Applied Energy最新文献_第4页

Comparative analyses of recuperator integration in PEMFC air systems PEMFC空气系统中回热器集成的比较分析

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127219

Rakibul Hassan , Evan M. Reich , Brian Costello , James E. McCarthy Jr. , Riley B. Barta

Meeting stringent carbon reduction goals in the commercial transport sector requires the rapid deployment of zero-emission solutions such as hydrogen fuel cell-powered heavy-duty vehicles. While proton exchange membrane fuel cells (PEMFCs) have demonstrated their viability in this context, significant parasitic losses in the air supply subsystem remain a barrier to further gains in overall system efficiency. The integration of a recuperator presents a substantial opportunity for improvement by enhancing expander energy recovery, thus reducing the net power consumption of the air supply system. This study systematically evaluates the impact of recuperator integration on heavy-duty vehicle PEMFC air system performance. Conceptual modeling and multiobjective optimization of two recuperator types—chevron-type plate heat exchanger and plate fin heat exchanger with offset strip fins—have been performed, using the non-dominated sorting genetic algorithm-II, to minimize pressure drop and maximize effectiveness under a predefined volume constraint. A steady-state model of an air system has been assessed under three distinct load conditions, integrating six optimized recuperator designs, along with one off-the-shelf, experimentally tested shell-and-tube unit. The results demonstrate potential for air system efficiency improvement through recuperator integration, particularly under high-pressure operating conditions. Among all evaluated configurations, one of the optimized plate fin heat exchanger designs achieves the greatest reduction in system power consumption, offering up to 5.29 % improvement at full load. Beyond confirming the efficiency benefits of recuperator integration, the findings underline the essential role of system-specific design optimization in realizing the full benefits of such integration.

为了实现商业运输领域严格的碳减排目标，需要快速部署零排放解决方案，如氢燃料电池驱动的重型车辆。虽然质子交换膜燃料电池（pemfc）已经证明了其在这种情况下的可行性，但空气供应子系统中显著的寄生损失仍然是进一步提高整体系统效率的障碍。通过提高膨胀器的能量回收，从而降低空气供应系统的净功率消耗，再生器的集成提供了大量的改进机会。本研究系统地评估了蓄热器集成对重型汽车PEMFC空气系统性能的影响。利用非支配排序遗传算法ii，对两种类型的换热器（线形板式换热器和带偏置条形翅片的板式换热器）进行了概念建模和多目标优化，在预先设定的体积约束下，实现了压降最小化和效率最大化。在三种不同的负载条件下，对空气系统的稳态模型进行了评估，该模型集成了六种优化的回热器设计，以及一种现成的、经过实验测试的管壳式装置。结果表明，通过集成回热器可以提高空气系统的效率，特别是在高压操作条件下。在所有评估的配置中，优化的板翅式换热器设计之一实现了最大的系统功耗降低，在满负荷时提供高达5.29%的改进。除了确认回热器集成的效率效益外，研究结果还强调了系统特定设计优化在实现这种集成的全部效益方面的重要作用。

{"title":"Comparative analyses of recuperator integration in PEMFC air systems","authors":"Rakibul Hassan , Evan M. Reich , Brian Costello , James E. McCarthy Jr. , Riley B. Barta","doi":"10.1016/j.apenergy.2025.127219","DOIUrl":"10.1016/j.apenergy.2025.127219","url":null,"abstract":"<div><div>Meeting stringent carbon reduction goals in the commercial transport sector requires the rapid deployment of zero-emission solutions such as hydrogen fuel cell-powered heavy-duty vehicles. While proton exchange membrane fuel cells (PEMFCs) have demonstrated their viability in this context, significant parasitic losses in the air supply subsystem remain a barrier to further gains in overall system efficiency. The integration of a recuperator presents a substantial opportunity for improvement by enhancing expander energy recovery, thus reducing the net power consumption of the air supply system. This study systematically evaluates the impact of recuperator integration on heavy-duty vehicle PEMFC air system performance. Conceptual modeling and multiobjective optimization of two recuperator types—chevron-type plate heat exchanger and plate fin heat exchanger with offset strip fins—have been performed, using the non-dominated sorting genetic algorithm-II, to minimize pressure drop and maximize effectiveness under a predefined volume constraint. A steady-state model of an air system has been assessed under three distinct load conditions, integrating six optimized recuperator designs, along with one off-the-shelf, experimentally tested shell-and-tube unit. The results demonstrate potential for air system efficiency improvement through recuperator integration, particularly under high-pressure operating conditions. Among all evaluated configurations, one of the optimized plate fin heat exchanger designs achieves the greatest reduction in system power consumption, offering up to 5.29 % improvement at full load. Beyond confirming the efficiency benefits of recuperator integration, the findings underline the essential role of system-specific design optimization in realizing the full benefits of such integration.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127219"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Accurate urban solar potential estimation empowered by multimodal 3-D building reconstruction: a case study in Landshut, Germany 基于多模式三维建筑重建的精确城市太阳能潜力估算：以德国兰茨胡特为例

