Applied Energy最新文献

{"title":"Machine learning assisted health status analysis and degradation prediction of aging proton exchange membrane fuel cells","authors":"Fan Zhang ,&nbsp;Meng Ni ,&nbsp;Shupeng Tai ,&nbsp;Bingfeng Zu ,&nbsp;Fuqiang Xi ,&nbsp;Yangyang Shen ,&nbsp;Bowen Wang ,&nbsp;Zhikun Qin ,&nbsp;Rongxuan Wang ,&nbsp;Ting Guo ,&nbsp;Kui Jiao","doi":"10.1016/j.apenergy.2025.125483","DOIUrl":"10.1016/j.apenergy.2025.125483","url":null,"abstract":"<div><div>Proton exchange membrane fuel cells (PEMFCs) represent a significant application scenario for hydrogen energy and an important sector in achieving net-zero carbon emission. Prognostics and health management are crucial for enhancing their durability and reducing maintenance costs. This study proposes a framework for health status analysis and degradation prediction of aging PEMFCs, addressing the challenge of accurately identifying internal parameter states faced by current life prediction methods. Six aging factors are incorporated into the developed PEMFC mechanism model to characterize its intricate degradation process. The variations in these factors over a 3750-h experimental period are then estimated using the Particle Filtering method. Results demonstrate a notable reduction in the electrochemical surface area, decreasing from 5.76 m² to 4.08 m², accompanied by a significant increase in leakage current to nearly 6 A m⁻². These findings indicate substantial degradation of both the catalyst layer and membrane. Furthermore, ionic and contact resistances have increased as a result of reduced membrane conductivity and bipolar plate corrosion, respectively. The mass transport capacity has diminished, leading to an elevated concentration loss within the cell. Subsequently, the Transformer model is employed to forecast future changes in the aging factors and realize the degradation prediction over the next 1000 h. The effectiveness of the proposed method is fully validated under various conditions, with the average prediction error less than 4 %, which demonstrates higher long-term prediction accuracy compared to previous studies. This study provides an effective framework for the health management of PEMFCs and facilitates their widespread commercialization.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":""},"PeriodicalIF":10.1,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348498","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}

{"title":"Flattening the peak demand curve through energy efficient buildings: A holistic approach towards net-zero carbon","authors":"Yerbol Akhmetov ,&nbsp;Ekaterina Fedotova ,&nbsp;Martha Maria Frysztacki","doi":"10.1016/j.apenergy.2025.125421","DOIUrl":"10.1016/j.apenergy.2025.125421","url":null,"abstract":"<div><div>This study employs a sector-coupled energy system model to co-optimise investments in the supply side, demand side, and efficiency improvements. Beginning with a novel validation exercise of 2023, we demonstrate that the model can accurately reproduce the energy mix with an error of less than 5%. This approach incorporates often-neglected energy carriers, such as coal, gas, and nuclear, providing a holistic view of the current energy landscape. The analysis focuses on the impact of energy efficiency measures and building renovations on seasonal peak heating demand in Europe, featuring a pathway study that examines carbon emission targets for 2030, 2040, and 2050, while incorporating a new focus on efficiency improvements and demand-side response for the heating sector. Results indicate that reducing peak heating demand by up to 49% is cost-optimal and can facilitate annual reductions of 0.2 billion tons of greenhouse gas emissions by 2030, exceeding current emissions targets by 10%. Additionally, the findings suggest potential savings of €44.2 billion in distribution grid investments and a 75% decrease in transmission grid congestion. The study highlights that lowering peak demand could alleviate the need for significant investments in renewable energy infrastructure, potentially eliminating the requirement for 600 GW of onshore wind and 872 GW of solar PV capacity. Furthermore, optimising transmission and supply investments could lead to lower electricity prices, improving equity in pricing across European countries and significantly reducing energy bills for households and industries. Overall, the research underscores the critical role of energy efficiency and flexibility measures in achieving Europe’s decarbonisation goals while ensuring affordable energy access.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":""},"PeriodicalIF":10.1,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348497","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}

