首页 > 最新文献

IEEE Transactions on Sustainable Energy最新文献

英文 中文
Graph-Based Large Scale Probabilistic PV Power Forecasting Insensitive to Space-Time Missing Data 对时空缺失数据不敏感的基于图的大规模概率光伏功率预测
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-21 DOI: 10.1109/TSTE.2024.3447023
Keunju Song;Minsoo Kim;Hongseok Kim
In recent years, power systems integrated with distributed energy resources (DERs) have been considered to mitigate climate change. However, this makes power systems even more uncertain and complex, so uncertainty-aware accurate forecasting needs to be considered for the massive penetration of renewable energy. To this end, we propose a scalable and missing-insensitive framework for probabilistic multi-site photovoltaic (PV) power forecasting, specifically focused on large-scale PV sites and space-time missing data. By leveraging the graph neural network (GNN), the proposed scalable graph learning mechanism with random coarse graph attention and probabilistic spatio-temporal learning performs efficiently for large-scale PV sites in terms of forecasting accuracy and model training complexity. At the same time, our framework adaptively imputes the missing PV data in the space and time domain, respectively. Ablation study results demonstrate that our framework is effective for extracting complex spatial-temporal features across large-scale PV sites. Under extensive experiments, our framework shows 7$-$10% and 6$-$25% improvement on average for over 1600 PV sites and three types of space-time missing data, which ensures accurate and stable forecasting.
近年来,分布式能源集成电力系统被认为是减缓气候变化的重要手段。然而,这使得电力系统更加不确定和复杂,因此可再生能源的大规模渗透需要考虑具有不确定性的准确预测。为此,我们提出了一个可扩展和缺失不敏感的框架,用于概率多站点光伏(PV)功率预测,特别关注大规模光伏站点和时空缺失数据。利用图神经网络(GNN),本文提出的具有随机粗图注意和概率时空学习的可扩展图学习机制在预测精度和模型训练复杂度方面对大规模PV站点具有较好的效果。同时,我们的框架分别在空间和时间域自适应地对缺失的PV数据进行补全。消融研究结果表明,我们的框架可以有效地提取大型PV站点的复杂时空特征。在大量的实验中,我们的框架对1600多个光伏站点和三种时空缺失数据的预测平均提高了7 ~ 10%和6 ~ 25%,确保了预测的准确性和稳定性。
{"title":"Graph-Based Large Scale Probabilistic PV Power Forecasting Insensitive to Space-Time Missing Data","authors":"Keunju Song;Minsoo Kim;Hongseok Kim","doi":"10.1109/TSTE.2024.3447023","DOIUrl":"10.1109/TSTE.2024.3447023","url":null,"abstract":"In recent years, power systems integrated with distributed energy resources (DERs) have been considered to mitigate climate change. However, this makes power systems even more uncertain and complex, so uncertainty-aware accurate forecasting needs to be considered for the massive penetration of renewable energy. To this end, we propose a scalable and missing-insensitive framework for probabilistic multi-site photovoltaic (PV) power forecasting, specifically focused on large-scale PV sites and space-time missing data. By leveraging the graph neural network (GNN), the proposed scalable graph learning mechanism with random coarse graph attention and probabilistic spatio-temporal learning performs efficiently for large-scale PV sites in terms of forecasting accuracy and model training complexity. At the same time, our framework adaptively imputes the missing PV data in the space and time domain, respectively. Ablation study results demonstrate that our framework is effective for extracting complex spatial-temporal features across large-scale PV sites. Under extensive experiments, our framework shows 7\u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u000010% and 6\u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u000025% improvement on average for over 1600 PV sites and three types of space-time missing data, which ensures accurate and stable forecasting.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 1","pages":"160-173"},"PeriodicalIF":8.6,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219459","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
Shape Optimization of a Point Absorber Wave Energy Converter for Reduced Current Drag and Improved Wave Energy Capture Using Neural Networks and Genetic Algorithms 利用神经网络和遗传算法优化自反应点吸收器波能转换器的形状,以减少电流阻力并提高波能捕获率
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-16 DOI: 10.1109/TSTE.2024.3443117
Weihan Lin;Xiaofan Li;Lei Zuo
The shape of the floating buoy of a point absorber wave energy converter (WEC) plays a crucial role in both wave energy harvesting and current drag reduction. In this study, an approach to optimizing the buoy hull geometry with a neural network that replaces the hydrodynamic analysis software is presented, aimed at reducing the ocean current drag force while improving wave energy captured. A new parametric model is introduced to describe the complex shape of the buoy by utilizing the control points of non-uniform rational b-splines. A neural network is developed to significantly reduce the computational time compared to traditional hydrodynamic simulation methods. The optimal hull shape of the buoy is determined by solving an optimization problem using a genetic algorithm, a global optimization technique. The results of the case studies show that the optimal buoy hull shape reduces 68.7% and 71.1% of the current drag, and 50% of mooring line forces compared to the cylinder-shaped buoy and the optimal-power-shaped hull from literature. The optimal buoy hull shape increases the wave energy extraction by 46.1% compared to the thin-ship-shaped buoy but performs 21.1% worse than the optimal-power-shaped hull from the literature.