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127231

Yajin Xu , Juilson Jubanski , Ksenia Bittner , Florian Siegert

Solar potential analysis is crucial in decision-making to fight against climate change. In the literature, it still remains a difficult task to calculate rooftop solar potential in complex urban areas, primarily due to the lack of precise building models. To address this issue, a novel workflow is proposed to first extract high-fidelity 3-D building models and then accurately estimate solar potential on buildings. A multimodal neural network is proposed to reconstruct detailed 3-D building models while leveraging data fusion of RGB images, digital surface models, and point clouds. Subsequently, the reconstructed buildings are used to estimate incoming solar insolation and to obtain detailed solar panel configurations. Building-scale potential direct current (DC) outputs are calculated using the estimated solar insolation and panel configurations. Comprehensive experiments and evaluations demonstrate the superiority of the proposed pipeline. Compared to other publicly available sources, the proposed method minimized the estimation errors – compared to manual annotations – of solar insolation and solar potential by a large margin. In the study area of Landshut in Germany, the residual of estimated solar insolation was reduced from 123.15 kWh/m² to 52.36 kWh/m², corresponding to an improvement of over 50 %. For the estimated total DC output originating from solar energy, a substantially lower error of 24.93 MWh was achieved, outperforming the baseline residual of 78.16 MWh. Through uncertainty and sensitivity analysis using Monte-Carlo simulations, the introduced method is proven to be statistically robust and produces reliable and realistic results that can be integrated into real-world practices. Finally, the potential alternating current output of Landshut was estimated to be approximately 370.05 GWh according to the conducted sensitivity analysis.

太阳能潜力分析对应对气候变化的决策至关重要。在文献中，由于缺乏精确的建筑模型，在复杂的城市地区计算屋顶太阳能潜力仍然是一项艰巨的任务。为了解决这一问题，提出了一种新的工作流程，首先提取高保真的三维建筑模型，然后准确估计建筑物的太阳能潜力。提出了一种多模态神经网络，利用RGB图像、数字表面模型和点云的数据融合来重建详细的三维建筑模型。随后，重建的建筑被用来估计入射的太阳日照量，并获得详细的太阳能电池板配置。建筑规模的潜在直流电（DC）输出是使用估计的太阳日照和面板配置来计算的。综合实验和评价表明了该管道的优越性。与其他公开可用的资源相比，所提出的方法将太阳日晒和太阳能潜力的估计误差（与人工注释相比）降到最低。在德国兰茨胡特的研究区，估计太阳辐照的剩余量从123.15 kWh/m2减少到52.36 kWh/m2，相当于提高了50%以上。对于估计的来自太阳能的直流总输出，实现了24.93 MWh的低得多的误差，优于基线残差78.16 MWh。通过蒙特卡罗模拟的不确定性和敏感性分析，证明了所引入的方法具有统计稳健性，并产生了可靠和真实的结果，可以与现实世界的实践相结合。最后，根据所进行的灵敏度分析，估计Landshut的潜在交流输出约为370.05 GWh。

{"title":"Accurate urban solar potential estimation empowered by multimodal 3-D building reconstruction: a case study in Landshut, Germany","authors":"Yajin Xu , Juilson Jubanski , Ksenia Bittner , Florian Siegert","doi":"10.1016/j.apenergy.2025.127231","DOIUrl":"10.1016/j.apenergy.2025.127231","url":null,"abstract":"<div><div>Solar potential analysis is crucial in decision-making to fight against climate change. In the literature, it still remains a difficult task to calculate rooftop solar potential in complex urban areas, primarily due to the lack of precise building models. To address this issue, a novel workflow is proposed to first extract high-fidelity 3-D building models and then accurately estimate solar potential on buildings. A multimodal neural network is proposed to reconstruct detailed 3-D building models while leveraging data fusion of RGB images, digital surface models, and point clouds. Subsequently, the reconstructed buildings are used to estimate incoming solar insolation and to obtain detailed solar panel configurations. Building-scale potential direct current (DC) outputs are calculated using the estimated solar insolation and panel configurations. Comprehensive experiments and evaluations demonstrate the superiority of the proposed pipeline. Compared to other publicly available sources, the proposed method minimized the estimation errors – compared to manual annotations – of solar insolation and solar potential by a large margin. In the study area of Landshut in Germany, the residual of estimated solar insolation was reduced from 123.15 kWh/m<sup>2</sup> to 52.36 kWh/m<sup>2</sup>, corresponding to an improvement of over 50 %. For the estimated total DC output originating from solar energy, a substantially lower error of 24.93 MWh was achieved, outperforming the baseline residual of 78.16 MWh. Through uncertainty and sensitivity analysis using Monte-Carlo simulations, the introduced method is proven to be statistically robust and produces reliable and realistic results that can be integrated into real-world practices. Finally, the potential alternating current output of Landshut was estimated to be approximately 370.05 GWh according to the conducted sensitivity analysis.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127231"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Multi-objective stochastic optimization problem: a systematic literature review 多目标随机优化问题：系统的文献综述

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127237

Behzad Pirouz, Francesca Guerriero

In recent years, researchers have widely applied multi-objective stochastic optimization problems (MOSOPs) to decision-making problems involving conflicting objectives under different uncertainties. This study presents a systematic literature review and bibliometric analysis of MOSOP research published between 2018 and 2025, based on 572 published papers indexed in the Scopus database. Through keyword analysis, five main research areas are identified: energy, sustainability, management, engineering, and other fields. This classification represents the main areas where MOSOP has been applied to address uncertainty and trade-offs in real-world systems. The strongest methodological and practical relevance of MOSOP appears in energy systems and closely related sustainability applications. Accordingly, these two domains receive particular emphasis throughout this review. High-impact publications are analyzed to explore application areas, stochastic sources, objective functions, system constraints, and solution algorithms. Overall, the findings highlight that MOSOP related to energy systems represents the most mature and fastest-growing research direction within the literature reviewed. Additionally, the results indicate increased use of MOSOP in renewable energy, energy storage systems, sustainable transportation, electric vehicles, and transportation logistics. Despite its many advantages, there are still gaps in modeling stochastic and conflicting objectives, in advanced solution algorithms, and in interdisciplinary applications of MOSOP. This literature review provides a structured overview of MOSOP literature, highlights research trends and methods, and identifies opportunities for future work to address real-world stochastic optimization challenges.

