Applied Energy最新文献_第5页

Joint peak power and carbon emission shaving in active distribution systems using carbon emission flow-based deep reinforcement learning 利用基于碳排放流的深度强化学习，在主动配电系统中联合削峰填谷和减少碳排放

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124944

Sangyoon Lee , Panggah Prabawa , Dae-Hyun Choi

Distribution optimal power flow (D-OPF) with peak load shaving function is crucial for guaranteeing economical and reliable operations of active distribution grids with various distributed energy resources. However, conventional D-OPF methods reduce only the power operation cost without considering carbon emission reduction, which may lead to a slowdown in achieving global carbon neutrality. To resolve this issue, this study proposes a deep reinforcement learning (DRL)-assisted D-OPF framework realizing dual-peak shaving of power and carbon emission for low-carbon active distribution system operations based on the notion of carbon emission flow (CEF). The proposed framework aims to minimize the total power operation costs of substation and gas-turbine (GT) generators. It also aims to reduce the total carbon emission cost via mitigation of peak power and carbon emission in the CEF-based D-OPF framework with both power and carbon emission peak constraints. A key feature of the proposed framework is the adoption of the DRL method for the CEF-based D-OPF problem to determine economical and eco-friendly peaks of power and carbon emission under dynamically changing distribution system operations. Furthermore, a D-OPF optimization-based reward function for the DRL agent is designed to yield no constraint violations for the D-OPF problem during the agent’s training phase. Numerical examples conducted on the IEEE 33-node and IEEE 69-node distribution systems with GT generators, solar photovoltaic systems, and energy storage systems demonstrate that, in contrast with CEF-free and CEF-integrated optimization methods with fixed power and/or carbon emission peaks, the proposed method further reduces the total carbon emission and cost.

具有削峰填谷功能的配电网优化功率流（D-OPF）对于保证拥有各种分布式能源的主动配电网的经济可靠运行至关重要。然而，传统的 D-OPF 方法只降低电力运行成本，而不考虑碳减排，这可能会导致实现全球碳中和的进程放缓。为解决这一问题，本研究基于碳排放流（CEF）的概念，提出了一种深度强化学习（DRL）辅助的 D-OPF 框架，以实现电力和碳排放的双峰削减，从而实现低碳主动配电系统运营。所提出的框架旨在最大限度地降低变电站和燃气轮机（GT）发电机的总电力运营成本。同时，在基于 CEF 的 D-OPF 框架中，在电力和碳排放峰值约束条件下，通过缓解电力和碳排放峰值，降低总碳排放成本。所提框架的一个主要特点是，在基于 CEF 的 D-OPF 问题中采用 DRL 方法，以确定动态变化的配电系统运行条件下既经济又环保的电力和碳排放峰值。此外，还为 DRL 代理设计了基于 D-OPF 优化的奖励函数，以便在代理训练阶段不违反 D-OPF 问题的约束条件。在配有 GT 发电机、太阳能光伏系统和储能系统的 IEEE 33 节点和 IEEE 69 节点配电系统上进行的数值示例表明，与功率和/或碳排放峰值固定的无 CEF 和 CEF 集成优化方法相比，所提出的方法进一步降低了总碳排放量和成本。

{"title":"Joint peak power and carbon emission shaving in active distribution systems using carbon emission flow-based deep reinforcement learning","authors":"Sangyoon Lee , Panggah Prabawa , Dae-Hyun Choi","doi":"10.1016/j.apenergy.2024.124944","DOIUrl":"10.1016/j.apenergy.2024.124944","url":null,"abstract":"<div><div>Distribution optimal power flow (D-OPF) with peak load shaving function is crucial for guaranteeing economical and reliable operations of active distribution grids with various distributed energy resources. However, conventional D-OPF methods reduce only the power operation cost without considering carbon emission reduction, which may lead to a slowdown in achieving global carbon neutrality. To resolve this issue, this study proposes a deep reinforcement learning (DRL)-assisted D-OPF framework realizing dual-peak shaving of power and carbon emission for low-carbon active distribution system operations based on the notion of carbon emission flow (CEF). The proposed framework aims to minimize the total power operation costs of substation and gas-turbine (GT) generators. It also aims to reduce the total carbon emission cost via mitigation of peak power and carbon emission in the CEF-based D-OPF framework with both power and carbon emission peak constraints. A key feature of the proposed framework is the adoption of the DRL method for the CEF-based D-OPF problem to determine economical and eco-friendly peaks of power and carbon emission under dynamically changing distribution system operations. Furthermore, a D-OPF optimization-based reward function for the DRL agent is designed to yield no constraint violations for the D-OPF problem during the agent’s training phase. Numerical examples conducted on the IEEE 33-node and IEEE 69-node distribution systems with GT generators, solar photovoltaic systems, and energy storage systems demonstrate that, in contrast with CEF-free and CEF-integrated optimization methods with fixed power and/or carbon emission peaks, the proposed method further reduces the total carbon emission and cost.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124944"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721110","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

Effects of hydrogen dilution on performance and in-plane uniformity of large-scale PEM fuel cell with low anode catalyst loading 氢稀释对低阳极催化剂负载的大规模 PEM 燃料电池性能和平面内均匀性的影响

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124992

Ling Xu , Liangfei Xu , Yangbin Shao , Xiyuan Zhang , Zunyan Hu , Jianqiu Li , Minggao Ouyang

