Fault Location Method of Distribution Network Based on VGAE-GraphSAGE

The research on fast and accurate fault location technology in distribution networks is of great significance. Currently, many methods for fault location in distribution networks have been proposed, but most theories are difficult to solve the problem of fault location in multi branch distribution networks. Therefore, this paper analyzed the characteristics of traveling wave transmission and proposed a discrimination algorithm that uses the polarity of traveling waves to determine the source of fault traveling waves; Then, using the idea of first locating the fault section and then locating the fault point, a multi branch distribution network traveling wave fault location algorithm is proposed based on the configuration of micro PMU (Phasor Measurement Units) devices in the distribution network by combining the two end method and single end method of traveling wave distance measurement. A multi branch distribution network simulation model based on IEEE14 node standard topology was built using MATLAB/Simulink software, the experimental results also showed the effectiveness and the efficiency of the proposed algorithm.

Accurately evaluating the fault type and location is important for ensuring the reliability of the power distribution network. A mushrooming number of distributed generations (DGs) connected to the distribution system brings challenges to traditional fault classification and location methods. Novel AI-based methods are mostly based on wide area measurement with the assistance of intelligent devices, whose economic cost is somewhat high. This paper develops a super-resolution (SR) and graph neural network (GNN) based method for fault classification and location in the power distribution network. It can accurately evaluate the fault type and location only by obtaining the measurements of some key buses in the distribution network, which reduces the construction cost of the distribution system. The IEEE 37 Bus system is used for testing the proposed method and verifying its effectiveness. In addition, further experiments show that the proposed method has a certain anti-noise capability and is robust to fault resistance change, distribution network reconfiguration, and distributed power access.

With the increasing attention to the power supply reliability of distribution network, the fault location method of distribution network as an important subject can be studied in depth. Traditional fault location methods, such as impedance method and traveling wave method, are limited due to the complex topology and many line types of distribution network. Based on the analysis of the limitations of impedance method and traveling wave method, this paper studies the fault location method of distribution network based on time reversal, focusing on the influence of hybrid power network and load on fault location method, Compared with the traditional fault location method, the distribution network fault location method based on time reversal has stronger adaptability.

When the distribution network fails, the operation and maintenance personnel need to quickly determine the fault location and minimize the scope of the inspection line so that the fault repair personnel can accurately reach the vicinity of the fault point to carry out work. Whether the fault location method is advanced and reliable directly affects the power failure time of the power supply user, and further affects the social, economic, and life aspects. Therefore, the fault location of the distribution network needs to satisfy both reliability and accuracy. It is the basis and premise for troubleshooting, isolating and restoring the power supply. The automation level of China’s distribution network is relatively backward, and the reliability of power supply equipment is relatively low, making it difficult to find fault points. If we find out the intelligent algorithms that can meet the requirements of rapid positioning, accuracy and fault tolerance through theoretical research, we can Improve the fault location efficiency very well.

With the rapid development of national economy, the distribution network becomes more and more complex and the load density is increasing. The safe and stable operation of distribution network is crucial to reliable power supply. The faults in distribution network account for a large proportion in the whole power system, and have an increasing trend. Therefore, accurate fault location of distribution lines is of great significance for fast power recovery. At present, the traveling wave fault location of distribution network is usually based on the fault location method for transmission lines. The engineering situation of distribution network is not fully considered and the analysis is simple, which affects the precise analysis of fault traveling wave transient characteristics and the improvement of fault location method. In this paper, the transient characteristics of fault traveling wave under different fault conditions in distribution network are analyzed and the analysis results are validated by simulation.

Fault location in electrical energy distribution networks is an important task, as faults in distribution grids are among the main causes of electricity supply disruption. Fault location in the distribution systems, however, is a challenging task because of the topology of the distribution networks, as well as the main and side branches. Therefore, it is necessary to address these challenges through an intelligent approach to fault location. In this paper, fault location in electric energy distribution networks is addressed considering the changes in fault distance and fault resistance in the presence of different fault types. A new method for fault location is developed for conditions where the minimum information is available and only information at the beginning of the feeder is used. This facilitates wide adoption of the technique as it does not require significant investments in instrumentation and measurement. The proposed intelligent method is based on the impedance and transient state estimation. This technique employs a specific impedance analysis for determining possible fault locations considering the unbalanced performance of distribution systems, distances, and different fault resistances. To determine the real faulty section, real fault frequency component analysis and the simulated faults at possible fault locations are used. At this stage of the process, it is possible to eliminate multiple estimations with the help of comparison and identification of the similarities. Therefore, a real faulty section is determined. It is observed that some conditions of electric energy distribution networks affect the accuracy and performance of the proposed method significantly; thus, a detailed investigation is conducted to neutralize these conditions. Simulation results and calculations based on MATLAB along with a practical test of the proposed method in power network simulator confirm a satisfactory performance.