近年来，研究人员将多目标随机优化问题（MOSOPs）广泛应用于不同不确定性条件下目标冲突的决策问题。本研究基于Scopus数据库中收录的572篇已发表论文，对2018年至2025年间发表的MOSOP研究进行了系统的文献综述和文献计量分析。通过关键词分析，确定了五个主要研究领域：能源、可持续发展、管理、工程和其他领域。这种分类代表了MOSOP应用于解决现实世界系统中的不确定性和权衡的主要领域。在能源系统和密切相关的可持续性应用中，MOSOP的方法论和实践相关性最强。因此，这两个领域在整个审查中得到特别强调。分析高影响力的出版物，探索应用领域，随机来源，目标函数，系统约束和解决算法。总体而言，研究结果表明，与能源系统相关的MOSOP是文献综述中最成熟和发展最快的研究方向。此外，研究结果还表明，MOSOP在可再生能源、储能系统、可持续交通、电动汽车和交通物流领域的使用有所增加。尽管它有许多优点，但在随机和冲突目标建模、高级求解算法以及MOSOP的跨学科应用方面仍存在差距。本文献综述提供了MOSOP文献的结构化概述，突出了研究趋势和方法，并确定了未来工作解决现实世界随机优化挑战的机会。

{"title":"Multi-objective stochastic optimization problem: a systematic literature review","authors":"Behzad Pirouz, Francesca Guerriero","doi":"10.1016/j.apenergy.2025.127237","DOIUrl":"10.1016/j.apenergy.2025.127237","url":null,"abstract":"<div><div>In recent years, researchers have widely applied multi-objective stochastic optimization problems (MOSOPs) to decision-making problems involving conflicting objectives under different uncertainties. This study presents a systematic literature review and bibliometric analysis of MOSOP research published between 2018 and 2025, based on 572 published papers indexed in the Scopus database. Through keyword analysis, five main research areas are identified: energy, sustainability, management, engineering, and other fields. This classification represents the main areas where MOSOP has been applied to address uncertainty and trade-offs in real-world systems. The strongest methodological and practical relevance of MOSOP appears in energy systems and closely related sustainability applications. Accordingly, these two domains receive particular emphasis throughout this review. High-impact publications are analyzed to explore application areas, stochastic sources, objective functions, system constraints, and solution algorithms. Overall, the findings highlight that MOSOP related to energy systems represents the most mature and fastest-growing research direction within the literature reviewed. Additionally, the results indicate increased use of MOSOP in renewable energy, energy storage systems, sustainable transportation, electric vehicles, and transportation logistics. Despite its many advantages, there are still gaps in modeling stochastic and conflicting objectives, in advanced solution algorithms, and in interdisciplinary applications of MOSOP. This literature review provides a structured overview of MOSOP literature, highlights research trends and methods, and identifies opportunities for future work to address real-world stochastic optimization challenges.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127237"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Learning-to-optimize infused decentralized disaggregation for multi-entity technical VPP considering equity and privacy 考虑公平和隐私的多实体技术VPP的学习优化注入分散分解

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127226

Qihui Wang, Zhengshuo Li

The growing renewable energy integration challenges grid stability, highlighting demand response as a critical solution. 5G base stations emerge as a valuable demand-side response resource due to their inherent flexibility potential. Virtual Power Plants, especially Technical VPPs (TVPPs), play a crucial role in effectively aggregating these base stations and other resources to enhance grid flexibility. However, TVPPs encounter significant obstacles in achieving rapid disaggregation, concerning real-time requirements, energy equity and privacy security. This paper presents a novel instruction disaggregation algorithm addressing these issues through a decentralized coordination mechanism. Firstly, a multi-entity TVPP instruction disaggregation model is established by incorporating both grid security and energy equity, and distinct in considering energy equity regarding the disaggregation process. Then, a decentralized disaggregation method based on learning-to-optimize is proposed where self-supervised learning is embedded to train surrogate models so that the computational time due to traditional optimization can be significantly reduced. Moreover, a lightweight privacy-preserving scheme is integrated to avoid privacy breaches without introducing excessive computational burdens. Finally, theoretical guarantees for the proposed algorithm are established, including solution quasi-feasibility, convergence and generalization properties. Case studies show that the proposed method significantly decreases computational demands, achieving speedup ratios of two orders of magnitude compared to the traditional decentralized method while ensuring privacy security.

