Electric Power Systems Research最新文献_第7页

Multi-layer coordinated frequency control strategy for WTGs and energy storage considering system inertia requirement 考虑系统惯性要求的风电机组和储能多层协调频率控制策略

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-15 DOI: 10.1016/j.epsr.2024.111190

Meng Lingcong , Qin Chao , Hongtao Liu , Ligang Zhao , Huifan Xie , Hongyue Zhen

{"title":"Multi-layer coordinated frequency control strategy for WTGs and energy storage considering system inertia requirement","authors":"Meng Lingcong , Qin Chao , Hongtao Liu , Ligang Zhao , Huifan Xie , Hongyue Zhen","doi":"10.1016/j.epsr.2024.111190","DOIUrl":"10.1016/j.epsr.2024.111190","url":null,"abstract":"<div><div>Given the intimate correlation between the inertia response ability of wind turbine generators (WTGs) and their operational statuses, it becomes imperative to analyze the inertia contribution from wind farms across varying wind speeds and establish the rate of change of frequency (RoCoF) security boundary. Such endeavors are crucial for grid operators to assess the system's ability to withstand disturbances. This paper proposes a multi-layer frequency control method for hybrid wind power and energy storage (ES) systems. All WTGs and ESs in the wind farm are divided into several clusters. At the wind farm layer, the wind farm control center quantitatively assesses the maximum inertia that the wind farm can provide based on real-time wind speed and the operational status of WTGs, and communicates this information to the grid control center. At the grid layer, the power system operators establish the security boundary related to the RoCoF based on the inertia level of the wind farm and synchronous generators, thereby continuously evaluating the system's ability to withstand disturbances in real-time. In the event of significant disturbances (N-1 event), the power system dispatch center issues instructions to the wind farm, specifying the required level of inertia to be provided. The wind farm, in turn, coordinates the allocation of inertia among WTGs and ESs based on the dispatch center's instructions and considers the operational status of different WTGs, while tracking the system control commands. Through this approach, the inertia response ability of different WTGs and ESs can be fully utilized to enhance the transient frequency characteristics of the grid.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111190"},"PeriodicalIF":3.3,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Fault diagnosis of ship power grid based on attentional feature fusion and multi-scale 1D convolution 基于注意特征融合和多尺度一维卷积的船舶电网故障诊断

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-14 DOI: 10.1016/j.epsr.2024.111232

Yabo Cui , Rongjie Wang , Jianfeng Wang , Yichun Wang , Shiqi Zhang , Yupeng Si

{"title":"Fault diagnosis of ship power grid based on attentional feature fusion and multi-scale 1D convolution","authors":"Yabo Cui , Rongjie Wang , Jianfeng Wang , Yichun Wang , Shiqi Zhang , Yupeng Si","doi":"10.1016/j.epsr.2024.111232","DOIUrl":"10.1016/j.epsr.2024.111232","url":null,"abstract":"<div><div>The Ship Integrated Power System (SIPS) is evolving into a sophisticated network with prediction and active control functions, so accurate localization and identification of faults are crucial for the stable operation of the SIPS. The complex topology of power supply lines in ship power grids presents challenges in accurately locating and identifying faults. This paper presents a fault diagnosis model for the ship power grid based on attention feature fusion and multi-scale 1D convolutional neural network (AFF-MS-1DCNN), which can identify the fault type and locate the fault location only by using the three-phase currents of the busbar at the power supply output. By using the multi-scale 1DCNN, the method can effectively extract fault features on different scales. Furthermore, an attention mechanism is utilized to adaptively learn the weights of different features to enhance fault diagnosis precision. A transfer learning strategy is also applied to address variations in fault resistance. The experimental results demonstrate that the fault diagnosis accuracy of the AFF-MS-1DCNN model exceeds 98% under different fault resistance conditions, and it exhibits robust diagnostic performance even in the presence of noise interference.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111232"},"PeriodicalIF":3.3,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Cluster operation of microgrids: Assessing economic and resilience gains 微电网的集群运行：评估经济和复原力收益

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-14 DOI: 10.1016/j.epsr.2024.111220