点吸收式波浪能转换器(WEC)浮标的形状在收集波浪能和减少洋流阻力方面起着至关重要的作用。本研究提出了一种利用神经网络优化浮标船体几何形状的方法,该方法取代了流体力学分析软件,旨在减少洋流阻力,同时提高波浪能捕获效率。通过利用非均匀有理 b-样条曲线的控制点,引入了一个新的参数模型来描述浮标的复杂形状。与传统的流体力学模拟方法相比,神经网络的开发大大缩短了计算时间。通过使用遗传算法(一种全局优化技术)解决优化问题,确定了浮标的最佳船体形状。案例研究结果表明,与文献中的圆柱形浮标和最优动力型船体相比,最优浮标船体形状分别减少了 68.7% 和 71.1% 的水流阻力,以及 50% 的系泊线力。与薄船形浮标相比,最佳浮标船体形状提高了 46.1%的波浪能提取率,但与文献中的最佳动力型船体相比,性能降低了 21.1%。
{"title":"Shape Optimization of a Point Absorber Wave Energy Converter for Reduced Current Drag and Improved Wave Energy Capture Using Neural Networks and Genetic Algorithms","authors":"Weihan Lin;Xiaofan Li;Lei Zuo","doi":"10.1109/TSTE.2024.3443117","DOIUrl":"10.1109/TSTE.2024.3443117","url":null,"abstract":"The shape of the floating buoy of a point absorber wave energy converter (WEC) plays a crucial role in both wave energy harvesting and current drag reduction. In this study, an approach to optimizing the buoy hull geometry with a neural network that replaces the hydrodynamic analysis software is presented, aimed at reducing the ocean current drag force while improving wave energy captured. A new parametric model is introduced to describe the complex shape of the buoy by utilizing the control points of non-uniform rational b-splines. A neural network is developed to significantly reduce the computational time compared to traditional hydrodynamic simulation methods. The optimal hull shape of the buoy is determined by solving an optimization problem using a genetic algorithm, a global optimization technique. The results of the case studies show that the optimal buoy hull shape reduces 68.7% and 71.1% of the current drag, and 50% of mooring line forces compared to the cylinder-shaped buoy and the optimal-power-shaped hull from literature. The optimal buoy hull shape increases the wave energy extraction by 46.1% compared to the thin-ship-shaped buoy but performs 21.1% worse than the optimal-power-shaped hull from the literature.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2758-2768"},"PeriodicalIF":8.6,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219462","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
An Adaptive Transfer Learning Framework for Data-Scarce HVAC Power Consumption Forecasting 用于数据保密暖通空调耗电量预测的自适应迁移学习框架
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-16 DOI: 10.1109/TSTE.2024.3444689
Yanan Zhang;Gan Zhou;Zhan Liu;Li Huang;Yucheng Ren
Heating, ventilation, and air conditioning (HVAC) systems constitute a large proportion of building energy consumption and provide considerable potential for power grid regulation. While the HVAC power consumption forecasting task is generally straightforward with sufficient historical data, it becomes challenging when dealing with scarce data. Such situation is common in cases of intermittent data collection or early system implementations, where precise forecasting is required despite limited data available. Considering accessible datasets from nearby or similar HVAC systems through energy management systems, this paper proposes an adaptive transfer learning framework to tackle this issue. Specifically, the framework leverages diverse source domains, employing model-level regularizers to quantify domain discrepancies and an adaptive parameter regulation mechanism to dynamically align source domains with the target domain. Embedded within the framework, a unique deep learning architecture with attention mechanisms is proposed, capable of identifying complex temporal patterns and hierarchical features in HVAC systems. Experiments on public HVAC datasets demonstrate the generalization, accuracy and robustness of our methodology under diverse data-scarce scenarios.