不断增长的可再生能源整合挑战了电网的稳定性，需求响应成为关键的解决方案。5G基站因其固有的灵活性潜力而成为宝贵的需求侧响应资源。虚拟电厂，特别是技术虚拟电厂（tvpp），在有效聚合这些基站和其他资源以增强电网灵活性方面发挥着至关重要的作用。然而，tvpp在实现快速分解方面遇到了重大障碍，涉及实时需求、能源公平和隐私安全。本文提出了一种新的指令分解算法，通过分散的协调机制来解决这些问题。首先，将电网安全与能量公平性相结合，建立了多实体TVPP指令分解模型，并在分解过程中明确考虑了能量公平性；然后，提出了一种基于学习优化的分散解聚方法，该方法嵌入自监督学习来训练代理模型，从而大大减少了传统优化带来的计算时间。此外，还集成了一种轻量级的隐私保护方案，在不引入过多计算负担的情况下避免隐私泄露。最后，给出了算法的理论保证，包括解的拟可行性、收敛性和泛化性。案例研究表明，与传统的去中心化方法相比，该方法显著降低了计算需求，在保证隐私安全的同时实现了两个数量级的加速比。

{"title":"Learning-to-optimize infused decentralized disaggregation for multi-entity technical VPP considering equity and privacy","authors":"Qihui Wang, Zhengshuo Li","doi":"10.1016/j.apenergy.2025.127226","DOIUrl":"10.1016/j.apenergy.2025.127226","url":null,"abstract":"<div><div>The growing renewable energy integration challenges grid stability, highlighting demand response as a critical solution. 5G base stations emerge as a valuable demand-side response resource due to their inherent flexibility potential. Virtual Power Plants, especially Technical VPPs (TVPPs), play a crucial role in effectively aggregating these base stations and other resources to enhance grid flexibility. However, TVPPs encounter significant obstacles in achieving rapid disaggregation, concerning real-time requirements, energy equity and privacy security. This paper presents a novel instruction disaggregation algorithm addressing these issues through a decentralized coordination mechanism. Firstly, a multi-entity TVPP instruction disaggregation model is established by incorporating both grid security and energy equity, and distinct in considering energy equity regarding the disaggregation process. Then, a decentralized disaggregation method based on learning-to-optimize is proposed where self-supervised learning is embedded to train surrogate models so that the computational time due to traditional optimization can be significantly reduced. Moreover, a lightweight privacy-preserving scheme is integrated to avoid privacy breaches without introducing excessive computational burdens. Finally, theoretical guarantees for the proposed algorithm are established, including solution quasi-feasibility, convergence and generalization properties. Case studies show that the proposed method significantly decreases computational demands, achieving speedup ratios of two orders of magnitude compared to the traditional decentralized method while ensuring privacy security.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127226"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Low-carbon and QoS-aware operation of data centers by AI task splitting and allocation 通过AI任务划分和分配实现数据中心的低碳、qos感知运营

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127132

Nan Lu , Ruiyang Yao , Zhaoyang Wang , Yuejun Yan , Yi Wang

Artificial intelligence (AI) techniques have shown impressive performance in both industry and academia. In recent years, the energy consumption of AI tasks has experienced exponential growth, and how to schedule arriving AI tasks in a low-carbon manner is worth investigating for data centers. However, due to the computationally intensive and resource-demanding properties of AI tasks, current deferral-based scheduling methods cannot efficiently fit a large AI task (e.g., training a large language model) into low-carbon periods, so the temporal flexibility cannot be fully utilized to reduce carbon emissions. To this end, we propose a low-carbon and quality-of-service (QoS)-aware operation framework for data centers based on AI task splitting and allocation. Specifically, a fine-grained estimation approach is first designed for computing resource requirements of AI tasks under various split strategies; on this basis, each AI task is then split into a varying number of subtasks that can satisfy heterogeneous resource constraints and be smoothly fitted into low-carbon time slots, which is done by our proposed DRL-based scheduler. Extensive comparison experiments are conducted on a publicly available dataset to validate the superiority of the proposed framework, verifying that our proposed method can achieve a significant reduction in carbon emissions and an improvement in QoS.

人工智能（AI）技术在工业界和学术界都表现出令人印象深刻的表现。近年来，人工智能任务的能耗呈指数级增长，如何以低碳的方式调度到达的人工智能任务值得数据中心研究。然而，由于人工智能任务的计算密集型和资源需求，目前基于延迟的调度方法无法有效地将大型人工智能任务（如训练大型语言模型）拟合到低碳时期，因此无法充分利用时间灵活性来减少碳排放。为此，我们提出了一种基于AI任务分割与分配的低碳、QoS感知的数据中心运营框架。具体而言，首先设计了一种细粒度估计方法，用于各种分割策略下人工智能任务的计算资源需求；在此基础上，每个人工智能任务被分成不同数量的子任务，这些子任务可以满足异构资源约束，并顺利适应低碳时段，这是由我们提出的基于drl的调度程序完成的。在一个公开可用的数据集上进行了大量的对比实验，以验证所提出框架的优越性，验证我们提出的方法可以显著减少碳排放并提高QoS。

