Fault localization method for power distribution systems based on gated graph neural networks

Freitas, Jonas Teixeira de; Coelho, Frederico

doi:10.1007/s00202-021-01223-7

Cited by 16 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various sensing devices are deployed on the distribution transformer side, the low-voltage distribution line side and the user side in digitalized substation area, and the intelligent transformer terminal units is used as the core to complete the monitoring and computing functions of distribution transformers, low-voltage branch boxes, low-voltage electrical appliances and other equipment. Then the data is analyzed, calculated and sorted out according to the demand through the intelligent transformer terminal units and sent to the distribution master station (Cloud-side), which provides the implementation basis for the fault diagnosis of digitalized substation area [18].…”

Section: Fault Diagnosis In Digitalized Substation Areamentioning

confidence: 99%

Evaluation Method and Index System of Fault Diagnosis in Digitalized Distribution Substation Area

Chen

Sheng

Guan

et al. 2023

Preprint

View full text Add to dashboard Cite

Digitalized distribution substation area that constructed with intelligent transformer terminal could realize various advanced application scenarios by the use of IoT technology, which provides a new perspective for the fault diagnosis problem solving in power distribution system. This paper briefly introduces the principle of fault diagnosis based on digitalized substation area. Then propose a fault diagnosis effectiveness evaluation index system containing the first priority qualification index and the second priority performance index, and its index weight calculation method based on hierarchical analysis method and improved entropy weight method. And through the fuzzy comprehensive evaluation method, the comprehensive evaluation of the fault diagnosis effectiveness is carried out. At the end of this article, the effectiveness of the proposed evaluation method and index system is verified through example analysis.

show abstract

Section: Fault Diagnosis In Digitalized Substation Areamentioning

confidence: 99%

Evaluation Method and Index System of Fault Diagnosis in Digitalized Distribution Substation Area

Chen

Sheng

Guan

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Various sensing devices are deployed on the distribution transformer side, low-voltage distribution line side, and user side in a digitalized substation area, and intelligent transformer terminal units are used as the core to complete the monitoring and computing functions of distribution transformers, lowvoltage branch boxes, low-voltage electrical appliances and other equipment. Then, the data are analyzed, calculated and sorted according to the demand through the intelligent transformer terminal units and sent to the distribution master station (cloud-side), which provides the implementation basis for the fault diagnosis of digitalized substation areas [18]. The structure of the fault diagnosis system of a digitalized substation area is shown in Fig.…”

Section: Fault Diagnosis In Digitalized Substation Areasmentioning

confidence: 99%

Fault Diagnosis Evaluation Method and Index System in Digitalized Distribution Substation Areas

Chen

Sheng

Guan

et al. 2023

Preprint

View full text Add to dashboard Cite

Digitalized distribution substation areas constructed with intelligent transformer terminals can realize various advanced application scenarios using IoT technology, which provides a new perspective for fault diagnosis problem solving in power distribution systems. This paper briefly introduces the principle of fault diagnosis based on a digitalized substation area. Then, we propose a fault diagnosis effectiveness evaluation index system containing first priority qualification indices, second priority performance indices, and an index weight calculation method based on the hierarchical analysis method and improved entropy weight method. Through a fuzzy comprehensive evaluation method, a comprehensive evaluation of the fault diagnosis effectiveness is carried out. At the end of this article, the effectiveness of the proposed evaluation method and index system is verified through example analysis.

show abstract

“…Although they have their own advantages, there are two main challenges [68]: ① they cannot flexibly combine measurement data from different buses, especially in the case of data loss; ② most of traditional methods have difficulties in modeling the topology of the distribution network. In order to solve these problems, [69] employs the graph GRUs to automatically localize the faults of distribution networks. The feeder topology is represented by graph edges, and problem data, e. g., measurements and electrical characteristics, are regarded as graph nodes.…”

Section: ) Fault Locationmentioning

confidence: 99%

A Review of Graph Neural Networks and Their Applications in Power Systems

Liao

Bak‐Jensen

Pillai

et al. 2022

Journal of Modern Power Systems and Clean Energy

133

View full text Add to dashboard Cite

Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks are typically represented in Euclidean domains. Nevertheless, there is an increasing number of applications in power systems, where data are collected from non-Euclidean domains and represented as graph-structured data with high-dimensional features and interdependency among nodes. The complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domains. Recently, many publications generalizing deep neural networks for graphstructured data in power systems have emerged. In this paper, a comprehensive overview of graph neural networks (GNNs) in power systems is proposed. Specifically, several classical paradigms of GNN structures, e. g., graph convolutional networks, are summarized. Key applications in power systems such as fault scenario application, time-series prediction, power flow calculation, and data generation are reviewed in detail. Furthermore, main issues and some research trends about the applications of GNNs in power systems are discussed.

show abstract

Fault localization method for power distribution systems based on gated graph neural networks

Cited by 16 publications

References 13 publications

Evaluation Method and Index System of Fault Diagnosis in Digitalized Distribution Substation Area

Evaluation Method and Index System of Fault Diagnosis in Digitalized Distribution Substation Area

Fault Diagnosis Evaluation Method and Index System in Digitalized Distribution Substation Areas

A Review of Graph Neural Networks and Their Applications in Power Systems

Contact Info

Product

Resources

About