供暖、通风和空调(HVAC)系统在建筑能耗中占很大比例,并为电网调节提供了相当大的潜力。虽然在历史数据充足的情况下,暖通空调耗电量预测任务一般比较简单,但在数据匮乏的情况下,这项任务就变得具有挑战性。这种情况常见于数据收集时断时续或系统实施初期,尽管可用数据有限,但仍需要进行精确预测。考虑到可通过能源管理系统从附近或类似的暖通空调系统获取数据集,本文提出了一种自适应迁移学习框架来解决这一问题。具体来说,该框架利用不同的源域,采用模型级正则表达式量化域差异,并采用自适应参数调节机制动态调整源域与目标域。在该框架中,提出了一种独特的深度学习架构,该架构具有注意力机制,能够识别暖通空调系统中复杂的时间模式和分层特征。在公共暖通空调数据集上进行的实验证明了我们的方法在各种数据稀缺场景下的通用性、准确性和鲁棒性。
{"title":"An Adaptive Transfer Learning Framework for Data-Scarce HVAC Power Consumption Forecasting","authors":"Yanan Zhang;Gan Zhou;Zhan Liu;Li Huang;Yucheng Ren","doi":"10.1109/TSTE.2024.3444689","DOIUrl":"10.1109/TSTE.2024.3444689","url":null,"abstract":"Heating, ventilation, and air conditioning (HVAC) systems constitute a large proportion of building energy consumption and provide considerable potential for power grid regulation. While the HVAC power consumption forecasting task is generally straightforward with sufficient historical data, it becomes challenging when dealing with scarce data. Such situation is common in cases of intermittent data collection or early system implementations, where precise forecasting is required despite limited data available. Considering accessible datasets from nearby or similar HVAC systems through energy management systems, this paper proposes an adaptive transfer learning framework to tackle this issue. Specifically, the framework leverages diverse source domains, employing model-level regularizers to quantify domain discrepancies and an adaptive parameter regulation mechanism to dynamically align source domains with the target domain. Embedded within the framework, a unique deep learning architecture with attention mechanisms is proposed, capable of identifying complex temporal patterns and hierarchical features in HVAC systems. Experiments on public HVAC datasets demonstrate the generalization, accuracy and robustness of our methodology under diverse data-scarce scenarios.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2815-2825"},"PeriodicalIF":8.6,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219460","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 Comprehensive Control Strategy for F-SOP Considering Three-Phase Imbalance and Economic Operation in ISLDN 考虑 ISLDN 中三相不平衡和经济运行的 F-SOP 综合控制策略
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-16 DOI: 10.1109/TSTE.2024.3444794
Xin Wang;Qi Guo;Chunming Tu;Liang Che;Zhong Xu;Fan Xiao;Tianlin Li;Leiqi Chen
With the increasing integration of renewable energy sources (RES) and single-phase loads, three-phase imbalance and transformer lightly/heavily loaded operation issues has become more prominent in low-voltage distribution networks (LDN). However, existing research on interconnected systems of LDN (ISLDN) rarely addresses the comprehensive management of both three-phase imbalance and lightly/heavily loaded operation issues. To this end, a comprehensive control strategy for three-phase imbalance and lightly/heavily loaded operation in ISLDN based on a four-leg soft open point (F-SOP) is proposed in this paper. Firstly, the comprehensive loss characteristics model of ISLDN including the F-SOP and the transformer are established, revealing that both imbalance and load rate can affect the equipment efficiency. Secondly, considering the objective of minimizing power loss, an optimization dispatch strategy with constraints of three-phase imbalance and the optimal economic operation area is proposed to obtain the dispatch power commands for the F-SOP. Furthermore, an improved peer-to-peer control for F-SOP is proposed to ensure the conduct of the optimization dispatch strategy and enhance stability performance of system. Finally, the effectiveness and feasibility of the proposed comprehensive control strategy are validated by the simulations and experiments. The results show that comprehensive control of lightly/heavily loaded operation and three-phase imbalance in the ISLDN can significantly reduce daily power loss by 62%, improving system operation reliability and economy.