Enhancing hydrogen utilization is crucial for improving the efficiency of Proton Exchange Membrane (PEM) fuel cells. However, the widespread implementation of ultra-thin PEMs introduces a challenging objective: balancing hydrogen utilization with hydrogen dilution, which can adversely affect performance. To achieve this balance, understanding the impact of hydrogen dilution on fuel cell performance is critical, particularly for commercial large-scale fuel cells with low anode catalyst loadings, where significant research gaps remain. This study aims to fill these research gaps by investigating the performance and current distribution of a 291 cm² fuel cell with an anode platinum loading of 0.1 mg/cm² under varying hydrogen molar fractions (HMFs) and hydrogen stoichiometric ratios (HSRs). The results reveal that hydrogen dilution affects performance through three primary mechanisms: decreasing anode hydrogen partial pressure, exacerbating hydrogen supply non-uniformity, and altering the water balance. Notably, the latter two factors interact and collectively affect in-plane uniformity, leading to complex performance characteristics under hydrogen dilution conditions. Furthermore, the performance loss due to hydrogen dilution observed in this study is more pronounced than previously reported, primarily due to low catalyst loading and in-plane non-uniformity resulting from scale expansion. Nevertheless, at medium to low current densities and high HSR conditions, where the impact of hydrogen dilution is diminished, moderate hydrogen dilution can be permitted to enhance hydrogen utilization. Based on the data collected, this study maps the boundary for hydrogen dilution constrained by performance loss, offering valuable insights into the design and optimization of future control strategies.

提高氢气利用率对于提高质子交换膜燃料电池的效率至关重要。然而，超薄质子交换膜的广泛应用带来了一个具有挑战性的目标：平衡氢气利用率和氢气稀释，因为氢气稀释会对性能产生不利影响。要实现这一平衡，了解氢稀释对燃料电池性能的影响至关重要，特别是对于阳极催化剂负载较低的商用大型燃料电池，这方面的研究仍存在重大差距。本研究旨在通过调查阳极铂负载量为 0.1 mg/cm2 的 291 平方厘米燃料电池在不同氢摩尔分数（HMF）和氢化学计量比（HSR）条件下的性能和电流分布，填补这些研究空白。研究结果表明，氢稀释通过三种主要机制影响性能：降低阳极氢分压、加剧氢供应不均匀性以及改变水平衡。值得注意的是，后两个因素相互作用，共同影响平面内的均匀性，从而导致氢稀释条件下复杂的性能特征。此外，本研究中观察到的氢稀释导致的性能损失比之前报道的更为明显，这主要是由于催化剂装载量低以及水垢膨胀导致的面内不均匀性造成的。不过，在中低电流密度和高 HSR 条件下，氢稀释的影响会减弱，因此可以允许适度的氢稀释，以提高氢气利用率。根据收集到的数据，本研究绘制了受性能损失限制的氢稀释边界，为未来控制策略的设计和优化提供了宝贵的见解。

{"title":"Effects of hydrogen dilution on performance and in-plane uniformity of large-scale PEM fuel cell with low anode catalyst loading","authors":"Ling Xu , Liangfei Xu , Yangbin Shao , Xiyuan Zhang , Zunyan Hu , Jianqiu Li , Minggao Ouyang","doi":"10.1016/j.apenergy.2024.124992","DOIUrl":"10.1016/j.apenergy.2024.124992","url":null,"abstract":"<div><div>Enhancing hydrogen utilization is crucial for improving the efficiency of Proton Exchange Membrane (PEM) fuel cells. However, the widespread implementation of ultra-thin PEMs introduces a challenging objective: balancing hydrogen utilization with hydrogen dilution, which can adversely affect performance. To achieve this balance, understanding the impact of hydrogen dilution on fuel cell performance is critical, particularly for commercial large-scale fuel cells with low anode catalyst loadings, where significant research gaps remain. This study aims to fill these research gaps by investigating the performance and current distribution of a 291 cm<sup>2</sup> fuel cell with an anode platinum loading of 0.1 mg/cm<sup>2</sup> under varying hydrogen molar fractions (HMFs) and hydrogen stoichiometric ratios (HSRs). The results reveal that hydrogen dilution affects performance through three primary mechanisms: decreasing anode hydrogen partial pressure, exacerbating hydrogen supply non-uniformity, and altering the water balance. Notably, the latter two factors interact and collectively affect in-plane uniformity, leading to complex performance characteristics under hydrogen dilution conditions. Furthermore, the performance loss due to hydrogen dilution observed in this study is more pronounced than previously reported, primarily due to low catalyst loading and in-plane non-uniformity resulting from scale expansion. Nevertheless, at medium to low current densities and high HSR conditions, where the impact of hydrogen dilution is diminished, moderate hydrogen dilution can be permitted to enhance hydrogen utilization. Based on the data collected, this study maps the boundary for hydrogen dilution constrained by performance loss, offering valuable insights into the design and optimization of future control strategies.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124992"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721170","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

A copula-based whole system model to understand the environmental and economic impacts of grid-scale energy storage 基于 copula 的全系统模型，用于了解电网规模储能对环境和经济的影响

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124935

Fan He , Matthew Leach , Michael Short , Yurui Fan , Lirong Liu

Energy storage is important in future power systems. However, the role of grid-scale energy storage in the power system and in the whole socio-economic system is unclear. A copula-based whole system model is developed to explore the economic and environmental effects of grid-scale energy storage, thus supporting the decision-making at micro and macro levels. A power system optimisation model is linked with an input-output model, and the copula function is embedded in the model to reflect the multiple and interactive uncertainties from electricity demand, emission constraints, and sector disaggregation. We conducted case studies on China and the UK in 2025 considering different storage technologies (Pumped hydro, Battery, Flywheels storage) to show the differences related with power systems and economic structures. We find that increasing energy storage capacity leads to increase in renewable generation capacity (solar generation in China and wind generation in the UK). Thus, it can reduce their total economy-wide carbon emissions. Uncertainty in sector disaggregation will have a large impact on carbon emissions in some extreme cases, especially in those sectors closely linked to the power sector and with high emission intensity.