{"title":"Energy management of electric vehicles based on improved long short term memory network and data-enabled predictive control","authors":"Bin Chen ,&nbsp;Guo He ,&nbsp;Lin Hu ,&nbsp;Heng Li ,&nbsp;Miaoben Wang ,&nbsp;Rui Zhang ,&nbsp;Kai Gao","doi":"10.1016/j.apenergy.2025.125456","DOIUrl":"10.1016/j.apenergy.2025.125456","url":null,"abstract":"<div><div>As a popular energy management strategy (EMS) in electric vehicles with hybrid energy storage systems (HESS), model predictive control (MPC) is vulnerable to model accuracy and parameter sensitivity effects with existing parametric modeling methods. This paper proposes a novel EMS based on hierarchical data-driven predictive control. The upper layer utilizes an optimized long short-term memory (LSTM) network for trajectory prediction, enabling the acquisition of cost-effective load power demands for the lower layer. In the lower layer, a data-enabled predictive control (DeePC) is proposed for the HESS to achieve optimal power distribution between the battery and supercapacitor while minimizing battery capacity loss. Unlike conventional MPC, DeePC is based on a non-parametric model built solely from input–output data of the HESS, enabling agile handling of diverse nonlinearities and uncertainties across different tasks and environments. Comparison with nonlinear model predictive control shows that DeePC reduces the total operating cost by 22.68%, with optimization results closer to offline dynamic programming results. Furthermore, the effectiveness of the proposed DeePC method is validated through hardware-in-the-loop (HIL).</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125456"},"PeriodicalIF":10.1,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348986","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}

{"title":"How heat waves and urban microclimates affect building cooling energy demand? Insights from fifteen eastern Chinese cities","authors":"Xiaoshan Yang ,&nbsp;Lingye Yao ,&nbsp;Mingcai Li ,&nbsp;Jingfu Cao ,&nbsp;Qing Zhong ,&nbsp;Weidong Peng ,&nbsp;Wenkai Wu ,&nbsp;Jing Zhou","doi":"10.1016/j.apenergy.2025.125424","DOIUrl":"10.1016/j.apenergy.2025.125424","url":null,"abstract":"<div><div>Heat waves (HW), characterized by prolonged period of excessively high temperatures on a regional scale, are becoming increasingly frequent due to climate change. Concurrently, the urban heat island (UHI) effect—a localized climate phenomenon resulting from urbanization—affects cities worldwide. The interaction between HW and UHI exacerbates urban overheating, posing significant threats to human health, ecological stability, and energy consumption. A critical consequence of this synergy is the heightened demand for cooling energy in urban buildings. However, research examining the combined effects of HWs and urban microclimates (UMs)—particularly concerning both air temperature and humidity—remains limited. The present study utilized three years of hourly meteorological data from 15 cities in eastern China to explore the impacts of HWs and UMs on the cooling energy performance of a typical residential building. Key findings include: (1) During HW days, both air temperature (<em>T</em>_<em>a</em>) and dew-point temperature (<em>T</em>_<em>dew</em>) were significantly elevated compared to normal hot summer days. (2) The UHI effects led to increases in sensible cooling load, whereas the urban dry island (UDI) effects resulted in decreases in latent cooling load. (3) The combined impacts of HWs and UMs contributed to a 65% to 115% rise in sensible cooling energy demand, a 20% to 106% increase in latent cooling energy demand, and a 42% to 103% growth in total cooling energy demand. (4) Daily peak cooling loads for urban buildings during HWs increased by 21% to 62%. (5) Strong correlations were found between daily sensible cooling energy demand and daily mean <em>T</em>_<em>a</em> (<em>R</em>² = 0.94), as well as between daily latent cooling energy demand and daily mean <em>T</em>_<em>dew</em> (<em>R</em>² = 0.94). This study leverages long-term meteorological observations from multiple cities to provide a thorough understanding of how HWs and UMs impact building cooling energy performance. It underscores the necessity of considering the combined effects of HWs and UMs, as well as the roles of air temperature and humidity, when evaluating urban cooling energy needs. The findings offer valuable insights for planning energy infrastructure, designing effective cooling systems, improving energy management strategies, and enhancing grid resilience.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125424"},"PeriodicalIF":10.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332394","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}