随着可再生能源与单相负荷一体化程度的提高,低压配电网中三相不平衡和变压器轻、重负荷运行问题日益突出。然而,现有的LDN互连系统(ISLDN)研究很少涉及三相不平衡和轻/重负载运行问题的综合管理。为此,本文提出了一种基于四支路软开点(F-SOP)的ISLDN三相不平衡和轻/重负载综合控制策略。首先,建立了包括F-SOP和变压器在内的ISLDN的综合损耗特性模型,揭示了不平衡和负荷率都会影响设备效率。其次,以电力损耗最小为目标,提出了三相不平衡约束和最优经济运行区域约束下的优化调度策略,得到了F-SOP的电力调度指令;在此基础上,提出了一种改进的F-SOP点对点控制方法,保证了优化调度策略的实施,提高了系统的稳定性。最后,通过仿真和实验验证了所提综合控制策略的有效性和可行性。结果表明,综合控制ISLDN轻、重负荷运行和三相不平衡,可使ISLDN日功率损耗显著降低62%,提高系统运行可靠性和经济性。
{"title":"A Comprehensive Control Strategy for F-SOP Considering Three-Phase Imbalance and Economic Operation in ISLDN","authors":"Xin Wang;Qi Guo;Chunming Tu;Liang Che;Zhong Xu;Fan Xiao;Tianlin Li;Leiqi Chen","doi":"10.1109/TSTE.2024.3444794","DOIUrl":"10.1109/TSTE.2024.3444794","url":null,"abstract":"With the increasing integration of renewable energy sources (RES) and single-phase loads, three-phase imbalance and transformer lightly/heavily loaded operation issues has become more prominent in low-voltage distribution networks (LDN). However, existing research on interconnected systems of LDN (ISLDN) rarely addresses the comprehensive management of both three-phase imbalance and lightly/heavily loaded operation issues. To this end, a comprehensive control strategy for three-phase imbalance and lightly/heavily loaded operation in ISLDN based on a four-leg soft open point (F-SOP) is proposed in this paper. Firstly, the comprehensive loss characteristics model of ISLDN including the F-SOP and the transformer are established, revealing that both imbalance and load rate can affect the equipment efficiency. Secondly, considering the objective of minimizing power loss, an optimization dispatch strategy with constraints of three-phase imbalance and the optimal economic operation area is proposed to obtain the dispatch power commands for the F-SOP. Furthermore, an improved peer-to-peer control for F-SOP is proposed to ensure the conduct of the optimization dispatch strategy and enhance stability performance of system. Finally, the effectiveness and feasibility of the proposed comprehensive control strategy are validated by the simulations and experiments. The results show that comprehensive control of lightly/heavily loaded operation and three-phase imbalance in the ISLDN can significantly reduce daily power loss by 62%, improving system operation reliability and economy.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 1","pages":"149-159"},"PeriodicalIF":8.6,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219461","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
Comparative Evaluation of Converter Control Impact on Torsional Dynamics of Type-IV Grid-Forming Wind Turbines 变流器控制对 IV 型并网风力发电机扭转动力学影响的比较评估
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-15 DOI: 10.1109/TSTE.2024.3444474
Shiyi Liu;Razvan Gabriel Cirstea;Heng Wu;Theo Bosma;Xiongfei Wang
This paper explores the impact of back-to-back converter control strategies on the torsional dynamics of grid-forming permanent magnet synchronous generator wind turbines (GFM-WTs). Two general converter control methods for GFM-WTs, distinguished by the placement of dc-link voltage control (DVC)–either in the machine-side converter or the grid-side converter, are evaluated through the complex torque coefficient method to offer a theoretical basis. It reveals that a negative damping is introduced when the DVC is with the machine-side converter. Then, to further characterize the parametric impacts of electrical and mechanical system constants and controller gains, the sensitivity analysis is performed by employing the partial derivative algorithm, which is based on the feedforward neural network training. It is found that the converter control has a limited impact on the damped frequency in both GFM converter control methods. Finally, electromagnetic simulations based on full-order nonlinear models of GFM-WTs are carried out to confirm the theoretical findings.
本文探讨了背靠背变流器控制策略对并网永磁同步发电机风力涡轮机(GFM-WTs)扭转动力学的影响。本文通过复转矩系数法评估了用于 GFM-WT 的两种通用变流器控制方法,为其提供了理论依据,这两种方法的区别在于直流链路电压控制(DVC)的位置,即在机器侧变流器中还是在电网侧变流器中。结果表明,当 DVC 位于机器侧变流器时,会产生负阻尼。然后,为了进一步确定电气和机械系统常数及控制器增益对参数的影响,采用基于前馈神经网络训练的偏导数算法进行了灵敏度分析。结果发现,在两种 GFM 变流器控制方法中,变流器控制对阻尼频率的影响都很有限。最后,基于 GFM-WT 的全阶非线性模型进行了电磁仿真,以证实理论结论。
{"title":"Comparative Evaluation of Converter Control Impact on Torsional Dynamics of Type-IV Grid-Forming Wind Turbines","authors":"Shiyi Liu;Razvan Gabriel Cirstea;Heng Wu;Theo Bosma;Xiongfei Wang","doi":"10.1109/TSTE.2024.3444474","DOIUrl":"10.1109/TSTE.2024.3444474","url":null,"abstract":"This paper explores the impact of back-to-back converter control strategies on the torsional dynamics of grid-forming permanent magnet synchronous generator wind turbines (GFM-WTs). Two general converter control methods for GFM-WTs, distinguished by the placement of dc-link voltage control (DVC)–either in the machine-side converter or the grid-side converter, are evaluated through the complex torque coefficient method to offer a theoretical basis. It reveals that a negative damping is introduced when the DVC is with the machine-side converter. Then, to further characterize the parametric impacts of electrical and mechanical system constants and controller gains, the sensitivity analysis is performed by employing the partial derivative algorithm, which is based on the feedforward neural network training. It is found that the converter control has a limited impact on the damped frequency in both GFM converter control methods. Finally, electromagnetic simulations based on full-order nonlinear models of GFM-WTs are carried out to confirm the theoretical findings.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2803-2814"},"PeriodicalIF":8.6,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219463","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
