于4.0%。MLP-LUT框架通过将环境预测与特定于设备的性能映射分离开来，提供了硬件替代的弹性。相比之下，s-MLP方法受限于静态配置。本工作为系统选择建立了实用的指导方针，并为制定最佳温室控制策略提供了基础。

{"title":"Two-stage MLP-lookup table model for predicting heat pump power in greenhouses","authors":"Eun Jung Choi , Doyun Lee , Sang Min Lee , Sungil Lim","doi":"10.1016/j.enbuild.2026.117027","DOIUrl":"10.1016/j.enbuild.2026.117027","url":null,"abstract":"<div><div>Energy costs account for a significant proportion of greenhouse operating expenses; thus, high-fidelity predictive tools are increasingly important for optimizing energy consumption. Although machine learning models demonstrate high accuracy within training ranges, their applicability to diverse operational conditions remains limited. This study developed and compared two prediction approaches: a two-stage multilayer perceptron-lookup table (MLP-LUT) model and a standalone multilayer perceptron (s-MLP) model for forecasting electrical heat pumps (EHP) energy consumption. The MLP-LUT model first predicts greenhouse temperature and humidity and then estimates power consumption through manufacturer performance mapping, whereas the s-MLP model directly predicts consumption. Bayesian optimization was used for hyperparameter tuning.</div><div>The robust generalization performance of both models underwent evaluation across diverse operating conditions, including variations in the setpoint temperature, location, control strategies, and equipment model. At baseline, both models achieved comparable accuracy, with <span><math><mrow><mi>C</mi><mi>V</mi><msub><mrow><mfenced><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></mfenced></mrow><mrow><mi>h</mi><mi>r</mi></mrow></msub></mrow></math></span> values of 4.05% and 4.04%, respectively, satisfying the American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE) criteria. For generalization testing across various setpoint temperatures, locations, and control strategies, both models retained stable prediction accuracy. However, when the EHP units are replaced, the s-MLP model exhibits severe degradation, whereas the MLP-LUT model maintains <span><math><mrow><mi>C</mi><mi>V</mi><msub><mrow><mfenced><mrow><mi>R</mi><mi>M</mi><mi>S</mi><mi>E</mi></mrow></mfenced></mrow><mrow><mi>h</mi><mi>r</mi></mrow></msub></mrow></math></span> of less than 4.0%. The MLP-LUT framework offers resilience to hardware substitution by separating environmental predictions from equipment-specific performance mapping. In contrast, the s-MLP approach is constrained to static configurations. The present work establishes practical guidelines for the system selection and provides a foundation for the development of optimal greenhouse control strategies.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117027"},"PeriodicalIF":7.1,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995556","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}

引用次数: 0

Indoor thermal comfort and energy–saving opportunities in university classrooms: a field study across heating and cooling seasons 大学教室的室内热舒适和节能机会：跨供暖和制冷季节的实地研究

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-18 DOI: 10.1016/j.enbuild.2026.117005

Qiong He, Lu Han, Yayun Gan

Classroom thermal comfort is often compromised by a lack of localized data, leading to excessive cooling in summer and overheating in winter, resulting in huge energy waste. To meet students’ real thermal comfort needs and achieve the goal of energy saving in university classrooms, this study monitored the indoor thermal parameters in 35 different types of university classrooms and collected 1618 valid questionnaires in energy-consuming seasons in Nanjing with hot summer and cold winter climate. Key findings are as follows:(1) 77.8% and 12% of classrooms have above 60% humidity in summer and winter but the percentage of votes on “normal humidity” in these investigated classrooms is 67% and 68% in the same seasons, implying that most students generally prefer a more humid indoor environment in the area. (2) The gaps between

T_{n}

and

T_{p}

in summer and winter are 2.62°C and 2.0556°C, respectively, indicating that increase and decrease in classroom temperature can still ensure thermal comfort during summer and winter, respectively (3) Applying thermal comfort parameters

T_{p}

,

T_{n}

,

T_{A}^{s}

,

T_{A}^{a}

to maintain indoor environments can significantly reduce energy consumption based on values (19°C-25°C in winter and 22°C-26°C in summer) suggested by standards: the maximum energy savings can reach 4.5%, 13.7%, 15% and 18.1% in summer but up to 24.6%, 31.4%, 33.5% and 33.7% in winter, respectively. Thus, maintaining indoor thermal comfort according to real local demands rather than general specifications has great potential to save energy in university classrooms in Nanjing.