储能在未来的电力系统中非常重要。然而，电网储能在电力系统和整个社会经济系统中的作用尚不明确。我们开发了一个基于 copula 的全系统模型，以探索电网规模储能的经济和环境影响，从而为微观和宏观层面的决策提供支持。将电力系统优化模型与投入产出模型联系起来，并在模型中嵌入 copula 函数，以反映来自电力需求、排放限制和部门分类的多重交互式不确定性。我们对 2025 年的中国和英国进行了案例研究，考虑了不同的储能技术（抽水蓄能、电池储能、飞轮储能），以显示与电力系统和经济结构相关的差异。我们发现，增加储能容量会导致可再生能源发电量的增加（中国的太阳能发电量和英国的风力发电量）。因此，这可以减少整个经济的碳排放总量。在某些极端情况下，行业分类的不确定性将对碳排放产生巨大影响，尤其是那些与电力行业密切相关且排放强度较高的行业。

{"title":"A copula-based whole system model to understand the environmental and economic impacts of grid-scale energy storage","authors":"Fan He , Matthew Leach , Michael Short , Yurui Fan , Lirong Liu","doi":"10.1016/j.apenergy.2024.124935","DOIUrl":"10.1016/j.apenergy.2024.124935","url":null,"abstract":"<div><div>Energy storage is important in future power systems. However, the role of grid-scale energy storage in the power system and in the whole socio-economic system is unclear. A copula-based whole system model is developed to explore the economic and environmental effects of grid-scale energy storage, thus supporting the decision-making at micro and macro levels. A power system optimisation model is linked with an input-output model, and the copula function is embedded in the model to reflect the multiple and interactive uncertainties from electricity demand, emission constraints, and sector disaggregation. We conducted case studies on China and the UK in 2025 considering different storage technologies (Pumped hydro, Battery, Flywheels storage) to show the differences related with power systems and economic structures. We find that increasing energy storage capacity leads to increase in renewable generation capacity (solar generation in China and wind generation in the UK). Thus, it can reduce their total economy-wide carbon emissions. Uncertainty in sector disaggregation will have a large impact on carbon emissions in some extreme cases, especially in those sectors closely linked to the power sector and with high emission intensity.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124935"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704646","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}

引用次数: 0

A field test and evaluation of radiative cooling performance as applied on the sidewall surfaces of residential buildings in China 对应用于中国住宅建筑侧墙表面的辐射冷却性能进行实地测试和评估

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124961

Ze-Ye Wang , Xian Wu , Ming-Liang Qu , Li-Wu Fan , Zi-Tao Yu , Shu-Qin Chen , Jian Ge , Liang Wang , Sheng-Juan Dai

To investigate the energy-saving effect of radiative cooling materials when applied to the external surfaces of the side walls of buildings, the present study was carried out in a typical room-split multi-story residential building in Zhejiang province, China. The field test was conducted for a period of 259 days across all four seasons. Two types of rooms (middle rooms and side rooms) were selected to set up the control and experimental groups. By measuring the heat fluxes through the walls of both the control and experimental rooms, the effective cooling power of the radiative cooling materials was determined. The results show that the average cooling power calculated from the two sets of the middle rooms is 0.8 W/m² and 1.0 W/m², and the average cooling power of the side room is 1.0 W/m². A model of the residential building was then developed using EnergyPlus code. The measured effective cooling power of radiative cooling was embedded into the model via the “Other Equipment” module that resolves the issue of deviation in the prediction of energy-saving effect due to the spectral selectivity of radiative cooling materials at different angles. After verifying with the measured results, the model was used to evaluate the energy-saving performance of the radiatively-cooled sidewalls. Compared with traditional sidewalls, the energy-saving rate during the cooling season (from May to October) was found to be up to 1.5 % when radiative cooling is applied on the sidewalls of residential buildings in “hot summer and cold winter” regions in China.

为了研究辐射制冷材料应用于建筑物侧墙外表面时的节能效果，本研究在中国浙江省一幢典型的分室多层住宅楼中进行。实地测试在四个季节中进行了 259 天。试验选择了两种类型的房间（中间房间和两侧房间）分别作为对照组和试验组。通过测量通过对照组和实验组房间墙壁的热通量，确定了辐射制冷材料的有效制冷功率。结果表明，两组中间房间计算出的平均制冷功率分别为 0.8 W/m2 和 1.0 W/m2，边间的平均制冷功率为 1.0 W/m2。然后使用 EnergyPlus 代码建立了住宅楼模型。通过 "其他设备 "模块将实测的辐射制冷有效制冷功率嵌入模型，解决了不同角度辐射制冷材料光谱选择性导致节能效果预测偏差的问题。在与测量结果进行验证后，该模型被用于评估辐射冷却侧墙的节能性能。与传统侧墙相比，在中国 "夏热冬冷 "地区的住宅建筑侧墙采用辐射制冷时，制冷季节（5 月至 10 月）的节能率可达 1.5%。

{"title":"A field test and evaluation of radiative cooling performance as applied on the sidewall surfaces of residential buildings in China","authors":"Ze-Ye Wang , Xian Wu , Ming-Liang Qu , Li-Wu Fan , Zi-Tao Yu , Shu-Qin Chen , Jian Ge , Liang Wang , Sheng-Juan Dai","doi":"10.1016/j.apenergy.2024.124961","DOIUrl":"10.1016/j.apenergy.2024.124961","url":null,"abstract":"<div><div>To investigate the energy-saving effect of radiative cooling materials when applied to the external surfaces of the side walls of buildings, the present study was carried out in a typical room-split multi-story residential building in Zhejiang province, China. The field test was conducted for a period of 259 days across all four seasons. Two types of rooms (middle rooms and side rooms) were selected to set up the control and experimental groups. By measuring the heat fluxes through the walls of both the control and experimental rooms, the effective cooling power of the radiative cooling materials was determined. The results show that the average cooling power calculated from the two sets of the middle rooms is 0.8 W/m<sup>2</sup> and 1.0 W/m<sup>2</sup>, and the average cooling power of the side room is 1.0 W/m<sup>2</sup>. A model of the residential building was then developed using EnergyPlus code. The measured effective cooling power of radiative cooling was embedded into the model via the “Other Equipment” module that resolves the issue of deviation in the prediction of energy-saving effect due to the spectral selectivity of radiative cooling materials at different angles. After verifying with the measured results, the model was used to evaluate the energy-saving performance of the radiatively-cooled sidewalls. Compared with traditional sidewalls, the energy-saving rate during the cooling season (from May to October) was found to be up to 1.5 % when radiative cooling is applied on the sidewalls of residential buildings in “hot summer and cold winter” regions in China.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124961"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721111","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