Deep Learning-Based Failure Prognostic Model for PV Inverter Using Field Measurements 利用现场测量建立基于深度学习的光伏逆变器故障诊断模型
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-14 DOI: 10.1109/TSTE.2024.3443234
Liming Liu;Yi Luo;Zhaoyu Wang;Feng Qiu;Shijia Zhao;Murat Yildirim;Rajarshi Roychowdhury
This study presents a novel approach for the precise monitoring and prognosis of photovoltaic (PV) inverter status, which is crucial for the proactive maintenance of PV systems. It addresses the gaps in traditional model-based methods, which tend to neglect the overall reliability of inverters, and the limitations of data-driven approaches that largely depend on simulated data. This research presents a robust solution applicable to real-world scenarios. The proposed data-driven model for PV inverter failure prognosis employs actual inverter measurements, integrating various operational and weather-related factors based on domain knowledge. This approach effectively represents inverter stressors and operational status. Utilizing an Enhanced Siamese Convolutional Neural Network (ESCNN), the model merges operational data with domain knowledge features, redefining the prognosis challenge as a classification task. Furthermore, the paper discusses an ESCNN-based real-time inverter failure monitoring method developed on the well-trained model. The proposed models are rigorously trained and tested with real inverter data and a novel filtering method is included to address accidental failures in practical scenarios. The results validate the model's efficacy, and the directions for future research are also outlined.
本研究提出了一种精确监测和预测光伏逆变器状态的新方法,这对光伏系统的主动维护至关重要。它弥补了传统基于模型方法的不足(这种方法往往忽视逆变器的整体可靠性),并解决了数据驱动方法的局限性(这种方法主要依赖于模拟数据)。这项研究提出了一种适用于现实世界场景的稳健解决方案。所提出的光伏逆变器故障预测数据驱动模型采用了实际的逆变器测量数据,并根据领域知识整合了各种运行和天气相关因素。这种方法能有效反映逆变器的压力因素和运行状态。利用增强型连通卷积神经网络(ESCNN),该模型将运行数据与领域知识特征相结合,将预报挑战重新定义为分类任务。此外,本文还讨论了在训练有素的模型基础上开发的基于 ESCNN 的实时逆变器故障监测方法。提出的模型经过了严格的训练,并使用真实的逆变器数据进行了测试,还包括一种新颖的过滤方法,以解决实际场景中的意外故障。结果验证了模型的有效性,同时还概述了未来的研究方向。
{"title":"Deep Learning-Based Failure Prognostic Model for PV Inverter Using Field Measurements","authors":"Liming Liu;Yi Luo;Zhaoyu Wang;Feng Qiu;Shijia Zhao;Murat Yildirim;Rajarshi Roychowdhury","doi":"10.1109/TSTE.2024.3443234","DOIUrl":"10.1109/TSTE.2024.3443234","url":null,"abstract":"This study presents a novel approach for the precise monitoring and prognosis of photovoltaic (PV) inverter status, which is crucial for the proactive maintenance of PV systems. It addresses the gaps in traditional model-based methods, which tend to neglect the overall reliability of inverters, and the limitations of data-driven approaches that largely depend on simulated data. This research presents a robust solution applicable to real-world scenarios. The proposed data-driven model for PV inverter failure prognosis employs actual inverter measurements, integrating various operational and weather-related factors based on domain knowledge. This approach effectively represents inverter stressors and operational status. Utilizing an Enhanced Siamese Convolutional Neural Network (ESCNN), the model merges operational data with domain knowledge features, redefining the prognosis challenge as a classification task. Furthermore, the paper discusses an ESCNN-based real-time inverter failure monitoring method developed on the well-trained model. The proposed models are rigorously trained and tested with real inverter data and a novel filtering method is included to address accidental failures in practical scenarios. The results validate the model's efficacy, and the directions for future research are also outlined.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2789-2802"},"PeriodicalIF":8.6,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219464","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
Electric Energy Maximization for Oscillating Water Column Wave Energy Systems Using a Receding-Horizon Pseudospectral Control Approach 利用后退-地平线伪谱控制方法实现振荡水柱波浪能系统的电能最大化
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-14 DOI: 10.1109/TSTE.2024.3443228
Marco Rosati;John V. Ringwood
Among the various wave energy technologies, oscillating water columns (OWCs) have shown some of the greatest promise, due to their simplicity of operation and possibility for shore mounting, with consequent ease of access and integration with other infrastructure, such as breakwaters. To minimize the levelized cost of energy, OWC energy capture must be maximized. To date, most focus has been on maximizing air turbine efficiency, while neglecting other aspects of the system. This paper presents an integrated wave-to-wire optimal control approach, considering the OWC hydrodynamics, turbine characteristics, and generator. The approach is based on a receding-horizon pseudospectral formulation, which transcribes the continuous-time optimal control problem into a finite-dimensional nonlinear program. The results show optimal exploitation of the hydrodynamic, aerodynamic, and electric subsystem efficiency characteristics, surpassing the electric energy production available through a specific focus on turbine efficiency.