Paulo H. Cunha, Osvaldo R. Saavedra, Luiz A.S. Ribeiro, Denisson Q. Oliveira

{"title":"Cluster operation of microgrids: Assessing economic and resilience gains","authors":"Paulo H. Cunha, Osvaldo R. Saavedra, Luiz A.S. Ribeiro, Denisson Q. Oliveira","doi":"10.1016/j.epsr.2024.111220","DOIUrl":"10.1016/j.epsr.2024.111220","url":null,"abstract":"<div><div>Collaborative operation is one way to explore the flexibilities of microgrids for mutual benefit, exploiting the asymmetries in storage capacity and renewable energy sources of microgrids within a cluster. The economic feasibility of a cluster is achieved through operational agreements determined from studies of optimal operation, allowing for changes in topology (how many and which microgrids participate). In this article, we model the operation of collaborative microgrids forming clusters, with a particular focus on individual resilience and the collective benefits of cluster operation. By comparing the performance of microgrids operating in isolation versus those in a collaborative cluster, we assess the economic gains as well as the improvements in resilience. The study consistently demonstrates the advantages of collaborative operation, including the more effective use of renewable energy sources, the quantification and valuation of resilience, financial benefits from better infrastructure utilization, and significantly enhanced energy security for the entire set of microgrids.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111220"},"PeriodicalIF":3.3,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Disaster management approaches for active distribution networks based on Mobile Energy Storage System 基于移动储能系统的主动配电网络灾难管理方法

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-14 DOI: 10.1016/j.epsr.2024.111242

Maosong Zhang , Huixiao Fu , Xiuqin Wang , Dongsheng Shu , Jie Yang , Pan Yu , Mingxing Zhu , Jun Tao

{"title":"Disaster management approaches for active distribution networks based on Mobile Energy Storage System","authors":"Maosong Zhang , Huixiao Fu , Xiuqin Wang , Dongsheng Shu , Jie Yang , Pan Yu , Mingxing Zhu , Jun Tao","doi":"10.1016/j.epsr.2024.111242","DOIUrl":"10.1016/j.epsr.2024.111242","url":null,"abstract":"<div><div>In light of the frequent distribution network outages and economic losses caused by extreme natural disasters, the development of a reasonable disaster management method is crucial for building a resilient distribution network. Therefore, this paper proposes an active distribution network disaster management method based on Mobile Energy Storage System (MESS) active regulation. The method divides natural disasters into two stages: pre-disaster and post-disaster. In the pre-disaster prevention phase, the graph search algorithm is first used to search and determine the uninterrupted path of power supply for accessing MESS, and then with the goal of minimizing the pre-disaster prevention cost and setting the constraints, the pre-disaster two-phase robust MESS deployment model is constructed by taking into account the uncertainty of the distributed power supply, and the column constraints generation algorithm is used to iteratively solve the pre-layout scheme of MESS. In the post-disaster recovery phase, considering the time-varying nature of distributed power output, a dynamic scheduling model of multiple swarm co-evolution of MESS is constructed, and the improved Non-dominated Sorting Genetic Algorithm-II (NSGA-II) algorithm is used to solve the dynamic scheduling scheme of MESS. Finally, an example analysis is carried out through the IEEE 33-node distribution system to verify the robustness of the proposed strategy of the pre-disaster prevention model to the uncertainty of the distributed power output prediction error, and the feasibility of the post-disaster MESS dynamic dispatch model with the time-varying nature of the distributed power output; meanwhile, it confirms the validity of the establishment of the collection of power supply uninterrupted nodes in improving the proportion of the restoration of power supply of important loads of the distribution network during the disaster period.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111242"},"PeriodicalIF":3.3,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Risk assessment of integrated transmission and distribution systems considering load transfer 考虑负荷转移的综合输配电系统风险评估

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-13 DOI: 10.1016/j.epsr.2024.111205

Jiangang Lu , Ruifeng Zhao , Zufeng Hou , Guihui Lin , Yong Zhang , Chao Wang , Kaiyan Pan , Haixin Liu

{"title":"Risk assessment of integrated transmission and distribution systems considering load transfer","authors":"Jiangang Lu , Ruifeng Zhao , Zufeng Hou , Guihui Lin , Yong Zhang , Chao Wang , Kaiyan Pan , Haixin Liu","doi":"10.1016/j.epsr.2024.111205","DOIUrl":"10.1016/j.epsr.2024.111205","url":null,"abstract":"<div><div>Integrated transmission and distribution system (ITDS) analysis is gaining increasing attention from academics and industry. Load transfer, a critical factor in maintaining system reliability and reducing system risk during outages, is often overlooked in conventional system risk assessment. This paper proposes a framework that incorporates load transfer capabilities into ITDS modeling, enabling a comprehensive evaluation of its impact on risk mitigation. The framework integrates the uncertainty of electricity demand, initial outages suggested by contingency motifs, and detailed ITDS models. A centralized model using mixed-integer conic programming is formulated to identify optimal load transfer strategies. Recognizing the typical operational separation of transmission and distribution systems, a practical two-stage optimization method with limited information exchange is also proposed to determine degraded system states. Case studies demonstrate that incorporating load transfer can significantly reduce system risk, underscoring the importance of integrating this capability into risk assessments and operational strategies.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111205"},"PeriodicalIF":3.3,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 dynamic framework for optimizing peer-to-peer energy sharing: Enhancing local consumption and reducing power losses in smart grids 优化点对点能源共享的动态框架：提高智能电网的本地消耗并减少电力损耗