{"title":"Personalized federated learning for household electricity load prediction with imbalanced historical data","authors":"Shibo Zhu ,&nbsp;Xiaodan Shi ,&nbsp;Huan Zhao ,&nbsp;Yuntian Chen ,&nbsp;Haoran Zhang ,&nbsp;Xuan Song ,&nbsp;Tianhao Wu ,&nbsp;Jinyue Yan","doi":"10.1016/j.apenergy.2025.125419","DOIUrl":"10.1016/j.apenergy.2025.125419","url":null,"abstract":"<div><div>Household consumption accounts for about one-third of global electricity. Accurate results of household load prediction would help in energy management at both the building and the grid levels. Data-driven household load prediction methods have shown great advantages and potential in terms of accuracy. However, these methods still face challenges such as limited data for individual households, diversified electricity consumption behaviors, and data privacy concerns. To solve these problems, this paper proposes a personalized federated learning household load prediction framework (PF-HoLo), which allows personal models to learn collectively, leverages multisource data to capture diverse consumption behaviors, and ensures data privacy. In addition, the global encoder model and mutual learning are proposed to enhance the performance of the PF-HoLo framework considering imbalanced residential historical data. Ablation experiments results prove that the PF-HoLo framework could achieve significant improvements, with 13.41% Mean Square Error and 11.33% Mean Absolute Error, compared to traditional federated learning methods.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125419"},"PeriodicalIF":10.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Thermophotovoltaic performance metrics and techno-economics: Efficiency vs. power density","authors":"Shomik Verma,&nbsp;Kyle Buznitsky,&nbsp;Asegun Henry","doi":"10.1016/j.apenergy.2025.125479","DOIUrl":"10.1016/j.apenergy.2025.125479","url":null,"abstract":"<div><div>Thermophotovoltaics (TPV) are a promising new approach for converting heat to electricity. Their performance is primarily characterized by two metrics: efficiency and power density. While recent works have shown high efficiency, it is important to understand how both of these metrics impact the techno-economics of a TPV system as efforts to commercialize the technology advance. In this work, we develop the first unification of efficiency and power density into a single techno-economic metric based on the levelized cost of electricity (LCOE). We find that the LCOE can be broken into two parts: heating cost, including infrastructure and inputs for providing heat to the TPV cells, and cell cost, the capital cost of the TPV cells. We show that systems with high heating costs should prioritize TPV efficiency, while systems with high cell costs should prioritize power density. We then develop a model to identify the most impactful cell properties in improving the important performance metric and reducing system LCOE. Namely, improving spectral control with increased back-surface reflectance is the most effective to reduce LCOE in systems with high infrastructural costs, while increasing the view factor and reducing front-surface reflectance are most critical in systems with high TPV cell cost. Improving just one or two of these properties can reduce the LCOE by 25–75 %, reaching competitive values ∼8 ¢/kWh-e, less than the average cost of electricity in the US. This study thus elucidates which TPV performance metric is more important for system techno-economics and how to maximize it.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125479"},"PeriodicalIF":10.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143358837","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}

{"title":"Provincial allocation of China's commercial building operational carbon toward carbon neutrality","authors":"Yanqiao Deng ,&nbsp;Minda Ma ,&nbsp;Nan Zhou ,&nbsp;Chenchen Zou ,&nbsp;Zhili Ma ,&nbsp;Ran Yan ,&nbsp;Xin Ma","doi":"10.1016/j.apenergy.2025.125450","DOIUrl":"10.1016/j.apenergy.2025.125450","url":null,"abstract":"<div><div>National carbon peak track and optimized provincial carbon allocations are crucial for mitigating regional inequality within the commercial building sector during China's transition to carbon neutrality. This study proposes a top-down model to evaluate carbon trajectories in operational commercial buildings up to 2060. Through Monte Carlo simulation, scenario analysis is conducted to assess carbon peak values and the corresponding peaking year, thereby optimizing carbon allocation schemes both nationwide and provincially. The results reveal that (1) the nationwide carbon peak for commercial building operations is projected to reach 890 (± 50) megatons of carbon dioxide (MtCO₂) by 2028 (± 3.7 years) in the case of the business-as-usual scenario, with a 7.87 % probability of achieving the carbon peak under the decarbonization scenario. (2) Significant disparities will exist among provinces, with Shandong's carbon peak projected at 69.6 (± 4.0) MtCO₂ by 2029, approximately 11 times higher than Ningxia's peak of 6.0 (± 0.3) MtCO₂ by 2027. (3) Guided by the principle of maximizing the emission reduction potential, the optimal provincial allocation scheme reveals the top three provinces requiring the most significant reductions in the commercial sector: Xinjiang (5.6 MtCO₂), Shandong (4.8 MtCO₂), and Henan (4.7 MtCO₂). Overall, this study offers optimized provincial carbon allocation strategies within the commercial building sector in China via dynamic scenario simulations, with the goal of hitting the carbon peak target and progressing toward a low-carbon future for the building sector.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125450"},"PeriodicalIF":10.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel two-stage energy sharing model for data center cluster considering integrated demand response of multiple loads","authors":"Yifan Bian,&nbsp;Lirong Xie,&nbsp;Lan Ma,&nbsp;Chuanshi Cui","doi":"10.1016/j.apenergy.2025.125454","DOIUrl":"10.1016/j.apenergy.2025.125454","url":null,"abstract":"<div><div>The increasing energy demand of data centers highlights the necessity of exploring joint optimization strategies for scheduling and energy management within data centers. This study establishes a data center cluster (DCC) framework composed of a DCC operator (DCCO) and data center prosumers (DCPs). Furthermore, a two-stage energy sharing model is developed, incorporating the integrated demand response (IDR) across multiple loads. The first stage is the day-ahead optimization stage, in which the probability distribution uncertainties of wind power, photovoltaic power, and loads are fully considered, and a shared energy storage (SES) optimization scheduling method based on the worst conditional value-at-risk is constructed. The second stage is the real-time optimization stage; first, a new peer-to-peer (P2P) trading mechanism based on electricity and heat supply/demand ratios is designed to realize the joint sharing of electricity and heat among DCPs; then, a refined IDR model that considers the temporal-spatial transferability of data loads, household appliance flexibility, thermal retardation and thermal comfort is demonstrated, and some metrics such as efficiency improvement ratio are introduced to evaluate the IDR model; finally, the benefit functions for both DCCO and DCPs are formulated. A Stackelberg game model for DCC is introduced, which incorporates the SES trading price determined by DCCO, along with the IDR and P2P trading strategies employed by DCPs. The results demonstrate that the proposed DCC framework and energy-sharing model achieve a 39.34 % reduction in the total daily operating costs of DCPs, while fostering mutual benefits and a win-win outcome for both DCCO and DCPs.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125454"},"PeriodicalIF":10.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332392","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}