由于缺乏本地化数据，教室的热舒适往往受到影响，导致夏季过度冷却，冬季过热，造成巨大的能源浪费。为了满足学生的真实热舒适需求，实现高校教室节能的目标，本研究在夏热冬冷气候的南京地区，对35个不同类型的高校教室的室内热参数进行了监测，收集了1618份有效问卷。主要研究结果如下：(1)在夏季和冬季，77.8%和12%的教室湿度在60%以上，但在同一季节，被调查教室中“正常湿度”的投票比例分别为67%和68%，这意味着大多数学生普遍倾向于该地区更潮湿的室内环境。(2)夏季和冬季Tn与Tp的差值分别为2.62°C和2.0556°C，表明提高和降低教室温度在夏季和冬季仍能保证热舒适。(3)根据标准建议的值（冬季19°C-25°C，夏季22°C-26°C），应用热舒适参数Tp、Tn、TAs、TAa来维持室内环境，可显著降低能耗：夏季节能最高可达4.5%、13.7%、15%和18.1%，冬季节能最高可达24.6%、31.4%、33.5%和33.7%。因此，根据当地的实际需求而不是一般规格来保持室内热舒适，在南京大学教室节能方面具有很大的潜力。

{"title":"Indoor thermal comfort and energy–saving opportunities in university classrooms: a field study across heating and cooling seasons","authors":"Qiong He, Lu Han, Yayun Gan","doi":"10.1016/j.enbuild.2026.117005","DOIUrl":"10.1016/j.enbuild.2026.117005","url":null,"abstract":"<div><div>Classroom thermal comfort is often compromised by a lack of localized data, leading to excessive cooling in summer and overheating in winter, resulting in huge energy waste. To meet students’ real thermal comfort needs and achieve the goal of energy saving in university classrooms, this study monitored the indoor thermal parameters in 35 different types of university classrooms and collected 1618 valid questionnaires in energy-consuming seasons in Nanjing with hot summer and cold winter climate. Key findings are as follows:(1) 77.8% and 12% of classrooms have above 60% humidity in summer and winter but the percentage of votes on “normal humidity” in these investigated classrooms is 67% and 68% in the same seasons, implying that most students generally prefer a more humid indoor environment in the area. (2) The gaps between <span><math><mrow><msub><mi>T</mi><mi>n</mi></msub></mrow></math></span> and <span><math><mrow><msub><mi>T</mi><mi>p</mi></msub></mrow></math></span> in summer and winter are 2.62°C and 2.0556°C, respectively, indicating that increase and decrease in classroom temperature can still ensure thermal comfort during summer and winter, respectively (3) Applying thermal comfort parameters <span><math><mrow><msub><mi>T</mi><mi>p</mi></msub></mrow></math></span>, <span><math><mrow><msub><mi>T</mi><mi>n</mi></msub></mrow></math></span>, <span><math><mrow><msubsup><mi>T</mi><mrow><mi>A</mi></mrow><mi>s</mi></msubsup></mrow></math></span> , <span><math><mrow><msubsup><mi>T</mi><mrow><mi>A</mi></mrow><mi>a</mi></msubsup></mrow></math></span> to maintain indoor environments can significantly reduce energy consumption based on values (19°C-25°C in winter and 22°C-26°C in summer) suggested by standards: the maximum energy savings can reach 4.5%, 13.7%, 15% and 18.1% in summer but up to 24.6%, 31.4%, 33.5% and 33.7% in winter, respectively. Thus, maintaining indoor thermal comfort according to real local demands rather than general specifications has great potential to save energy in university classrooms in Nanjing.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117005"},"PeriodicalIF":7.1,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995553","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}

引用次数: 0

A non-intrusive load monitoring method for commercial buildings based on time-series periodicity adaptive fusion 基于时间序列周期自适应融合的商业建筑非侵入式负荷监测方法

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-18 DOI: 10.1016/j.enbuild.2026.117031

Xiaojie Lin , Ziyu Yang , Xueru Lin , Wei Zhong , Hong Zhang

Without the need for additional sensor installation, non-intrusive load monitoring (NILM) enables device-level energy consumption awareness and management by analyzing aggregate smart meter data. In commercial building environments, however, the simultaneous occurrence of transient events from multiple similar devices often leads to overlapping electrical signatures, which complicates load identification and increases monitoring difficulty. To address these challenges, this study proposes a NILM method based on a time-series modeling framework. By transforming one-dimensional power data into two-dimensional representations, the model captures both intra-period and inter-period variations. It integrates a frequency-domain periodicity extraction module, a multi-scale feature enhancement module based on the Inception architecture, and an adaptive fusion mechanism to jointly learn structured temporal patterns. Experimental results demonstrate that the proposed method outperforms conventional deep learning models, including LSTM, GRU, IndRNN, Transformer, Informer, and TTRNet, in both classification and energy disaggregation tasks. It achieves improvements of 1.91% in Precision, 5.86% in Recall, 3.7% in F1-score, 2.82% in Accuracy, and 5.47% in Matthews Correlation Coefficient (MCC), while maintaining high performance under diverse and irregular load conditions. In addition, an interpretability framework assigns weights to key time–frequency features, providing transparent and explainable monitoring results.