The structure complexity and the extended geographical area are among the factors that create challenges in accurate fault location and detection in distribution networks. The single‐phase to ground (SPG) faults are considered as most frequent reasons for distribution network interruption, which can threaten the network's reliability. Signal processing methods are usually used as common approaches to distinguish and locate faults in distribution networks. This paper proposes a novel scenario to select optimal wavelet packet transform (WPT) coefficients for SPG fault location and a method based on superimposed voltage energy to distinguish the faulty phase according to these coefficients. Furthermore, employing the energies of the superimposed voltages helps to minimize the effects of high resistance faults (HRFs) and load encroachment on the efficiency of the faulty phase detection part. Comparing the obtained results with other scenarios demonstrates the considerable efficiency of the proposed scenario. Finally, with the help of general regression neural networks (GRNN) as machine‐learning tools, a new algorithm is derived for detecting and locating the SPG fault and capacitor bank switching overvoltage (COV). Simulation results are implemented on the IEEE 34‐bus standard distribution network, demonstrating the efficiency and superiority of the suggested method.

Distribution network fault location technology is currently mainly concentrated in sub section positioning and based on the offline signal injection method precise positioning stage, this paper proposes a new online traveling wave fault location method based on the correlation matrix, the method based on line distributed terminal high sampling data waves, with terminal data construction association matrix, through the correlation matrix of the symmetry and correlation determine fault section and identify abnormal data set, on the basis of further accurate fault location, so as to improve the reliability and accuracy of fault location in distribution network.

Although single phase to ground fault location in non-solid grounded networks has been studied for many years and a lot of research has been done, yet adequate solution for direct fault location of radial distribution network hasn't been made, especially for the distribution network with the neutral point grounded via arc suppression coil. Involvement of the arc suppression coil may decrease short-circuit current, but the difficulty of finding fault location is increased. The key problem of non-solid single-phase to ground fault location is to solve the fault location of distribution network with the neutral point grounding via arc suppression coil. This paper will analyse line capacitive current distribution of isolated neutral point and neutral point grounded via arc suppression coil and propose the concept of per-unit zero sequence current method. Equipartition principle of zero sequence current is utilized to locate fault section of the distribution system. Simulation tests to verify the effectiveness of this method have been made as well.

Fault localization (FL) and automated program repair (APR) are two main tasks of automatic software debugging. Compared with traditional methods, deep learning-based approaches have been demonstrated to achieve better performance in FL and APR tasks. However, the existing deep learning-based FL methods ignore the deep semantic features or only consider simple code representations. And for APR tasks, existing template-based APR methods are weak in selecting the correct fix templates for more effective program repair, which are also not able to synthesize patches via the embedded end-to-end code modification knowledge obtained by training models on large-scale bug-fix code pairs. Moreover, in most of FL and APR methods, the model designs and training phases are performed separately, leading to ineffective sharing of updated parameters and extracted knowledge during the training process. This limitation hinders the further improvement in the performance of FL and APR tasks. To solve the above problems, we propose a novel approach called MTL-TRANSFER, which leverages a multi-task learning strategy to extract deep semantic features and transferred knowledge from different perspectives. First, we construct a large-scale open-source bug datasets and implement 11 multi-task learning models for bug detection and patch generation sub-tasks on 11 commonly used bug types, as well as one multi-classifier to learn the relevant semantics for the subsequent fix template selection task. Second, an MLP-based ranking model is leveraged to fuse spectrum-based, mutation-based and semantic-based features to generate a sorted list of suspicious statements. Third, we combine the patches generated by the neural patch generation sub-task from the multi-task learning strategy with the optimized fix template selecting order gained from the multi-classifier mentioned above. Finally, the more accurate FL results, the optimized fix template selecting order, and the expanded patch candidates are combined together to further enhance the overall performance of APR tasks. Our extensive experiments on widely-used benchmark Defects4J show that MTL-TRANSFER outperforms all baselines in FL and APR tasks, proving the effectiveness of our approach. Compared with our previously proposed FL method TRANSFER-FL (which is also the state-of-the-art statement-level FL method), MTL-TRANSFER increases the faults hit by 8/11/12 on Top-1/3/5 metrics (92/159/183 in total). And on APR tasks, the number of successfully repaired bugs of MTL-TRANSFER under the perfect localization setting reaches 75, which is 8 more than our previous APR method TRANSFER-PR. Furthermore, another experiment to simulate the actual repair scenarios shows that MTL-TRANSFER can successfully repair 15 and 9 more bugs (56 in total) compared with TBar and TRANSFER, which demonstrates the effectiveness of the combination of our optimized FL and APR components.