Cooling demand reduction with nighttime natural ventilation to cool internal thermal mass under harmonic design-day weather conditions 在设计日谐波天气条件下，利用夜间自然通风冷却内部热量，减少制冷需求

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124947

Mingtong Li , Xiong Shen , Wentao Wu , Kristen Cetin , Finn Mcintyre , Liangzhu Wang , Lixing Ding , Daniel Bishop , Larry Bellamy , Meng Liu

Cooling demand is steadily increasing across different climate zones due to global warming. A potential solution for cooling demand reduction is applying nighttime natural ventilation to cool internal thermal mass. However, a simplified and accurate modelling framework to assess the technique is still missing. The goal of the study is to build that framework integrated with a validated internal thermal mass model and apply the framework to quantify the cooling demand reduction potential in a space with different thermal mass and envelope configurations and in different climate zones. Results show that using Granite as internal thermal mass is three times more effective than concrete to reduce peak cooling load. Adding too much internal thermal mass can create adverse effects on cooling load reduction. The optimum thickness of internal thermal mass is between 28 and 45 mm. Envelope construction also has an influence on the performance of nighttime cooling. Applying the technique in buildings with lightweight structures reduces peak cooling load by 35.9% more than heavyweight structures. As heavyweight structures delay the release of the daily absorbed heat and cause higher indoor air temperatures at night. The two belts between the Tropic of Cancer and 60 degrees north latitude, and between the Tropic of Capricorn and 45 degrees south latitude are suitable for nighttime natural ventilation of internal thermal mass, achieving the annual cooling demand reduction above 1.25 kWh m⁻². In Dessert climate zones, the technique exhibits an extraordinary potential to reduce cooling demand, up to 6.67 kWh m⁻² per year.

由于全球变暖，不同气候区的制冷需求都在稳步增长。减少制冷需求的一个潜在解决方案是利用夜间自然通风冷却内部热量。然而，目前仍缺少一个简化而准确的建模框架来评估这项技术。本研究的目标是建立一个与经过验证的内部热质模型相结合的框架，并应用该框架来量化不同热质和围护结构的空间以及不同气候区的制冷需求减少潜力。研究结果表明，使用花岗岩作为内热质量比使用混凝土降低峰值制冷负荷的效果要好三倍。增加过多的内部热质会对降低制冷负荷产生不利影响。内保温材料的最佳厚度在 28 至 45 毫米之间。围护结构对夜间制冷性能也有影响。在轻质结构建筑中应用该技术，峰值制冷负荷比重质结构建筑减少 35.9%。因为重型结构会延迟释放每天吸收的热量，导致夜间室内空气温度升高。北回归线和北纬 60 度之间以及南回归线和南纬 45 度之间的两个地带适合采用内部热质夜间自然通风，每年可减少 1.25 千瓦时 m-2 以上的制冷需求。在沙漠气候区，该技术在减少制冷需求方面具有非凡的潜力，每年可减少制冷需求达 6.67 千瓦时 m-2。

{"title":"Cooling demand reduction with nighttime natural ventilation to cool internal thermal mass under harmonic design-day weather conditions","authors":"Mingtong Li , Xiong Shen , Wentao Wu , Kristen Cetin , Finn Mcintyre , Liangzhu Wang , Lixing Ding , Daniel Bishop , Larry Bellamy , Meng Liu","doi":"10.1016/j.apenergy.2024.124947","DOIUrl":"10.1016/j.apenergy.2024.124947","url":null,"abstract":"<div><div>Cooling demand is steadily increasing across different climate zones due to global warming. A potential solution for cooling demand reduction is applying nighttime natural ventilation to cool internal thermal mass. However, a simplified and accurate modelling framework to assess the technique is still missing. The goal of the study is to build that framework integrated with a validated internal thermal mass model and apply the framework to quantify the cooling demand reduction potential in a space with different thermal mass and envelope configurations and in different climate zones. Results show that using Granite as internal thermal mass is three times more effective than concrete to reduce peak cooling load. Adding too much internal thermal mass can create adverse effects on cooling load reduction. The optimum thickness of internal thermal mass is between 28 and 45 mm. Envelope construction also has an influence on the performance of nighttime cooling. Applying the technique in buildings with lightweight structures reduces peak cooling load by 35.9% more than heavyweight structures. As heavyweight structures delay the release of the daily absorbed heat and cause higher indoor air temperatures at night. The two belts between the Tropic of Cancer and 60 degrees north latitude, and between the Tropic of Capricorn and 45 degrees south latitude are suitable for nighttime natural ventilation of internal thermal mass, achieving the annual cooling demand reduction above 1.25 kWh m<sup>−2</sup>. In Dessert climate zones, the technique exhibits an extraordinary potential to reduce cooling demand, up to 6.67 kWh m<sup>−2</sup> per year.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124947"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721112","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}

引用次数: 0

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124903

Ying Du , Junxiang Zhang , Yuntian Chen , Haoran Zhang , Haoran Ji , Chengshan Wang , Jinyue Yan

The resilience of distribution system is severely influenced by typhoon disasters and the secondary disasters such as floods and debris flows. The cascading propagation of typhoon disasters, coupled with the cascading propagation of faults in distribution systems, creates a dual-coupling dynamic that results in large-scale faults. The key to mitigating losses from typhoon-related cascading faults lies in understanding the potential paths of cascading propagation and taking corresponding measures to preemptively interrupt the chain propagation. In this paper, based on the analysis of actual typhoon related fault data of Guangzhou, China, we created the knowledge graph of the typhoon related cascading fault chains and modeled the chain formation mechanism, successfully integrating the distribution systems and the typhoon disaster propagation systems. We also achieved the dynamic evolution of typhoon related cascading fault chains by using system dynamics. In the case studies of Guangzhou, we selected three typical typhoon related fault scenarios, and then the proposed model is utilized to capture the fault cascading pathway, which can help mitigate typhoon related fault risks in distribution systems.