无需额外安装传感器，非侵入式负载监控（NILM）可以通过分析智能电表的汇总数据，实现设备级能耗感知和管理。然而，在商业建筑环境中，多个类似设备同时发生的瞬态事件往往导致电气特征重叠，这使得负载识别复杂化，增加了监测难度。为了解决这些挑战，本研究提出了一种基于时间序列建模框架的NILM方法。通过将一维功率数据转换为二维表示，该模型捕获了周期内和周期间的变化。它集成了频域周期性提取模块、基于Inception架构的多尺度特征增强模块和自适应融合机制，共同学习结构化时间模式。实验结果表明，该方法在分类和能量分解任务上都优于传统的深度学习模型，包括LSTM、GRU、IndRNN、Transformer、Informer和trnet。精度提高1.91%，召回率提高5.86%，f1得分提高3.7%，准确率提高2.82%，马修斯相关系数（MCC）提高5.47%，同时在不同和不规则负载条件下保持较高的性能。此外，可解释性框架为关键时频特征分配权重，提供透明和可解释的监测结果。

{"title":"A non-intrusive load monitoring method for commercial buildings based on time-series periodicity adaptive fusion","authors":"Xiaojie Lin , Ziyu Yang , Xueru Lin , Wei Zhong , Hong Zhang","doi":"10.1016/j.enbuild.2026.117031","DOIUrl":"10.1016/j.enbuild.2026.117031","url":null,"abstract":"<div><div>Without the need for additional sensor installation, non-intrusive load monitoring (NILM) enables device-level energy consumption awareness and management by analyzing aggregate smart meter data. In commercial building environments, however, the simultaneous occurrence of transient events from multiple similar devices often leads to overlapping electrical signatures, which complicates load identification and increases monitoring difficulty. To address these challenges, this study proposes a NILM method based on a time-series modeling framework. By transforming one-dimensional power data into two-dimensional representations, the model captures both intra-period and inter-period variations. It integrates a frequency-domain periodicity extraction module, a multi-scale feature enhancement module based on the Inception architecture, and an adaptive fusion mechanism to jointly learn structured temporal patterns. Experimental results demonstrate that the proposed method outperforms conventional deep learning models, including LSTM, GRU, IndRNN, Transformer, Informer, and TTRNet, in both classification and energy disaggregation tasks. It achieves improvements of 1.91% in Precision, 5.86% in Recall, 3.7% in F1-score, 2.82% in Accuracy, and 5.47% in Matthews Correlation Coefficient (MCC), while maintaining high performance under diverse and irregular load conditions. In addition, an interpretability framework assigns weights to key time–frequency features, providing transparent and explainable monitoring results.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"354 ","pages":"Article 117031"},"PeriodicalIF":7.1,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995552","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}

引用次数: 0

A data-driven approach to identifying cost-effective retrofits, predicting energy ratings, and evaluating national retrofit CO2 savings in UK homes 一种数据驱动的方法，以确定具有成本效益的改造，预测能源评级，并评估英国家庭的全国改造二氧化碳节约

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-18 DOI: 10.1016/j.enbuild.2026.117029