在各种波浪能技术中,振荡水柱(OWCs)的前景最为广阔,因为它操作简单,可以安装在岸上,从而便于使用和与其他基础设施(如防波堤)集成。为了最大限度地降低平准化能源成本,必须最大限度地捕获 OWC 能源。迄今为止,大部分关注点都集中在空气涡轮机效率的最大化上,而忽略了系统的其他方面。本文提出了一种综合的 "波-线 "优化控制方法,考虑了 OWC 流体力学、涡轮机特性和发电机。该方法基于后退地平线伪谱公式,将连续时间最优控制问题转换为有限维非线性程序。结果表明,通过对涡轮机效率的特别关注,水动力、空气动力和电力子系统效率特性得到了优化利用,从而超过了可获得的电能产量。
{"title":"Electric Energy Maximization for Oscillating Water Column Wave Energy Systems Using a Receding-Horizon Pseudospectral Control Approach","authors":"Marco Rosati;John V. Ringwood","doi":"10.1109/TSTE.2024.3443228","DOIUrl":"10.1109/TSTE.2024.3443228","url":null,"abstract":"Among the various wave energy technologies, oscillating water columns (OWCs) have shown some of the greatest promise, due to their simplicity of operation and possibility for shore mounting, with consequent ease of access and integration with other infrastructure, such as breakwaters. To minimize the levelized cost of energy, OWC energy capture must be maximized. To date, most focus has been on maximizing air turbine efficiency, while neglecting other aspects of the system. This paper presents an integrated wave-to-wire optimal control approach, considering the OWC hydrodynamics, turbine characteristics, and generator. The approach is based on a receding-horizon pseudospectral formulation, which transcribes the continuous-time optimal control problem into a \u0000<italic>finite-dimensional</i>\u0000 nonlinear program. The results show optimal exploitation of the hydrodynamic, aerodynamic, and electric subsystem efficiency characteristics, surpassing the electric energy production available through a specific focus on turbine efficiency.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2769-2776"},"PeriodicalIF":8.6,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10636763","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219466","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
Inertial Frequency Response of Wind Turbines Using Adaptive Full Feedback Linearization Control: Stability and Robustness Analysis 使用自适应全反馈线性化控制的风力涡轮机惯性频率响应:稳定性和鲁棒性分析
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-14 DOI: 10.1109/TSTE.2024.3443230
M. Jafari Harandi;Mohammad Tavakoli Bina;M. Aliakbar Golkar;M. Reza J. Harandi;Mohammadreza Toulabi
It is a challenging task to affect suitably on the frequency response of a variable speed wind turbine (VSWT). The problem would be more crucial when the system is subjected to uncertainty in parameters as well as various external effects such as load changes and grid disturbances. Feedback linearization has already been applied to the VSWT, where two state variables experience instability. Hence, this paper presents a new methodology based on full-state feedback linearization in which by choosing an appropriate output, the closed-loop system is fully linearized, and the resulting linear system is stabilized by an optimal linear quadratic regulator (LQR). Since the parameters may be uncertain, the developed controller is augmented with an adaptive dynamic feedback such that all of the parameters are estimated while asymptotic stability is ensured by the Lyapunov method. Furthermore, robustness analysis is performed, and the effects of external disturbance are reduced by suitable selection of the gains. The analytical outcomes are verified through simulations, where these are compared with those of available work to show the improvement have been made by the suggested method.