{"title":"Reservation reward-based approach for reducing energy consumption peaks in urban rail transit","authors":"Meiling Ding ,&nbsp;Xin Guo ,&nbsp;Wen-Long Shang ,&nbsp;Jianjun Wu ,&nbsp;Ziyou Gao","doi":"10.1016/j.apenergy.2025.125466","DOIUrl":"10.1016/j.apenergy.2025.125466","url":null,"abstract":"<div><div>In light of the swift expansion of urban rail transit systems, this paper addresses the challenges of reducing energy consumption using a reservation reward-based approach, thereby reducing the overall environmental footprint of rail operations. The approach encourages passengers to shift from peak to off-peak hours, reducing energy use and improving service quality. A multi-objective mixed-integer programming model with a pre-departure idea is proposed to evaluate energy consumption peaks while maintaining high levels of passenger service. To achieve this, a pre-departure strategy is embedded to encourage passengers to adjust their departure times from peak hours to off-peak hours. Secondly, a layered-sorted-based heuristic multi-objective optimization algorithm is designed to solve the model, demonstrating excellent convergence through all results. Finally, Computational results confirm the approach's effectiveness and provide valuable insights into key parameters affecting sustainability. This research supports sustainable urban transit by reducing energy peaks, enhancing efficiency, and minimizing environmental impacts.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125466"},"PeriodicalIF":10.1,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332053","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}

{"title":"A Generic physics-informed machine learning framework for battery remaining useful life prediction using small early-stage lifecycle data","authors":"Weikun Deng ,&nbsp;Hung Le ,&nbsp;Khanh T.P. Nguyen ,&nbsp;Christian Gogu ,&nbsp;Kamal Medjaher ,&nbsp;Jérôme Morio ,&nbsp;Dazhong Wu","doi":"10.1016/j.apenergy.2025.125314","DOIUrl":"10.1016/j.apenergy.2025.125314","url":null,"abstract":"<div><div>Predicting the remaining useful life (RUL) of fast-charging lithium-ion batteries using early-stage lifecycle data is remains challenging due to limited run-to-failure data and lack of knowledge on battery degradation mechanisms. To address this issue, a generic Physics-Informed Machine Learning (PIML) framework is developed. The PIML framework consists of two parallel branches: a physics-informed (PI) branch and a data-driven branch. The PI branch is a neural network stacked by the linear projection layers with embedded physics knowledge, while the data-driven branch is a task-specific machine-learning model. In addition, a three-step training strategy is introduced, including (1) Training the data-driven branch, (2) Training the PI branch for aligning physical consistency without updating the hyperparameters in the data-driven branch, and (3) Fine-tuning both branches simultaneously to achieve optimal performance. To validate this framework, a physics-based model that represents the growth of solid electrolyte interphase (SEI) and a dilated convolutional neural network are implemented in the PI and data-driven branches, respectively. The solid electrolyte interphase-informed dilated convolutional neural network (SEI-DCN) model is demonstrated on the Stanford–MIT–Toyota-battery dataset. Using only four lifecycle data, the SEI-DCN model achieves very high prediction accuracy compared to standard dilated CNNs and other state-of-the-art models under various testing conditions and lifetime ranges. Moreover, the framework is generalizable to different physics-based battery degradation models.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"384 ","pages":"Article 125314"},"PeriodicalIF":10.1,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143358836","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}