Rinku Mohan , Farrukh Saleem , Turki Althaqafi , Nahla J. Abid

Energy efficiency is an important factor contributing to the sustainability and for reducing energy costs. There has been an increasing attention in residential energy performance, but detailed studies exploring cost-effectiveness analysis, predictive modelling, and adoption modelling are still lacking. This study addresses these issues by analysing a large Energy Performance Certificate (EPC) dataset in the UK in 2024, having over 4.8 million property records. The research explores retrofit costs and impact data to investigate three critical research questions. First, we evaluated the energy efficiency and CO₂ savings per pound spent across different property types in the UK, analysing 41 retrofit improvement types using statistical analysis. Second, machine learning models were trained to predict a building’s energy rating from its efficiency and structural traits. Third, standard retrofit interventions were assessed for defining the actual CO₂ savings by integrating retrofit adoption probabilities and Monte Carlo simulations. Our results show that the highest energy efficiency per pound spent could be achieved with inexpensive improvements like low-energy lighting, installing hot water cylinders and draught proofing. The Voting Classifier model (XGB + RF) achieved the best discrimination with 70.8% outperforming XGBoost (69.4%), Random Forest (69.09%), and MLP Neural Network (59.5%). The simulations based on different adoption scenarios demonstrate that even a small increase in the adoption rates can lead to significant national CO₂ reductions. Overall, this study provides a transferable methodology that combines cost-effectiveness analysis, predictive analysis, and retrofit adoption modelling for sustainable housing research in the UK. The findings offer insightful applicability to guide retrofit priority, policy targeting, and future studies in sustainable residential energy planning.

能源效率是促进可持续性和降低能源成本的一个重要因素。人们对住宅能源性能的关注越来越多，但对成本效益分析、预测模型和采用模型的详细研究仍然缺乏。本研究通过分析2024年英国的大型能源绩效证书（EPC）数据集来解决这些问题，该数据集拥有超过480万条财产记录。该研究探讨了改造成本和影响数据，以调查三个关键的研究问题。首先，我们评估了英国不同房地产类型的能源效率和每磅二氧化碳的节省，使用统计分析分析了41种改造改进类型。其次，机器学习模型经过训练，可以根据建筑物的效率和结构特征预测建筑物的能源等级。第三，通过整合改造采用概率和蒙特卡洛模拟，评估了标准改造干预措施，以确定实际的二氧化碳节约。我们的研究结果表明，每磅消耗的最高能源效率可以通过低成本的改进来实现，比如低能耗照明、安装热水缸和防风。投票分类器模型（XGB + RF）的识别率为70.8%，优于XGBoost（69.4%）、Random Forest（69.09%）和MLP Neural Network（59.5%）。基于不同采用情景的模拟表明，即使采用率的小幅增加也能导致国家二氧化碳的显著减少。总体而言，本研究为英国的可持续住房研究提供了一种可转移的方法，该方法结合了成本效益分析、预测分析和改造采用模型。研究结果为指导可持续住宅能源规划的改造优先级、政策目标和未来研究提供了深刻的适用性。

{"title":"A data-driven approach to identifying cost-effective retrofits, predicting energy ratings, and evaluating national retrofit CO2 savings in UK homes","authors":"Rinku Mohan , Farrukh Saleem , Turki Althaqafi , Nahla J. Abid","doi":"10.1016/j.enbuild.2026.117029","DOIUrl":"10.1016/j.enbuild.2026.117029","url":null,"abstract":"<div><div>Energy efficiency is an important factor contributing to the sustainability and for reducing energy costs. There has been an increasing attention in residential energy performance, but detailed studies exploring cost-effectiveness analysis, predictive modelling, and adoption modelling are still lacking. This study addresses these issues by analysing a large Energy Performance Certificate (EPC) dataset in the UK in 2024, having over 4.8 million property records. The research explores retrofit costs and impact data to investigate three critical research questions. First, we evaluated the energy efficiency and CO<sub>2</sub> savings per pound spent across different property types in the UK, analysing 41 retrofit improvement types using statistical analysis. Second, machine learning models were trained to predict a building’s energy rating from its efficiency and structural traits. Third, standard retrofit interventions were assessed for defining the actual CO<sub>2</sub> savings by integrating retrofit adoption probabilities and Monte Carlo simulations. Our results show that the highest energy efficiency per pound spent could be achieved with inexpensive improvements like low-energy lighting, installing hot water cylinders and draught proofing. The Voting Classifier model (XGB + RF) achieved the best discrimination with 70.8% outperforming XGBoost (69.4%), Random Forest (69.09%), and MLP Neural Network (59.5%). The simulations based on different adoption scenarios demonstrate that even a small increase in the adoption rates can lead to significant national CO<sub>2</sub> reductions. Overall, this study provides a transferable methodology that combines cost-effectiveness analysis, predictive analysis, and retrofit adoption modelling for sustainable housing research in the UK. The findings offer insightful applicability to guide retrofit priority, policy targeting, and future studies in sustainable residential energy planning.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117029"},"PeriodicalIF":7.1,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995555","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}

引用次数: 0

Optimal ventilation systems via MILP: Duct sizing, fan placement, control strategies 通过MILP优化通风系统：管道尺寸，风扇放置，控制策略

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-01-17 DOI: 10.1016/j.enbuild.2026.117016