{"title":"Low-carbon and QoS-aware operation of data centers by AI task splitting and allocation","authors":"Nan Lu , Ruiyang Yao , Zhaoyang Wang , Yuejun Yan , Yi Wang","doi":"10.1016/j.apenergy.2025.127132","DOIUrl":"10.1016/j.apenergy.2025.127132","url":null,"abstract":"<div><div>Artificial intelligence (AI) techniques have shown impressive performance in both industry and academia. In recent years, the energy consumption of AI tasks has experienced exponential growth, and how to schedule arriving AI tasks in a low-carbon manner is worth investigating for data centers. However, due to the computationally intensive and resource-demanding properties of AI tasks, current deferral-based scheduling methods cannot efficiently fit a large AI task (e.g., training a large language model) into low-carbon periods, so the temporal flexibility cannot be fully utilized to reduce carbon emissions. To this end, we propose a low-carbon and quality-of-service (QoS)-aware operation framework for data centers based on AI task splitting and allocation. Specifically, a fine-grained estimation approach is first designed for computing resource requirements of AI tasks under various split strategies; on this basis, each AI task is then split into a varying number of subtasks that can satisfy heterogeneous resource constraints and be smoothly fitted into low-carbon time slots, which is done by our proposed DRL-based scheduler. Extensive comparison experiments are conducted on a publicly available dataset to validate the superiority of the proposed framework, verifying that our proposed method can achieve a significant reduction in carbon emissions and an improvement in QoS.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127132"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Hydrogen applications in buildings: A systematic review of decarbonization pathways 氢在建筑中的应用：脱碳途径的系统回顾

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127201

Yimeng Li , Muhammad Shafique , Xiaowei Luo

The building sector is a major contributor to global energy use and carbon emissions, positioning it as a key target for decarbonization. Hydrogen, as a clean and flexible energy carrier, offers significant potential in supporting this transition. This review synthesizes recent advances in hydrogen applications for buildings, highlighting experimental findings, technological feasibility, socio-technical considerations, and policy developments. Key deployment models include hydrogen fuel cell integration, hydrogen-based microgrids, and combined heat and power systems. Emerging innovations such as renewable-powered hydrogen production, decentralized storage, and cross-sector integration with transport systems are also examined. In particular, the role of hydrogen-powered vehicles as energy buffers is emphasized for enhancing building energy autonomy. Despite its promise, hydrogen deployment faces technical, economic, and institutional challenges. The study calls for coordinated strategies that integrate hydrogen with other renewables, improve policy frameworks, and foster public acceptance. Future research should prioritize system integration pathways, techno-economic optimization, real-world demonstrations, and interdisciplinary collaboration. This review offers a strategic reference for scaling up hydrogen use in the built environment and underscores its critical role in achieving net-zero emissions and sustainable urban energy systems.

建筑行业是全球能源使用和碳排放的主要贡献者，将其定位为脱碳的关键目标。氢作为一种清洁、灵活的能源载体，在支持这一转变方面具有巨大潜力。本综述综合了氢能在建筑中的应用的最新进展，重点介绍了实验结果、技术可行性、社会技术考虑和政策发展。关键的部署模式包括氢燃料电池集成、氢基微电网和热电联产系统。新兴的创新，如可再生能源制氢，分散存储，以及与运输系统的跨部门整合也进行了研究。特别是，为了提高建筑的能源自主性，强调了氢动力汽车的能量缓冲作用。尽管前景光明，但氢能部署面临着技术、经济和体制方面的挑战。该研究呼吁协调战略，将氢与其他可再生能源结合起来，改善政策框架，促进公众接受。未来的研究应优先考虑系统集成路径、技术经济优化、现实世界示范和跨学科合作。本综述为扩大氢在建筑环境中的使用提供了战略参考，并强调了氢在实现净零排放和可持续城市能源系统中的关键作用。

{"title":"Hydrogen applications in buildings: A systematic review of decarbonization pathways","authors":"Yimeng Li , Muhammad Shafique , Xiaowei Luo","doi":"10.1016/j.apenergy.2025.127201","DOIUrl":"10.1016/j.apenergy.2025.127201","url":null,"abstract":"<div><div>The building sector is a major contributor to global energy use and carbon emissions, positioning it as a key target for decarbonization. Hydrogen, as a clean and flexible energy carrier, offers significant potential in supporting this transition. This review synthesizes recent advances in hydrogen applications for buildings, highlighting experimental findings, technological feasibility, socio-technical considerations, and policy developments. Key deployment models include hydrogen fuel cell integration, hydrogen-based microgrids, and combined heat and power systems. Emerging innovations such as renewable-powered hydrogen production, decentralized storage, and cross-sector integration with transport systems are also examined. In particular, the role of hydrogen-powered vehicles as energy buffers is emphasized for enhancing building energy autonomy. Despite its promise, hydrogen deployment faces technical, economic, and institutional challenges. The study calls for coordinated strategies that integrate hydrogen with other renewables, improve policy frameworks, and foster public acceptance. Future research should prioritize system integration pathways, techno-economic optimization, real-world demonstrations, and interdisciplinary collaboration. This review offers a strategic reference for scaling up hydrogen use in the built environment and underscores its critical role in achieving net-zero emissions and sustainable urban energy systems.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127201"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Compression-absorption hybrid heat pumps operating wide temperature ranges: A review and perspectives for large temperature lift 宽温度范围压缩-吸收混合热泵：大温度提升的回顾与展望

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127217

Qiang Ji , Yizhen Li , Yonggao Yin , Chunwen Che , Gongsheng Huang

Traditional heat pumps often fail to meet expectations in challenging scenarios such as building heating in severe cold regions and ultra-high temperature industrial heating, primarily due to their limited capacity for wide temperature range operation and restricted delivery of large temperature lifts. Compression-absorption hybrid heat pumps (CAHHP) demonstrate significant potential to overcome these limitations. However, existing literature lacks a systematic review that focuses on addressing these two core challenges and integrates the recent research progress in these extreme application scenarios. To address the identified knowledge gaps, this paper provides a comprehensive review of the fundamental principles and key configurations of CAHHP. It critically examines the advantages and limitations of various working pairs, ranging from traditional types to novel options such as ionic liquids and deep eutectic solvents. On this basis, the current development status of advanced CAHHP in key application areas is highlighted and analyzed. For heating in severe cold climates, the emphasis is on enhancing low-temperature adaptability and developing multi-mode, multi-source complementary strategies. For ultra-high temperature industrial heating, the focus shifts to achieving large temperature lifts and optimizing cascade configurations. Through the prospective analysis of CAHHP for applications requiring wide temperature ranges and significant temperature lifts, this review distills critical insights and outlines potential development directions. It aims to provide valuable theoretical references and technological guidelines to drive the advancement of CAHHP in essential sectors.