配电系统的抗灾能力受到台风灾害以及洪水和泥石流等次生灾害的严重影响。台风灾害的级联传播与配电系统故障的级联传播形成双重耦合动态，导致大规模故障。减轻台风相关级联故障损失的关键在于了解级联传播的潜在路径，并采取相应措施预先阻断链式传播。本文在分析中国广州实际台风相关故障数据的基础上，创建了台风相关级联故障链知识图谱，并对故障链的形成机理进行了建模，成功地将配电系统与台风灾害传播系统集成在一起。我们还利用系统动力学实现了台风相关级联故障链的动态演化。在广州的案例研究中，我们选取了三个典型的台风相关故障场景，然后利用所提出的模型捕捉故障级联路径，这有助于降低配电系统的台风相关故障风险。

{"title":"Typhoon related cascading fault chain dynamic evolution model and risk mitigation in distribution systems","authors":"Ying Du , Junxiang Zhang , Yuntian Chen , Haoran Zhang , Haoran Ji , Chengshan Wang , Jinyue Yan","doi":"10.1016/j.apenergy.2024.124903","DOIUrl":"10.1016/j.apenergy.2024.124903","url":null,"abstract":"<div><div>The resilience of distribution system is severely influenced by typhoon disasters and the secondary disasters such as floods and debris flows. The cascading propagation of typhoon disasters, coupled with the cascading propagation of faults in distribution systems, creates a dual-coupling dynamic that results in large-scale faults. The key to mitigating losses from typhoon-related cascading faults lies in understanding the potential paths of cascading propagation and taking corresponding measures to preemptively interrupt the chain propagation. In this paper, based on the analysis of actual typhoon related fault data of Guangzhou, China, we created the knowledge graph of the typhoon related cascading fault chains and modeled the chain formation mechanism, successfully integrating the distribution systems and the typhoon disaster propagation systems. We also achieved the dynamic evolution of typhoon related cascading fault chains by using system dynamics. In the case studies of Guangzhou, we selected three typical typhoon related fault scenarios, and then the proposed model is utilized to capture the fault cascading pathway, which can help mitigate typhoon related fault risks in distribution systems.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124903"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721169","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

Enhancing the methane production from methane hydrate by cyclic N2–CO2 gas injection and soaking method: Significance of the slow diffusion-controlled process 通过循环注入 N2-CO2 气体和浸泡法提高甲烷水合物的甲烷产量：缓慢扩散控制过程的意义

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-26 DOI: 10.1016/j.apenergy.2024.124912

Masahiro Yasue , Yoshihiro Masuda, Yunfeng Liang

Methane hydrate (MH) is a crucial lower-carbon energy resource in climate mitigation and current energy transition. A depressurization technique has been mainly attempted to produce methane gas. Simultaneously, the exchange of CH₄ from gas hydrates by N₂–CO₂ has been studied to enhance methane gas production and CO₂ sequestration. We conducted experiments with hydrate-bearing cores by applying the cyclic injection and soaking method. An N₂–CO₂ gas (ca. 60 mol% CO₂) was injected into a core during the injection period, and the core was allowed to stand stationary during the soaking period. Concurrently, a numerical model was developed to simulate the gas production performance of the cyclic injection and soaking method. This model considers a two-stage process for the gas replacement phenomena between CH₄ and (N₂ + CO₂) in the hydrate: an almost immediate replacement at the hydrate surface followed by a more gradual diffusion-controlled replacement in the subsurface hydrate layer. The rapid replacement is modeled by phase equilibrium between the vapor phase and the hydrate surface. The diffusion due to the difference in concentration of each gas component between the surface hydrate layer and the inner hydrate describes the slow gas replacement phenomenon. By repeating four cycles of soaking and injection, the experiments achieved a high CH₄ recovery factor of 67.7 % and a high exchange ratio of 54.7 %. About 18 % of the CO₂ injected gas was sequestrated. The soaking process enhanced methane recovery by 1.5 times in the recovery factor compared to the first injection production and almost half of the CH₄ molecules in MH were extracted. Our simulations demonstrated excellent agreement with experimental results, confirming the soaking process is very efficient for methane recovery. From the production history matching, the diffusion coefficient of CH₄ molecules in the solid-state MH during slow replacement phenomena was estimated to be on the order of 10⁻¹⁹ m²/s, significantly smaller than those of previous research.