对变速风力发电机(VSWT)的频率响应产生适当影响是一项具有挑战性的任务。当系统受到参数的不确定性以及负载变化和电网干扰等各种外部影响时,问题就会变得更加严重。反馈线性化已被应用于 VSWT,其中两个状态变量出现了不稳定性。因此,本文提出了一种基于全状态反馈线性化的新方法,即通过选择适当的输出,对闭环系统进行全线性化,并通过最优线性二次调节器(LQR)稳定所得到的线性系统。由于参数可能是不确定的,因此开发的控制器增加了自适应动态反馈,这样所有的参数都可以估算,同时通过 Lyapunov 方法确保渐近稳定性。此外,还进行了鲁棒性分析,并通过适当选择增益来减少外部干扰的影响。通过模拟验证了分析结果,并将这些结果与现有研究成果进行了比较,以显示所建议方法的改进之处。
{"title":"Inertial Frequency Response of Wind Turbines Using Adaptive Full Feedback Linearization Control: Stability and Robustness Analysis","authors":"M. Jafari Harandi;Mohammad Tavakoli Bina;M. Aliakbar Golkar;M. Reza J. Harandi;Mohammadreza Toulabi","doi":"10.1109/TSTE.2024.3443230","DOIUrl":"10.1109/TSTE.2024.3443230","url":null,"abstract":"It is a challenging task to affect suitably on the frequency response of a variable speed wind turbine (VSWT). The problem would be more crucial when the system is subjected to uncertainty in parameters as well as various external effects such as load changes and grid disturbances. Feedback linearization has already been applied to the VSWT, where two state variables experience instability. Hence, this paper presents a new methodology based on full-state feedback linearization in which by choosing an appropriate output, the closed-loop system is fully linearized, and the resulting linear system is stabilized by an optimal linear quadratic regulator (LQR). Since the parameters may be uncertain, the developed controller is augmented with an adaptive dynamic feedback such that all of the parameters are estimated while asymptotic stability is ensured by the Lyapunov method. Furthermore, robustness analysis is performed, and the effects of external disturbance are reduced by suitable selection of the gains. The analytical outcomes are verified through simulations, where these are compared with those of available work to show the improvement have been made by the suggested method.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2777-2788"},"PeriodicalIF":8.6,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219465","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
An Equitable Active Power Curtailment Framework for Overvoltage Mitigation in PV-Rich Active Distribution Networks 用于缓解富光伏有功配电网过电压的公平有功功率削减框架
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-13 DOI: 10.1109/TSTE.2024.3442834
Eihab E.E. Ahmed;Alpaslan Demirci;Gokturk Poyrazoglu;Saeed D. Manshadi
There are various active power curtailment (APC) approaches to mitigate overvoltage. In PV-rich networks, the overvoltage happens to be especially at the end of the distribution feeders. While APC helps maintain voltage within operational limits, it results in varying degrees of renewable curtailment for each prosumer. This curtailment increases as the distance from the transformer grows. Hence, these approaches introduce unfairness among prosumers. This study proposes an equitable APC (EAPC) based on the prosumer's self-consumption rate (SCR). The method calculates each prosumer's SCR, compares it with the precalculated critical SCR, and calculates a fair share of curtailment for each prosumer. Subsequently, leveraging the voltage sensitivity matrix obtained from the inverse of the Jacobian matrix, the new active power injection at the point of common coupling (PCC) is calculated to mitigate the overvoltage. To show the effectiveness of the proposed method, a comparison with three other methods is presented under various PV penetration levels. The proposed EAPC is less sensitive to the prosumer's location and improves fairness among prosumers. In addition, a battery deployment scenario is analysed considering the annual supply and demand balance to suppress the extra curtailment introduced by EAPC without increasing the battery capacity.
有多种有功功率削减(APC)方法可以缓解过电压。在光伏资源丰富的网络中,过电压尤其发生在配电馈线的末端。虽然有功功率削减有助于将电压维持在运行限制范围内,但会对每个用户造成不同程度的可再生能源削减。随着与变压器距离的增加,这种削减也会增加。因此,这些方法在用户之间造成了不公平。本研究提出了一种基于用户自消耗率(SCR)的公平可再生能源削减率(EAPC)。该方法计算每个用户的自耗电率,将其与预先计算的临界自耗电率进行比较,并为每个用户计算出公平的缩减份额。随后,利用从雅各布矩阵逆矩阵中获得的电压灵敏度矩阵,计算出共耦点(PCC)上新的有功功率注入,以缓解过电压。为了说明所提方法的有效性,我们在不同的光伏渗透水平下将其与其他三种方法进行了比较。所提出的 EAPC 对用户位置的敏感度较低,并提高了用户之间的公平性。此外,考虑到年度供需平衡,还对电池部署方案进行了分析,以在不增加电池容量的情况下抑制 EAPC 带来的额外缩减。
{"title":"An Equitable Active Power Curtailment Framework for Overvoltage Mitigation in PV-Rich Active Distribution Networks","authors":"Eihab E.E. Ahmed;Alpaslan Demirci;Gokturk Poyrazoglu;Saeed D. Manshadi","doi":"10.1109/TSTE.2024.3442834","DOIUrl":"10.1109/TSTE.2024.3442834","url":null,"abstract":"There are various active power curtailment (APC) approaches to mitigate overvoltage. In PV-rich networks, the overvoltage happens to be especially at the end of the distribution feeders. While APC helps maintain voltage within operational limits, it results in varying degrees of renewable curtailment for each prosumer. This curtailment increases as the distance from the transformer grows. Hence, these approaches introduce unfairness among prosumers. This study proposes