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-13 DOI: 10.1016/j.epsr.2024.111215

Jinglin He , Tao Feng , Rengan Wei

{"title":"A dynamic framework for optimizing peer-to-peer energy sharing: Enhancing local consumption and reducing power losses in smart grids","authors":"Jinglin He , Tao Feng , Rengan Wei","doi":"10.1016/j.epsr.2024.111215","DOIUrl":"10.1016/j.epsr.2024.111215","url":null,"abstract":"<div><div>The integration of distributed energy resources has enabled peer-to-peer energy sharing (P2PES), offering an innovative approach to energy planning. While previous research has focused on the economic benefits of P2PES for users, it often overlooks strategic network responses. This paper presents a P2PES framework that incorporates dynamic network architecture. The framework's core involves developing a P2PES model aimed at increasing local energy consumption and reducing electrical losses during peer-to-peer (P2P) exchanges. Additionally, a dynamic grid structure model facilitates active grid operator participation in optimizing grid structure and reducing power losses. These dual models synergize, sharing information to optimize P2PES programs, network operations, and energy utilization. The framework's coordination is achieved through an algorithm combining a matching mechanism with a branch exchange method, refined iteratively to enhance performance. Numerical analysis demonstrates the framework's effectiveness, showing an 18.31 % improvement with joint optimization strategies. Additionally, incorporating distribution system operator switching strategies results in a 31.69 % reduction in total network power losses and a 2.81 % increase in local energy consumption. This highlights not only buyer strategies but also dynamic network evolution, emphasizing the framework's practical feasibility in electrical engineering.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111215"},"PeriodicalIF":3.3,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal hybrid backup systems for substation auxiliary services during outages through stochastic programming 通过随机编程实现停电期间变电站辅助服务的最佳混合备份系统

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-12 DOI: 10.1016/j.epsr.2024.111191

Matheus Holzbach , Norberto Abrante Martinez , Lucas Teles Faria , Alejandra Tabares , José F. Resende , John F. Franco

{"title":"Optimal hybrid backup systems for substation auxiliary services during outages through stochastic programming","authors":"Matheus Holzbach , Norberto Abrante Martinez , Lucas Teles Faria , Alejandra Tabares , José F. Resende , John F. Franco","doi":"10.1016/j.epsr.2024.111191","DOIUrl":"10.1016/j.epsr.2024.111191","url":null,"abstract":"<div><div>Auxiliary services are fundamental to ensure the uninterrupted operation, control, and surveillance of critical infrastructure. Traditional dependency on diesel generators as backup power sources during service disruptions is increasingly challenged by their non-renewable nature, operational costs, and environmental impacts. Addressing these concerns, this paper introduces a novel stochastic programming method for the optimal design of a hybrid backup system (HBS), integrating photovoltaic (PV) panels, battery storage, and bidirectional inverters, specifically tailored for substation auxiliary services (SAS). The proposed model represents the uncertainties associated with solar irradiance and power outages (occurrence and duration) through a scenario-based analysis, ensuring a required level of robustness. The proposed model is applied to a case study and a sensitivity analysis of the most important parameters was executed. It was identified that the optimal investment corresponds to an HBS formed by 6 batteries and 22 PV panels (18 kWh/8.58 kWp), providing a robustness level of 99.526 %, which reduces the unavailable hours of the SAS by 61 %. The findings underscore the pivotal contribution of battery systems to support SAS under outages, facilitating the attainment of requisite reliability thresholds. Nonetheless, achieving higher levels of robustness is intrinsically linked to increased financial investment in the backup system infrastructure.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111191"},"PeriodicalIF":3.3,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-level consensus based load frequency controller with multi-battery energy storage systems 基于多电池储能系统的多级共识负载频率控制器

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-12 DOI: 10.1016/j.epsr.2024.111208