甲烷水合物（MH）是气候减缓和当前能源转型中一种重要的低碳能源资源。人们主要尝试采用减压技术来生产甲烷气体。与此同时，人们还研究了用 N2-CO2 交换天然气水合物中的 CH4，以提高甲烷气体的生产和二氧化碳的封存。我们采用循环注入和浸泡法对含水合物的岩心进行了实验。在注入期向岩心注入 N2-CO2气体（约 60 mol% CO2），在浸泡期让岩心静止不动。同时，还开发了一个数值模型来模拟循环注入和浸泡法的产气性能。该模型考虑了水合物中 CH4 和（N2 + CO2）气体置换现象的两个阶段：在水合物表面几乎立即置换，然后在地下水合物层中进行更渐进的扩散控制置换。快速置换是通过气相和水合物表面之间的相平衡来模拟的。表面水合物层和内部水合物之间每种气体成分的浓度差引起的扩散描述了缓慢的气体置换现象。通过重复四次浸泡和注入循环，实验实现了 67.7% 的高 CH4 回收率和 54.7% 的高交换率。大约 18% 的二氧化碳注入气体被封存。与首次注入生产相比，浸泡过程将甲烷回收率提高了 1.5 倍，MH 中近一半的 CH4 分子被提取出来。我们的模拟结果与实验结果非常吻合，证实了浸泡过程对甲烷回收非常有效。根据生产历史匹配，估计在缓慢置换现象中，固态 MH 中 CH4 分子的扩散系数约为 10-19 m2/s，明显小于之前的研究。

{"title":"Enhancing the methane production from methane hydrate by cyclic N2–CO2 gas injection and soaking method: Significance of the slow diffusion-controlled process","authors":"Masahiro Yasue , Yoshihiro Masuda, Yunfeng Liang","doi":"10.1016/j.apenergy.2024.124912","DOIUrl":"10.1016/j.apenergy.2024.124912","url":null,"abstract":"<div><div>Methane hydrate (MH) is a crucial lower-carbon energy resource in climate mitigation and current energy transition. A depressurization technique has been mainly attempted to produce methane gas. Simultaneously, the exchange of CH<sub>4</sub> from gas hydrates by N<sub>2</sub>–CO<sub>2</sub> has been studied to enhance methane gas production and CO<sub>2</sub> sequestration. We conducted experiments with hydrate-bearing cores by applying the cyclic injection and soaking method. An N<sub>2</sub>–CO<sub>2</sub> gas (ca. 60 mol% CO<sub>2</sub>) was injected into a core during the injection period, and the core was allowed to stand stationary during the soaking period. Concurrently, a numerical model was developed to simulate the gas production performance of the cyclic injection and soaking method. This model considers a two-stage process for the gas replacement phenomena between CH<sub>4</sub> and (N<sub>2</sub> + CO<sub>2</sub>) in the hydrate: an almost immediate replacement at the hydrate surface followed by a more gradual diffusion-controlled replacement in the subsurface hydrate layer. The rapid replacement is modeled by phase equilibrium between the vapor phase and the hydrate surface. The diffusion due to the difference in concentration of each gas component between the surface hydrate layer and the inner hydrate describes the slow gas replacement phenomenon. By repeating four cycles of soaking and injection, the experiments achieved a high CH<sub>4</sub> recovery factor of 67.7 % and a high exchange ratio of 54.7 %. About 18 % of the CO<sub>2</sub> injected gas was sequestrated. The soaking process enhanced methane recovery by 1.5 times in the recovery factor compared to the first injection production and almost half of the CH<sub>4</sub> molecules in MH were extracted. Our simulations demonstrated excellent agreement with experimental results, confirming the soaking process is very efficient for methane recovery. From the production history matching, the diffusion coefficient of CH<sub>4</sub> molecules in the solid-state MH during slow replacement phenomena was estimated to be on the order of 10<sup>−19</sup> m<sup>2</sup>/s, significantly smaller than those of previous research.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124912"},"PeriodicalIF":10.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704831","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}

引用次数: 0

Performance of district energy system under changing climate: A case study of Shenzhen 气候变化下的区域能源系统性能：深圳案例研究

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-25 DOI: 10.1016/j.apenergy.2024.124986

Pengyuan Shen , Yuchen Ji , Menglei Zhong

The impacts of climate change on the economic performance of different district energy systems (DES) are rarely evaluated. In this research, the performance of both conventional and combined heat and power systems (CCHP) are simulated and compared by modeling and analyzing the DES. Building simulation is conducted by using the downscaled future hourly weather data in the period of 2050–2060 under two future climate scenarios. Optimal sizing and operation schedule of the DES are determined in both current and future climate. Lifetime annualized heating and cooling per area cost (HC) is used to compare the economic performance of the district system. It is found that the annul cooling load in RCP4.5 and RCP8.5 increases by 6 % and 9.68 %. The HC of the conventional system ranges from 122.72 Yuan/m² to 141.1 Yuan/m² with a range of profit rate from 5 % to 20 % under various climate scenarios, and that number for the CCHP is from 72.36 Yuan/m² to 95.24 Yuan/m². Compared with the conventional system, the optimal CCHP system charges 32.5 % to 41 % less on the building end users if the lifetime profit rate is to be maintained between 5 % to 20 %.

气候变化对不同区域能源系统（DES）经济效益的影响很少得到评估。在本研究中，通过对 DES 进行建模和分析，对传统系统和热电联产系统 (CCHP) 的性能进行了模拟和比较。在两种未来气候情景下，使用 2050-2060 年期间的降尺度未来每小时天气数据进行建筑物模拟。在当前和未来气候条件下，确定了 DES 的最佳尺寸和运行时间表。使用终身年化供热和制冷单位面积成本（HC）来比较区域系统的经济性能。结果发现，在 RCP4.5 和 RCP8.5 条件下，年制冷负荷分别增加了 6% 和 9.68%。传统系统的 HC 值为 122.72 元/m2 至 141.1 元/m2，在各种气候情景下的利润率范围为 5 % 至 20 %，而 CCHP 的 HC 值为 72.36 元/m2 至 95.24 元/m2。与传统系统相比，如果终生利润率保持在 5%至 20%之间，最佳冷热电三联供系统对建筑最终用户的收费将减少 32.5%至 41%。