an equitable APC (EAPC) based on the prosumer's self-consumption rate (SCR). The method calculates each prosumer's SCR, compares it with the precalculated critical SCR, and calculates a fair share of curtailment for each prosumer. Subsequently, leveraging the voltage sensitivity matrix obtained from the inverse of the Jacobian matrix, the new active power injection at the point of common coupling (PCC) is calculated to mitigate the overvoltage. To show the effectiveness of the proposed method, a comparison with three other methods is presented under various PV penetration levels. The proposed EAPC is less sensitive to the prosumer's location and improves fairness among prosumers. In addition, a battery deployment scenario is analysed considering the annual supply and demand balance to suppress the extra curtailment introduced by EAPC without increasing the battery capacity.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2745-2757"},"PeriodicalIF":8.6,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219467","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
Cooperative Planning of Multi-Energy System and Carbon Capture, Utilization and Storage 多能源系统与碳捕获、利用和储存的合作规划
IF 8.6 1区 工程技术 Q1 ENERGY & FUELS Pub Date : 2024-08-08 DOI: 10.1109/TSTE.2024.3440322
Da Xu;Aoyu Hu;Chi-Seng Lam;Xiaodong Yang;Xiaolong Jin
Carbon capture, utilization, and storage (CCUS) can play critical roles in transitioning to global net-zero emissions. However, existing works only focus on small-scale or local CO2 utilization. For the first time, this paper proposes a cooperative planning model of multi-energy system and CCUS considering the regional CO2 availability. In this model, the multi-energy system and CCUS are coupled through interconnected energy hubs. To leverage its inherent operational dispatchability and flexibility, the physicochemical and thermo-electrochemical processes of CCUS are mathematically formulated with source-sink matching analysis. The multi-energy planning is a demanding optimization challenge owing to its inherent nonconvexities and substantial energy-interest couplings. The original problem is firstly relaxed as mixed integer second-order cone programming (MISOCP) to ensure satisfactory computational efficiency. A carbon-oriented bargaining problem can then be reformulated to share the cooperative surplus, which is further decomposed into a joint investment/operation subproblem and a cost-sharing subproblem. The proposed methodology is benchmarked over interconnected energy hub systems to show its effectiveness and superiority in technical, economic, and environmental aspects.
碳捕集、利用和封存(CCUS)可在向全球净零排放过渡方面发挥关键作用。然而,现有研究仅关注小规模或局部的二氧化碳利用。本文首次提出了一种考虑区域二氧化碳可用性的多能源系统与 CCUS 合作规划模型。在该模型中,多能源系统和 CCUS 通过相互连接的能源枢纽耦合。为了充分利用其固有的运行调度性和灵活性,通过源-汇匹配分析,对 CCUS 的物理化学和热电化学过程进行了数学计算。由于其固有的非凸性和大量的能源-利益耦合,多能源规划是一项艰巨的优化挑战。首先将原始问题放宽为混合整数二阶圆锥编程(MISOCP),以确保令人满意的计算效率。然后,可以重新制定一个面向碳的讨价还价问题,以分享合作盈余,并将其进一步分解为一个联合投资/运营子问题和一个成本分担子问题。对所提出的方法进行了互联能源枢纽系统的基准测试,以显示其在技术、经济和环境方面的有效性和优越性。
{"title":"Cooperative Planning of Multi-Energy System and Carbon Capture, Utilization and Storage","authors":"Da Xu;Aoyu Hu;Chi-Seng Lam;Xiaodong Yang;Xiaolong Jin","doi":"10.1109/TSTE.2024.3440322","DOIUrl":"10.1109/TSTE.2024.3440322","url":null,"abstract":"Carbon capture, utilization, and storage (CCUS) can play critical roles in transitioning to global net-zero emissions. However, existing works only focus on small-scale or local CO\u0000<sub>2</sub>\u0000 utilization. For the first time, this paper proposes a cooperative planning model of multi-energy system and CCUS considering the regional CO\u0000<sub>2</sub>\u0000 availability. In this model, the multi-energy system and CCUS are coupled through interconnected energy hubs. To leverage its inherent operational dispatchability and flexibility, the physicochemical and thermo-electrochemical processes of CCUS are mathematically formulated with source-sink matching analysis. The multi-energy planning is a demanding optimization challenge owing to its inherent nonconvexities and substantial energy-interest couplings. The original problem is firstly relaxed as mixed integer second-order cone programming (MISOCP) to ensure satisfactory computational efficiency. A carbon-oriented bargaining problem can then be reformulated to share the cooperative surplus, which is further decomposed into a joint investment/operation subproblem and a cost-sharing subproblem. The proposed methodology is benchmarked over interconnected energy hub systems to show its effectiveness and superiority in technical, economic, and environmental aspects.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"15 4","pages":"2718-2732"},"PeriodicalIF":8.6,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141943725","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
期刊
IEEE Transactions on Sustainable Energy
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1