Don Gamage , Chathura Wanigasekara , Abhisek Ukil , Akshya Swain

{"title":"Multi-level consensus based load frequency controller with multi-battery energy storage systems","authors":"Don Gamage , Chathura Wanigasekara , Abhisek Ukil , Akshya Swain","doi":"10.1016/j.epsr.2024.111208","DOIUrl":"10.1016/j.epsr.2024.111208","url":null,"abstract":"<div><div>This study introduces a primary and secondary level multi-consensus load frequency controller (LFC) with distributed multi-battery energy storage system (MBESS) to regulate the frequency and voltage of the islanded grid. The suggested control approach uses battery storage devices’ ability to deliver or absorb active power during power shortages or surpluses in order to regulate the system frequency and voltage. The controller uses consensus-based distributed coordination among agents in order to achieve stabilise frequency and voltage. In primary mode, each node exchanges local information with its neighbour, such as battery energy, power, and state of charge (SoC), to reach an agreement value in finite time. In secondary mode, the controller achieves its stability by sharing active and reactive power to regulate the frequency and the voltage. The conventional PI controller with a state feedback loop controller is used as a local controller for LFC in the multi-agent control platform. Numerical examples are considered throughout the simulations to highlight the controller’s functionality and are compared with the past literature. As simulation results suggested, the proposed model with the MBESS will have a efficient system performances compare to traditional LFC mode. In this case, each single battery model has the ability to work as a generator and as an active load to the grid to balance frequency and voltage fluctuations. Furthermore, the results are obtained through the OP5700 real-time simulator to compare the values with the simulation. The results are further validated on the IEEE 14-bus power system. Analysis of the results indicates that the proposed system exhibits better characteristics with the multi-level consensus approach, compared to the traditional LFC.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111208"},"PeriodicalIF":3.3,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

High-impedance fault location method using guessed fault resistance 利用猜测故障电阻的高阻抗故障定位方法

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-11 DOI: 10.1016/j.epsr.2024.111221

Haonan Cui, Qing Yang

{"title":"High-impedance fault location method using guessed fault resistance","authors":"Haonan Cui, Qing Yang","doi":"10.1016/j.epsr.2024.111221","DOIUrl":"10.1016/j.epsr.2024.111221","url":null,"abstract":"<div><div>Electromagnetic time reversal fault location method requires the placement of observation points at a single location and is effective for searching fault location. Among the various existing metrics, the transfer function correlation metric emerged as the most robust. However, its application to high-impedance faults also presents challenges. This difficulty can be attributed to the unknown real fault resistance in the direct-time process, where the guessed fault resistance is typically set to 0 during the reversed-time process of the electromagnetic time reversal fault location method. Consequently, this practice yields comparable direct-time and reversed-time transfer functions for low-impedance faults. Conversely, high-impedance faults exhibit significant discrepancies between direct-time and reversed-time transfer functions, leading to errors in fault location. To overcome this challenge, this paper proposes a location method based on specific guessed fault resistance preset during the reversed-time process. First, the direct-time voltage and reversed-time current transfer functions under high-impedance faults were derived in the frequency domain. Subsequently, by comparing transfer function differences when fault resistances in the direct-time and reversed-time processes did not align, a principle for selecting the guessed fault resistance was established. Additionally, the similarity of the two transfer functions under specific guessed fault resistances was investigated. Furthermore, the symmetry of the fault current was leveraged to reflect the correlation between the two transfer functions, and the differential fault current symmetry coefficient metric was introduced. A fault location time-domain algorithm based on guessed fault resistance was proposed, and its effectiveness was demonstrated through both reduced-scale and simulation experiments. The results indicate that the proposed method is not only applicable to complex lines but also offers a straightforward calculation approach, facilitating fault location under high-impedance faults.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111221"},"PeriodicalIF":3.3,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Intelligent fault diagnosis in power distribution networks using LSTM-DenseNet network 利用 LSTM-DenseNet 网络进行配电网智能故障诊断

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2024-11-10 DOI: 10.1016/j.epsr.2024.111202

Lipeng Ji, Xianglei Tian, Zhonghao Wei, Daqi Zhu

{"title":"Intelligent fault diagnosis in power distribution networks using LSTM-DenseNet network","authors":"Lipeng Ji, Xianglei Tian, Zhonghao Wei, Daqi Zhu","doi":"10.1016/j.epsr.2024.111202","DOIUrl":"10.1016/j.epsr.2024.111202","url":null,"abstract":"<div><div>This paper introduces a novel fault diagnosis method that combines DenseNet and Long Short-Term Memory (LSTM) networks. The DenseNet utilizes its unique dense block structure to detect subtle variations in three-phase voltage and zero-sequence current signals. In addition, the Squeeze-and-Excitation (SE) module is introduced in DenseNet. The SE module enhances DenseNet's feature representation by adapting the importance of each channel in the feature map. Furthermore, integrating the LSTM model enables capturing time-domain features of fault signals, enhancing the analysis of waveform changes and trends. These extracted features are subsequently fused in a cascaded manner, leveraging the strengths of both approaches to obtain a more comprehensive information representation. To better explain the capability of feature extraction in each part of the model, t-distributed Stochastic Neighbor Embedding (t-SNE) method is used for visual analysis. The proposed method is evaluated using two distribution network models, namely the 10 kV and IEEE34 networks, in simulation. The verification results indicate that the proposed method achieves exceptionally high accuracy in fault identification for both tested distribution network models, with rates of 99.87 % and 99.82 %, respectively, while also demonstrating robust performance in noisy environments. This performance surpasses that of other related methods, underscoring the enhanced effectiveness of our approach.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"239 ","pages":"Article 111202"},"PeriodicalIF":3.3,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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