{"title":"Performance of district energy system under changing climate: A case study of Shenzhen","authors":"Pengyuan Shen , Yuchen Ji , Menglei Zhong","doi":"10.1016/j.apenergy.2024.124986","DOIUrl":"10.1016/j.apenergy.2024.124986","url":null,"abstract":"<div><div>The impacts of climate change on the economic performance of different district energy systems (DES) are rarely evaluated. In this research, the performance of both conventional and combined heat and power systems (CCHP) are simulated and compared by modeling and analyzing the DES. Building simulation is conducted by using the downscaled future hourly weather data in the period of 2050–2060 under two future climate scenarios. Optimal sizing and operation schedule of the DES are determined in both current and future climate. Lifetime annualized heating and cooling per area cost (HC) is used to compare the economic performance of the district system. It is found that the annul cooling load in RCP4.5 and RCP8.5 increases by 6 % and 9.68 %. The HC of the conventional system ranges from 122.72 Yuan/m<sup>2</sup> to 141.1 Yuan/m<sup>2</sup> with a range of profit rate from 5 % to 20 % under various climate scenarios, and that number for the CCHP is from 72.36 Yuan/m<sup>2</sup> to 95.24 Yuan/m<sup>2</sup>. Compared with the conventional system, the optimal CCHP system charges 32.5 % to 41 % less on the building end users if the lifetime profit rate is to be maintained between 5 % to 20 %.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124986"},"PeriodicalIF":10.1,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704645","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

Secure frequency regulation in power system: A comprehensive defense strategy against FDI, DoS, and latency cyber-attacks 电力系统的安全频率调节：针对 FDI、DoS 和延迟网络攻击的综合防御策略

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-25 DOI: 10.1016/j.apenergy.2024.124772

Shaohua Yang , Keng-Weng Lao , Hongxun Hui , Jinshuo Su , Sheng Wang

Maintaining frequency is crucial for the security of power systems, while deep cyber–physical interactions make frequency regulation susceptible to cyber-attack risks. False data injection (FDI) attacks, denial-of-service (DoS) attacks, and latency attacks are typical types of cyber-attacks prevalent in power systems, each capable of deteriorating system frequency through distinct mechanisms and posing serious security risks. However, existing studies on frequency regulation lack security aspects that can comprehensively address all these attack types. To fill this gap, this paper investigates a security strategy to safeguard power system frequency regulation. First, considering all these attacks, the system frequency regulation system is modeled to reveal the severity of cyber-security problems, specifically the failure to maintain frequency due to cyber-attacks. Moreover, a cyber-resilient control (CRC) strategy is developed to counter FDI, DoS, and latency attacks comprehensively. The CRC strategy involves a two-step process, including a safety surface and auxiliary trajectory control. The safety surface serves as a defensive barrier against multiple cyber-attacks, while the auxiliary trajectory control activates the safety surface’s defense capability, thereby ensuring the security of system frequency. Furthermore, rigorous proofs are given based on Lyapunov theorem, demonstrating that system stability can be guaranteed by the developed CRC strategy, even under multiple types of cyber-attacks. Finally, test results confirm the efficacy of the CRC strategy. For instance, it prevents pre-existing frequency oscillations and destabilization, and also reduces the maximum frequency deviation by approximately 96.61% under multiple cyber-attacks. Therefore, the developed CRC strategy can comprehensively defend against FDI, DoS, and latency cyber-attacks, significantly contributing to the power system security.

保持频率对电力系统的安全至关重要，而深层次的网络-物理相互作用使频率调节容易受到网络攻击风险的影响。虚假数据注入（FDI）攻击、拒绝服务（DoS）攻击和延迟攻击是电力系统中普遍存在的典型网络攻击类型，每种攻击都能通过不同的机制使系统频率恶化，并带来严重的安全风险。然而，现有的频率调节研究缺乏能全面应对所有这些攻击类型的安全方面。为了填补这一空白，本文研究了一种保障电力系统频率调节的安全策略。首先，考虑到所有这些攻击，对系统频率调节系统进行建模，以揭示网络安全问题的严重性，特别是网络攻击导致的频率失稳。此外，还开发了一种网络弹性控制（CRC）策略，以全面应对 FDI、DoS 和延迟攻击。CRC 策略包括两个步骤，包括安全面和辅助轨迹控制。安全面是抵御多种网络攻击的防御屏障，而辅助轨迹控制则激活安全面的防御能力，从而确保系统频率的安全性。此外，基于李亚普诺夫定理给出了严格的证明，表明即使在多种类型的网络攻击下，所开发的 CRC 策略也能保证系统的稳定性。最后，测试结果证实了 CRC 策略的有效性。例如，它能防止预先存在的频率振荡和失稳，还能在多种网络攻击下将最大频率偏差降低约 96.61%。因此，所开发的 CRC 策略可以全面抵御 FDI、DoS 和延迟网络攻击，极大地促进了电力系统安全。

{"title":"Secure frequency regulation in power system: A comprehensive defense strategy against FDI, DoS, and latency cyber-attacks","authors":"Shaohua Yang , Keng-Weng Lao , Hongxun Hui , Jinshuo Su , Sheng Wang","doi":"10.1016/j.apenergy.2024.124772","DOIUrl":"10.1016/j.apenergy.2024.124772","url":null,"abstract":"<div><div>Maintaining frequency is crucial for the security of power systems, while deep cyber–physical interactions make frequency regulation susceptible to cyber-attack risks. False data injection (FDI) attacks, denial-of-service (DoS) attacks, and latency attacks are typical types of cyber-attacks prevalent in power systems, each capable of deteriorating system frequency through distinct mechanisms and posing serious security risks. However, existing studies on frequency regulation lack security aspects that can comprehensively address all these attack types. To fill this gap, this paper investigates a security strategy to safeguard power system frequency regulation. First, considering all these attacks, the system frequency regulation system is modeled to reveal the severity of cyber-security problems, specifically the failure to maintain frequency due to cyber-attacks. Moreover, a cyber-resilient control (CRC) strategy is developed to counter FDI, DoS, and latency attacks comprehensively. The CRC strategy involves a two-step process, including a safety surface and auxiliary trajectory control. The safety surface serves as a defensive barrier against multiple cyber-attacks, while the auxiliary trajectory control activates the safety surface’s defense capability, thereby ensuring the security of system frequency. Furthermore, rigorous proofs are given based on Lyapunov theorem, demonstrating that system stability can be guaranteed by the developed CRC strategy, even under multiple types of cyber-attacks. Finally, test results confirm the efficacy of the CRC strategy. For instance, it prevents pre-existing frequency oscillations and destabilization, and also reduces the maximum frequency deviation by approximately 96.61% under multiple cyber-attacks. Therefore, the developed CRC strategy can comprehensively defend against FDI, DoS, and latency cyber-attacks, significantly contributing to the power system security.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124772"},"PeriodicalIF":10.1,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704642","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