With the access of distributed generators (DG), the power flow direction and structure of distribution networks have changed, and therefore many traditional fault location methods are no longer applicable. Single-phase grounding fault is a common fault in power distribution network, which may bring secondary fault and even blackout. Starting from the relationship between the wavelet eigenvalues of traveling waves and the fault section of distribution lines with DG, the optimal fault features were selected by dimension reduction of linear discriminant analysis (LDA), and then the Bayesian classification model based on kernel distribution was used to realize the new method of Single phase grounding fault location. The IEEE 33-bus model with DGs was constructed to test the faults in different sections of active distribution network, the locating accuracy of the optimal three-dimensional feature sample is 97.9%. The result shows the method can achieve accurate fault location.

To address the challenges of high dimensionality, nonlinearity, and multiple constraints in distribution network fault location, where traditional intelligent optimization algorithms are prone to local optima and slow convergence, this paper proposes a fault location method based on the Archimedes Optimization Algorithm (AOA). By constructing a fault state encoding model for the distribution network, the fault location problem is transformed into a binary optimization problem. Leveraging the global search capability and convergence characteristics of the AOA, rapid and accurate location of faulty sections is achieved. Simulation experiments based on the IEEE 33-node system under various fault scenarios, including single-point and multi-point faults, demonstrate that the proposed method outperforms comparative algorithms in terms of convergence speed.

The addition of distributed generation sources into conventional distribution networks results in several technical challenges for successful operation of distribution network. As far as physical integration is concerned, finding the exact location of fault is a key issue. The coordination between the protection devices existing in the distribution network gets disrupted due to presence of distributed generation (DG). Therefore existing fault location techniques for distribution system will not work properly with penetration of DG. Therefore new fault location schemes for distribution networks with distributed generations (DG) have been developed in the recent times, but there are still problems whose solution needs to be found out. This paper investigates the issues and current state regarding fault location in distribution network with DG. A comparative analysis is carried out in which the merit and demerit of each technique is assessed and some conclusion and suggestion for fault location in distribution system with DG is put forward.

The fault location of an active distribution network is a vital analysis to prevent major outages in the power system. Considering the influence of renewable distributed generations on fault characteristics, this paper proposes a novel location method based on a dynamic quantum genetic algorithm to solve for fault locations in active distribution networks. In the method, the fault current code is measured based on feeder terminal units. A universal switching function is presented to convert the feeder switch status into an uploaded fault current code. The fault location model is defined as an optimization problem that presents the evaluation objective function with an anti-false-positive factor. The dynamic quantum genetic algorithm is developed to locate the fault feeder according to the uploaded fault current code of the feeder terminal unit. The algorithm adopts dynamic rotating gate strategy and adaptive quantum crossover strategy to satisfy the requirements of quickness and accuracy for fault location. Moreover, the method avoids easily falling into a local optimum by integrating the discrete quantum mutation. The proposed fault location technique is tested and compared to other existing techniques on a 33-bus active distribution network. The simulation results show that the proposed fault location method can locate fault feeders accurately with fast computational times under conditions of single or multiple faults and with an information distortion of the feeder terminal unit.

A new method of fault location of distribution network based on the tree structure diagram and improved Dempster-Shafer Theory of evidence is proposed to solve the problem of misjudgment caused by abnormal fault information in distribution network. Firstly, this paper presents a new search method based on tree structure diagram. Through the tree structure diagram, we can ensure the initial positioning result respectively based on three different alarm information. The three alarm information include fault indicator information, distribution transformer information and trouble calls. And then, through using the improved Dempster-Shafer Theory of evidence, we can integrate the initial positioning results to get the final positioning result. Finally, a concrete example is given to demonstrate the effectiveness and feasibility of this method, which indicates that the method can solve the problem when misinformation or information happens. The outstanding advantage of this method is that the multi-source information is used to locate the fault, and the misjudgment due to the abnormality of the single source information can be avoided.