Julius H.P. Breuer, Peter F. Pelz

Ventilation systems in buildings account for a substantial share of overall energy consumption, with fans representing one of the largest contributors. Improving energy efficiency requires considering the interaction of system components. Novel topologies, such as distributed fans integrated into the central duct network, offer promising potential for efficiency gains. At the same time, building owners demand cost-effective solutions, which depend strongly on a well-designed duct network. Meeting these requirements calls for a life-cycle-oriented planning approach with integrated component selection and duct sizing. Existing planning algorithms, however, have several limitations: they often assume single load cases, rely on overly simplified fan models, neglect novel, distributed topologies, and lack guarantees of global optimality. This paper addresses these shortcomings by presenting a novel optimisation problem formulation that jointly considers topological decisions (e.g., fan and volume flow controller placement, duct sizing) and system operation under multiple load cases. The methodology enables systematic comparison of control strategies, duct limitations – in velocity and height – and analysis of cost-energy trade-offs. To reduce computation times, the non-linear optimisation problem is relaxed to a Mixed-Integer Linear Program (MILP), with proven error bounds that quantify the distance to the global optimum. The methodology is demonstrated on a case study building, showing 14 % reduced LCC compared to the existing system. Six different central or distributed control strategies and duct constraints are optimised within seconds of computation time. This makes the method suitable for practical planning processes, providing transparent decision support, e.g. through Pareto front analyses.

建筑物的通风系统占总能耗的很大一部分，风扇是最大的贡献者之一。提高能源效率需要考虑系统组件的相互作用。新颖的拓扑结构，如集成到中央管道网络中的分布式风扇，为提高效率提供了有希望的潜力。同时，建筑业主需要具有成本效益的解决方案，这在很大程度上取决于设计良好的管道网络。为了满足这些要求，需要采用一种面向生命周期的规划方法，包括集成组件选择和管道尺寸。然而，现有的规划算法有一些局限性：它们通常假设单负载情况，依赖于过于简化的风扇模型，忽视新颖的分布式拓扑结构，并且缺乏全局最优性的保证。本文通过提出一种新的优化问题公式来解决这些缺点，该公式联合考虑了拓扑决策（例如，风扇和容积流量控制器的放置，管道尺寸）和系统在多种负载情况下的运行。该方法可以系统地比较控制策略、管道限制（速度和高度）以及成本-能源权衡分析。为了减少计算时间，非线性优化问题被简化为一个混合整数线性规划（MILP），用已证明的误差界限来量化到全局最优的距离。该方法在一个案例研究中进行了演示，与现有系统相比，LCC降低了14%。六种不同的中央或分布式控制策略和管道约束在几秒钟的计算时间内进行优化。这使得该方法适用于实际的规划过程，提供透明的决策支持，例如通过帕累托前沿分析。

{"title":"Optimal ventilation systems via MILP: Duct sizing, fan placement, control strategies","authors":"Julius H.P. Breuer, Peter F. Pelz","doi":"10.1016/j.enbuild.2026.117016","DOIUrl":"10.1016/j.enbuild.2026.117016","url":null,"abstract":"<div><div>Ventilation systems in buildings account for a substantial share of overall energy consumption, with fans representing one of the largest contributors. Improving energy efficiency requires considering the interaction of system components. Novel topologies, such as distributed fans integrated into the central duct network, offer promising potential for efficiency gains. At the same time, building owners demand cost-effective solutions, which depend strongly on a well-designed duct network. Meeting these requirements calls for a life-cycle-oriented planning approach with integrated component selection and duct sizing. Existing planning algorithms, however, have several limitations: they often assume single load cases, rely on overly simplified fan models, neglect novel, distributed topologies, and lack guarantees of global optimality. This paper addresses these shortcomings by presenting a novel optimisation problem formulation that jointly considers topological decisions (e.g., fan and volume flow controller placement, duct sizing) and system operation under multiple load cases. The methodology enables systematic comparison of control strategies, duct limitations – in velocity and height – and analysis of cost-energy trade-offs. To reduce computation times, the non-linear optimisation problem is relaxed to a Mixed-Integer Linear Program (MILP), with proven error bounds that quantify the distance to the global optimum. The methodology is demonstrated on a case study building, showing 14 % reduced LCC compared to the existing system. Six different central or distributed control strategies and duct constraints are optimised within seconds of computation time. This makes the method suitable for practical planning processes, providing transparent decision support, e.g. through Pareto front analyses.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"355 ","pages":"Article 117016"},"PeriodicalIF":7.1,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995564","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}

引用次数: 0