Power Grid Fault Research Articles

Efficient Fault Detection and Analysis of Power System Distribution Networks by Integrating BP Data Mining

As the basic guarantee for people’s production and life, the safe operation of the power system has an important impact on the development and operation of society. To ensure the safe and stable operation of the power grid, predicting potential faults and taking reasonable preventive measures can effectively avoid the occurrence of power accidents. However, due to the difficulty in ensuring the prediction accuracy of traditional methods, there are issues of protection misoperation and rejection. Therefore, in order to achieve accurate prediction of power grid faults and avoid protection misoperation and rejection issues, a distribution network fault classification prediction model using a combination of three-layer data mining model (TLDM) and adaptive moment estimation (Adam) algorithm/random gradient descent algorithm improved backpropagation neural network (BPNN) is proposed. The implementation results showed that the classification accuracy of artificial fish school [Formula: see text] priori, [Formula: see text]-means clustering convolutional neural network model and TLDM for single-phase grounding faults was 93.2%, 91.5% and 96.6%, respectively. The classification accuracy for two-phase faults was 92.8%, 92.4% and 95.7%, respectively. The classification accuracy for two-phase grounding faults was 93.7%, 91.2% and 96.9%, respectively. The classification accuracy for three-phase faults was 93.3%, 92.1% and 97.1%, respectively. The TLDM had the highest classification accuracy. The average accuracy, average accuracy and average recall of the BPNN improved by the combination of the ADAM algorithm and random gradient descent algorithm were 94.1%, 90.9% and 88%, respectively, which were higher than the BPNN improved by the combination of ADAM algorithm and random gradient descent algorithm. The above results indicate that the proposed distribution network fault classification and prediction model has good performance and can achieve accurate prediction of distribution network faults.

A Power Grid Topological Error Identification Method Based on Knowledge Graphs and Graph Convolutional Networks

Precise and comprehensive model development is essential for predicting power network balance and maintaining power system analysis and optimization. The development of big data technologies and measurement systems has introduced new challenges in power grid modeling, simulation, and fault prediction. In-depth analysis of grid data has become vital for maintaining steady and safe operations. Traditional knowledge graphs can structure data in graph form, but identifying topological errors remains a challenge. Meanwhile, Graph Convolutional Networks (GCNs) can be trained on graph data to detect connections between entities, facilitating the identification of potential topological errors. Therefore, this paper proposes a method for power grid topological error identification that combines knowledge graphs with GCNs. The proposed method first constructs a knowledge graph to organize grid data and introduces a new GCN model for deep training, significantly improving the accuracy and robustness of topological error identification compared to traditional GCNs. This method is tested on the IEEE 30-bus system, the IEEE 118-bus system, and a provincial power grid system. The results demonstrate the method’s effectiveness in identifying topological errors, even in scenarios involving branch disconnections and data loss.

Predictive Models for Aggregate Available Capacity Prediction in Vehicle-to-Grid Applications

The integration of vehicle-to-grid (V2G) technology into smart energy management systems represents a significant advancement in the field of energy suppliers for Industry 4.0. V2G systems enable a bidirectional flow of energy between electric vehicles and the power grid and can provide ancillary services to the grid, such as peak shaving, load balancing, and emergency power supply during power outages, grid faults, or periods of high demand. In this context, reliable prediction of the availability of V2G as an energy source in the grid is fundamental in order to optimize both grid stability and economic returns. This requires both an accurate modeling framework that includes the integration and pre-processing of readily accessible data and a prediction phase over different time horizons for the provision of different time-scale ancillary services. In this research, we propose and compare two data-driven predictive modeling approaches to demonstrate their suitability for dealing with quasi-periodic time series, including those dealing with mobility data, meteorological and calendrical information, and renewable energy generation. These approaches utilize publicly available vehicle tracking data within the floating car data paradigm, information about meteorological conditions, and fuzzy weekend and holiday information to predict the available aggregate capacity with high precision over different time horizons. Two data-driven predictive modeling approaches are then applied to the selected data, and the performance is compared. The first approach is Hankel dynamic mode decomposition with control (HDMDc), a linear state-space representation technique, and the second is long short-term memory (LSTM), a deep learning method based on recurrent nonlinear neural networks. In particular, HDMDc performs well on predictions up to a time horizon of 4 h, demonstrating its effectiveness in capturing global dynamics over an entire year of data, including weekends, holidays, and different meteorological conditions. This capability, along with its state-space representation, enables the extraction of relationships among exogenous inputs and target variables. Consequently, HDMDc is applicable to V2G integration in complex environments such as smart grids, which include various energy suppliers, renewable energy sources, buildings, and mobility data.

Robust distance protection for cross-country faults in power grids with high penetration of inverter- based resources

Cross-country faults can adversely affect the operation of protection devices. Relays whose pickup is based on overcurrent or impedance elements are more likely to fail during cross-country faults. The failure can be expressed as an unnecessary trip of all phases during a single-phase fault or even blocked relay functions. Relays may also fail to operate due to low fault currents, which is the case when power grids make use of many inverter-based resources (IBR) or when two simultaneous faults occur in the same phase and in different locations. This paper proposes a Recursive Discrete Stockwell Transform (RDST) method for addressing the mentioned challenges. The energy content computed by the RDST is used for fault detection and faulty phase selection. A robust distance relay model is proposed to ensure correct relay performance and is combined with a directional and an impedance trajectory module. The proposed method performance is thoroughly evaluated by applying real-time simulations for 6480 different cross-country faults, including three repetitions, four different generators (Synchronous generators, Wind turbine type-III, Wind turbine type-IV), two rating powers, three different fault distances, five different types of faults, and six grid codes. Ninety cases are also tested with real devices in hardware in the loop. Simulation results confirm the method's ability to detect different fault types, even during low fault currents, and to ensure high accuracy in phase selection.