Feasibility-guaranteed machine learning unit commitment: Fuzzy Optimization approaches 有可行性保证的机器学习单位承诺：模糊优化方法

IF 10.1 1区工程技术 Q1 ENERGY & FUELS

Applied Energy

Pub Date : 2024-11-25 DOI: 10.1016/j.apenergy.2024.124923

Bala Venkatesh , Mohamed Ibrahim Abdelaziz Shekeew , Jessie Ma

The unit commitment (UC) problem is solved several times daily in a limited amount of time and is commonly formulated using mixed-integer linear programs (MILP). However, solution time for MILP formulation increases exponentially with the number of binary variables required. To address this, machine learning (ML) models have been attempted with limited success as they cannot be trained for all scenarios, whereby they may contain false predictions leading to infeasibility, hindering their practical applicability. To overcome these issues, we first propose a hybrid deep learning model comprising a convolutional neural network (CNN) and bidirectional long-short-term memory (BiLSTM) to predict the UC decisions. Second, we incorporate these predictions as non-binding fuzzy constraints, enhancing the traditional UC model and creating an ML-fuzzy UC model. Two implementations of non-binding fuzzy constraints are studied. The first develops each ML decision variable as a separate fuzzy set, while the second creates one fuzzy set per hour, considering all decisions within. Introducing ML-UC decisions as non-binding fuzzy constraints ensures the ML-fuzzy UC model has a feasible solution if the basic MILP-UC problem does, while leveraging ML predictions. Moreover, the proposed model benefits from a reduced solution space, leading to substantial reductions in computing time. Results on IEEE 118-bus and Polish 2383-bus systems demonstrate 92 % and 89 % computation time reductions for both systems, respectively and achieve 100 % feasibility for both seen and unseen datasets when the basic MILP-UC problem has a feasible solution.

单位承诺（UC）问题每天都要在有限的时间内多次求解，通常采用混合整数线性方程组（MILP）。然而，MILP 的求解时间会随着所需的二进制变量数量呈指数级增长。为了解决这个问题，人们尝试了机器学习（ML）模型，但成效有限，因为这些模型无法针对所有情况进行训练，因此可能包含错误预测，导致不可行性，阻碍了其实际应用。为了克服这些问题，我们首先提出了一种混合深度学习模型，该模型由卷积神经网络（CNN）和双向长短期记忆（BiLSTM）组成，用于预测统一通信决策。其次，我们将这些预测作为非约束性模糊约束纳入其中，从而增强了传统的统一通信模型，并创建了一个 ML-fuzzy 统一通信模型。我们研究了两种非约束模糊约束的实现方法。第一种方法是将每个 ML 决策变量发展为一个单独的模糊集，第二种方法是每小时创建一个模糊集，考虑其中的所有决策。如果基本的 MILP-UC 问题可行，那么将 ML-UC 决策作为非约束模糊约束引入，就能确保 ML-fuzzy UC 模型有一个可行的解决方案，同时充分利用 ML 预测。此外，所提出的模型还能缩小求解空间，从而大幅减少计算时间。对 IEEE 118 总线和波兰 2383 总线系统的研究结果表明，这两个系统的计算时间分别减少了 92% 和 89%，当基本 MILP-UC 问题有可行解时，可见数据集和未见数据集的可行性都达到了 100%。

{"title":"Feasibility-guaranteed machine learning unit commitment: Fuzzy Optimization approaches","authors":"Bala Venkatesh , Mohamed Ibrahim Abdelaziz Shekeew , Jessie Ma","doi":"10.1016/j.apenergy.2024.124923","DOIUrl":"10.1016/j.apenergy.2024.124923","url":null,"abstract":"<div><div>The unit commitment (UC) problem is solved several times daily in a limited amount of time and is commonly formulated using mixed-integer linear programs (MILP). However, solution time for MILP formulation increases exponentially with the number of binary variables required. To address this, machine learning (ML) models have been attempted with limited success as they cannot be trained for all scenarios, whereby they may contain false predictions leading to infeasibility, hindering their practical applicability. To overcome these issues, we first propose a hybrid deep learning model comprising a convolutional neural network (CNN) and bidirectional long-short-term memory (BiLSTM) to predict the UC decisions. Second, we incorporate these predictions as non-binding fuzzy constraints, enhancing the traditional UC model and creating an ML-fuzzy UC model. Two implementations of non-binding fuzzy constraints are studied. The first develops each ML decision variable as a separate fuzzy set, while the second creates one fuzzy set per hour, considering all decisions within. Introducing ML-UC decisions as non-binding fuzzy constraints ensures the ML-fuzzy UC model has a feasible solution if the basic MILP-UC problem does, while leveraging ML predictions. Moreover, the proposed model benefits from a reduced solution space, leading to substantial reductions in computing time. Results on IEEE 118-bus and Polish 2383-bus systems demonstrate 92 % and 89 % computation time reductions for both systems, respectively and achieve 100 % feasibility for both seen and unseen datasets when the basic MILP-UC problem has a feasible solution.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"379 ","pages":"Article 124923"},"PeriodicalIF":10.1,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704644","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}

引用次数: 0