传统的热泵往往不能满足在极端寒冷地区的建筑供暖和超高温工业供暖等具有挑战性的情况下的期望，主要是因为它们在宽温度范围内运行的能力有限，并且限制了大型温度升降机的交付。压缩-吸收混合热泵（CAHHP）显示出克服这些限制的巨大潜力。然而，现有文献缺乏针对这两个核心挑战的系统综述，并整合这些极端应用场景下的最新研究进展。为了解决已确定的知识空白，本文对CAHHP的基本原理和关键配置进行了全面回顾。它批判性地检查了各种工作对的优点和局限性，从传统类型到新的选择，如离子液体和深共晶溶剂。在此基础上，重点分析了先进CAHHP在关键应用领域的发展现状。对于严寒气候下的供暖，重点是增强低温适应性，发展多模式、多源互补策略。对于超高温工业加热，重点转移到实现大的温度提升和优化级联配置。通过对CAHHP应用于需要宽温度范围和显著温度提升的应用的前瞻性分析，本文总结了关键的见解，并概述了潜在的发展方向。它旨在提供有价值的理论参考和技术指导，以推动CAHHP在关键领域的发展。

{"title":"Compression-absorption hybrid heat pumps operating wide temperature ranges: A review and perspectives for large temperature lift","authors":"Qiang Ji , Yizhen Li , Yonggao Yin , Chunwen Che , Gongsheng Huang","doi":"10.1016/j.apenergy.2025.127217","DOIUrl":"10.1016/j.apenergy.2025.127217","url":null,"abstract":"<div><div>Traditional heat pumps often fail to meet expectations in challenging scenarios such as building heating in severe cold regions and ultra-high temperature industrial heating, primarily due to their limited capacity for wide temperature range operation and restricted delivery of large temperature lifts. Compression-absorption hybrid heat pumps (CAHHP) demonstrate significant potential to overcome these limitations. However, existing literature lacks a systematic review that focuses on addressing these two core challenges and integrates the recent research progress in these extreme application scenarios. To address the identified knowledge gaps, this paper provides a comprehensive review of the fundamental principles and key configurations of CAHHP. It critically examines the advantages and limitations of various working pairs, ranging from traditional types to novel options such as ionic liquids and deep eutectic solvents. On this basis, the current development status of advanced CAHHP in key application areas is highlighted and analyzed. For heating in severe cold climates, the emphasis is on enhancing low-temperature adaptability and developing multi-mode, multi-source complementary strategies. For ultra-high temperature industrial heating, the focus shifts to achieving large temperature lifts and optimizing cascade configurations. Through the prospective analysis of CAHHP for applications requiring wide temperature ranges and significant temperature lifts, this review distills critical insights and outlines potential development directions. It aims to provide valuable theoretical references and technological guidelines to drive the advancement of CAHHP in essential sectors.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127217"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Quenching thermal runaway propagation in lithium-ion battery arrays with various thermal barriers: Experimental and modeling characterization 具有不同热障的锂离子电池阵列中淬火热失控传播：实验和建模表征

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-15 DOI: 10.1016/j.apenergy.2025.127197

Kyeong Soo Han , John Heinzel , Juliette Franqueville , Ofodike A. Ezekoye

Incorporation of thermal barriers (TBs) into lithium-ion battery modules has been shown to quench thermal runaway propagation (TRP). The design of such modules is required to optimize TBs to minimize weight and volume while maintaining TRP suppression. To construct an efficient design framework for evaluating diverse TBs, a modular, reconfigurable experimental system was developed to generate datasets for model calibration and validation, and a computational modeling environment was tailored to the physics of the specific cell and TB configurations being explored. The experimental system was constructed and exercised, permitting changes to the number of insulation layers, inclusion of finned surfaces, and the number of cells under test. In parallel, thermophysical-property calibration tests for TBs were conducted. Together, they produced extensive datasets for model calibration and validation. A fast yet sufficiently accurate low-order model was developed to predict TRP quenching in 11-Ah lithium-cobalt-oxide pouch cells at 100 % state of charge, across TB and no-TB configurations. Because the model contained more than ten unknown parameters (e.g., thermal contact resistances), a sequential, multi-step calibration framework was developed to estimate them and improve model accuracy. The calibrated model was validated against independent datasets. The design framework was then applied to assess the TRP-quenching performance of prospective designs based on an analysis of TB mechanisms (thermal storage, dissipation, and transmission). A quenching boundary map was generated, indicating that a TB comprising 2.5 mm aerogel layer and 1 mm fin quenched TRP and reduced mass and volume by 83 % and 72 %, respectively, relative to the baseline experimental TB.

在锂离子电池模块中加入热障（TBs）已被证明可以抑制热失控传播（TRP）。这类模块的设计需要优化TBs，在保持TRP抑制的同时最小化重量和体积。为了构建一个有效的设计框架来评估不同的TB，开发了一个模块化的、可重构的实验系统来生成模型校准和验证的数据集，并根据特定细胞的物理特性和正在探索的TB配置定制了计算建模环境。实验系统被构建和运行，允许改变保温层的数量，包括翅片表面，和测试细胞的数量。同时，对TBs进行了热物性校准试验。他们一起为模型校准和验证提供了广泛的数据集。建立了一个快速且足够精确的低阶模型来预测11-Ah锂钴氧化物袋状电池在100%充电状态下的TRP猝灭，包括TB和非TB配置。由于该模型包含10多个未知参数（例如，热接触电阻），因此开发了一个顺序的多步骤校准框架来估计它们并提高模型精度。校正后的模型在独立数据集上进行了验证。然后应用设计框架来评估基于TB机制（热储存、耗散和传输）分析的前瞻性设计的trp猝灭性能。生成的淬火边界图表明，含有2.5 mm气凝胶层和1 mm翅片的TB淬火了TRP，相对于基线实验TB，质量和体积分别减少了83%和72%。

{"title":"Quenching thermal runaway propagation in lithium-ion battery arrays with various thermal barriers: Experimental and modeling characterization","authors":"Kyeong Soo Han , John Heinzel , Juliette Franqueville , Ofodike A. Ezekoye","doi":"10.1016/j.apenergy.2025.127197","DOIUrl":"10.1016/j.apenergy.2025.127197","url":null,"abstract":"<div><div>Incorporation of thermal barriers (TBs) into lithium-ion battery modules has been shown to quench thermal runaway propagation (TRP). The design of such modules is required to optimize TBs to minimize weight and volume while maintaining TRP suppression. To construct an efficient design framework for evaluating diverse TBs, a modular, reconfigurable experimental system was developed to generate datasets for model calibration and validation, and a computational modeling environment was tailored to the physics of the specific cell and TB configurations being explored. The experimental system was constructed and exercised, permitting changes to the number of insulation layers, inclusion of finned surfaces, and the number of cells under test. In parallel, thermophysical-property calibration tests for TBs were conducted. Together, they produced extensive datasets for model calibration and validation. A fast yet sufficiently accurate low-order model was developed to predict TRP quenching in 11-Ah lithium-cobalt-oxide pouch cells at 100 % state of charge, across TB and no-TB configurations. Because the model contained more than ten unknown parameters (e.g., thermal contact resistances), a sequential, multi-step calibration framework was developed to estimate them and improve model accuracy. The calibrated model was validated against independent datasets. The design framework was then applied to assess the TRP-quenching performance of prospective designs based on an analysis of TB mechanisms (thermal storage, dissipation, and transmission). A quenching boundary map was generated, indicating that a TB comprising 2.5 mm aerogel layer and 1 mm fin quenched TRP and reduced mass and volume by 83 % and 72 %, respectively, relative to the baseline experimental TB.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127197"},"PeriodicalIF":11.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Graph-based multi-agent reinforcement learning with an enriched environment for joint ride-sharing and charging optimization 基于图的多智能体强化学习和丰富环境的联合拼车和收费优化

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-13 DOI: 10.1016/j.apenergy.2025.127220

Guixiang Yang , Hao Zhang , Lin Qiu

With the rapid growth of electric taxis, charging demand has become increasingly concentrated in specific urban areas due to the suboptimal pricing strategies. Meanwhile, ride-matching and charging processes are inherently coupled across temporal and spatial dimensions, making their joint coordination critical for boosting driver incomes and balancing energy loads. To tackle these challenges, we propose a graph-based multi-agent reinforcement learning strategy that incorporates an enriched environment for the joint optimization of ride-sharing and charging decisions. In our framework, electric vehicle charging stations, characterized by competitive and cooperative relationships that depend on their charging station operators, are regarded as reinforcement learning agents. The charging market is represented as a dynamic heterogeneous graph, which captures the interactions between charging stations from station-centric and query-centric perspectives. Finally, extensive simulation is performed, demonstrating the effectiveness of the control framework in balancing charging load distribution and boosting service revenue across stations compared to the baseline algorithms. The proposed control method with the ride-sharing process embedded into the environment optimizes the urban taxi distribution, expands the service coverage area, and enhances the overall driver earnings.

随着电动出租车的快速发展，由于定价策略的不优，充电需求越来越集中于特定的城市区域。同时，乘车匹配和充电过程在时间和空间维度上是固有耦合的，因此它们的联合协调对于提高司机收入和平衡能源负荷至关重要。为了应对这些挑战，我们提出了一种基于图的多智能体强化学习策略，该策略包含了一个丰富的环境，用于联合优化拼车和收费决策。在我们的框架中，电动汽车充电站被视为强化学习代理，其特点是依赖于充电站运营商的竞争和合作关系。充电市场被表示为一个动态的异构图，它从以站为中心和以查询为中心的角度捕捉充电站之间的交互。最后，进行了广泛的仿真，与基线算法相比，证明了控制框架在平衡充电负载分配和提高跨站服务收入方面的有效性。本文提出的控制方法将拼车过程嵌入到环境中，优化了城市出租车的分布，扩大了服务覆盖范围，提高了司机的整体收益。

{"title":"Graph-based multi-agent reinforcement learning with an enriched environment for joint ride-sharing and charging optimization","authors":"Guixiang Yang , Hao Zhang , Lin Qiu","doi":"10.1016/j.apenergy.2025.127220","DOIUrl":"10.1016/j.apenergy.2025.127220","url":null,"abstract":"<div><div>With the rapid growth of electric taxis, charging demand has become increasingly concentrated in specific urban areas due to the suboptimal pricing strategies. Meanwhile, ride-matching and charging processes are inherently coupled across temporal and spatial dimensions, making their joint coordination critical for boosting driver incomes and balancing energy loads. To tackle these challenges, we propose a graph-based multi-agent reinforcement learning strategy that incorporates an enriched environment for the joint optimization of ride-sharing and charging decisions. In our framework, electric vehicle charging stations, characterized by competitive and cooperative relationships that depend on their charging station operators, are regarded as reinforcement learning agents. The charging market is represented as a dynamic heterogeneous graph, which captures the interactions between charging stations from station-centric and query-centric perspectives. Finally, extensive simulation is performed, demonstrating the effectiveness of the control framework in balancing charging load distribution and boosting service revenue across stations compared to the baseline algorithms. The proposed control method with the ride-sharing process embedded into the environment optimizes the urban taxi distribution, expands the service coverage area, and enhances the overall driver earnings.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127220"},"PeriodicalIF":11.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145735899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

State of power prediction considering cell inconsistency for a series-parallel battery pack based on adaptive SRUKF and double-neural network 基于自适应SRUKF和双神经网络的串并联电池组考虑电池不一致性的功率预测状态

IF 11 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2025-12-13 DOI: 10.1016/j.apenergy.2025.127239

Simin Peng , Shengdong Chen , Xuexia Zhang , Jian Liu , Chong Chen , Jiarong Kan , Quanqing Yu

Accurate prediction of the state of power (SOP) for lithium-ion batteries is critical in electric vehicles, where state of charge (SOC) serves as a key constraint. Increasing battery cell count and inherent inconsistencies raise predicted SOP deviation despite accurate SOC. In this study, a SOP prediction method for a series-parallel battery pack based on adaptive square root unscented Kalman filter (ASRUKF) and double neural network is developed. First, cell inconsistency is quantified using weighted cosine similarity, and the cell with the largest coefficient in each branch is selected to establish a pack mean model. Second, since noise interference such as battery measurement noises can cause instability in SOP prediction, an ASRUKF with variable forgetting factor is developed to improve the system's noise resistance. Finally, to describe the influence of cell inconsistency on the SOP deviation and capture the power characteristics in different stages, a double-neural network model containing radial basis function and gated recurrent unit is designed. Moreover, an enhanced beluga whale optimization algorithm is presented to tune the hyperparameters for the network model. The results show the developed SOP prediction method has a maximum error below 0.32 W across time scales, while simultaneously reducing the runtime cost by at least 32.2 %.

准确预测锂离子电池的功率状态（SOP）对于电动汽车来说至关重要，其中充电状态（SOC）是一个关键的约束条件。尽管SOC准确，但不断增加的电池数量和固有的不一致性会增加预测的SOP偏差。本文提出了一种基于自适应平方根无气味卡尔曼滤波（ASRUKF）和双神经网络的串并联电池组SOP预测方法。首先，利用加权余弦相似度对单元格不一致性进行量化，选取各分支中系数最大的单元格建立包平均模型；其次，由于电池测量噪声等噪声干扰会导致SOP预测不稳定，因此开发了可变遗忘因子的ASRUKF来提高系统的抗噪声能力。最后，为了描述电池不一致性对SOP偏差的影响，并捕捉不同阶段的功率特性，设计了包含径向基函数和门控循环单元的双神经网络模型。在此基础上，提出了一种改进的白鲸优化算法对网络模型的超参数进行调优。结果表明，所建立的SOP预测方法在时间尺度上的最大误差小于0.32 W，同时运行成本至少降低32.2%。

{"title":"State of power prediction considering cell inconsistency for a series-parallel battery pack based on adaptive SRUKF and double-neural network","authors":"Simin Peng , Shengdong Chen , Xuexia Zhang , Jian Liu , Chong Chen , Jiarong Kan , Quanqing Yu","doi":"10.1016/j.apenergy.2025.127239","DOIUrl":"10.1016/j.apenergy.2025.127239","url":null,"abstract":"<div><div>Accurate prediction of the state of power (SOP) for lithium-ion batteries is critical in electric vehicles, where state of charge (SOC) serves as a key constraint. Increasing battery cell count and inherent inconsistencies raise predicted SOP deviation despite accurate SOC. In this study, a SOP prediction method for a series-parallel battery pack based on adaptive square root unscented Kalman filter (ASRUKF) and double neural network is developed. First, cell inconsistency is quantified using weighted cosine similarity, and the cell with the largest coefficient in each branch is selected to establish a pack mean model. Second, since noise interference such as battery measurement noises can cause instability in SOP prediction, an ASRUKF with variable forgetting factor is developed to improve the system's noise resistance. Finally, to describe the influence of cell inconsistency on the SOP deviation and capture the power characteristics in different stages, a double-neural network model containing radial basis function and gated recurrent unit is designed. Moreover, an enhanced beluga whale optimization algorithm is presented to tune the hyperparameters for the network model. The results show the developed SOP prediction method has a maximum error below 0.32 W across time scales, while simultaneously reducing the runtime cost by at least 32.2 %.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"405 ","pages":"Article 127239"},"PeriodicalIF":11.0,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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