AC fault ride-through control strategy of MMC-UHVDC system with hierarchical connection mode

The ultra-high voltage direct current (UHVDC) transmission composed of modular multilevel converters (MMC) is an important technology for large-scale centralized transmission of renewable energy. In UHVDC system, temporary faults in the AC power grid system are a high probability fault, and the fault control strategy affects the safety and reliability of system operation. This paper studies on the condition of AC power grid faults occurring at the receiving converter station. Firstly, study the system characteristics after the occurrence of AC faults, and use theoretical analysis to derive the trend of DC voltage changes of each converter valve. Then, an AC fault ride-through control strategy with high power transmission capability is proposed with hierarchical connection structure, the strategy controls the system to synchronously reduce DC voltage and AC active power after a fault, maximizing the retention of the system’s transmission capacity during the occurrence of faults, thereby reduce power shock in the system. Finally, a simulation model of the dual ended system has built based on the PSCAD simulation platform. The simulation results show that when a single-phase ground fault and a three-phase ground fault occur in the high valve group at the receiving station, the system can retain about 83% and 50% of the transmission capacity during the fault period, respectively. Meanwhile, there is no serious overvoltage or overcurrent phenomenon in the system. The simulation results verified the effectiveness of the proposed control strategy.

Optimized voltage support strategy under asymmetrical faults in power grids

Abstract Asymmetrical faults in the grid can lead to voltage drops at the grid-connected points, and in serious cases, there is also a risk of cutting the machine. The traditional voltage support strategy is easily affected by the output of the units and cannot support the voltage flexibly. To address the above problems, an optimized strategy for boosting voltage performance is proposed under asymmetrical faults in the power grid. Firstly, the voltage support principle under asymmetrical fault is analyzed, and the voltage support equation is derived. Then, based on the above equations, an optimal voltage support strategy under asymmetrical faults is proposed by taking the operation requirements of grid-connected standard voltage as the objective and considering the peak current and active power fluctuation amplitude as the constraints. Finally, the effectiveness and flexibility of the above strategy are validated by simulation.

ESG guidance and artificial intelligence support for power systems analytics in the energy industry.

In order to increase the precision and effectiveness of power system analysis and fault diagnosis, this study aims to assess the power systems in the energy sector while utilizing artificial intelligence (AI) and environmental social governance (ESG). First, the ESG framework is presented in this study to fully account for the effects of the power system on the environment, society, and governance. Second, to coordinate the operation of various components and guarantee the balance and security of the power system, the CNN-BiLSTM power load demand forecasting model is built by merging convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM). Lastly, the particle swarm optimization (PSO) algorithm is used to introduce and optimize the deep belief network (DBN), and a power grid fault diagnostic model is implemented using the PSO technique and DBN. The model's performance is assessed through experimentation. The outcomes demonstrate how the CNN-BiLSTM algorithm significantly increases forecasting accuracy while overcoming the drawback of just having one dimension of power load data. The values of 0.054, 0.076, and 0.102, respectively, are the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Effective processing of large-scale nonlinear data is achieved in the area of power grid fault diagnosis, resulting in prediction accuracy of 96.22% and prediction time of only 129.94s. This is clearly better than other algorithms and increases fault prediction efficiency and accuracy. Consequently, the model presented in this study not only produces impressive results in fault diagnosis and load demand forecasting, but also advances the field of power system analysis in the energy industry and offers a significant amount of support for the sustainable and intelligent growth of the energy industry.

An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.

Fisher matrix based fault detection for PMUs data in power grids

In this paper, using the data collected from phasor measurement units (PMUs), two methods based on Fisher random matrix are proposed to detect faults in power grids. Firstly, the fault detection matrix is constructed and the event detection problem is reformatted as a testing problem for two-sample covariance matrices, which is related with the so-called Fisher matrix. To save computing resources, the screening step of fault interval based on the test statistic is designed to check the existence of faults. Then two point-by-point methods are proposed to determine the time of the fault in the selected interval. One method detects faults by the limiting spectral distribution of the standard Fisher matrix, which can detect the faults with higher accuracy. The other method tests the faults based on the proposed test statistic , which has a faster detection speed. Compared with existing works, the simulation results illustrate that two methods proposed in this paper cost less computational time and provide a higher degree of accuracy and sensitivity.

Fault prevention strategy for coupled networks of power grids and transportation with the participation of electric vehicles

The increasing number of electric vehicles (EVs) that are connected to the power grid has raised concerns about the security of both transportation and power grids. This paper presents a fault prevention strategy that involves the use of social networks to improve the performance of electric vehicle charging stations. Firstly, the goal of this strategy is to improve the electric vehicle charging station’s performance by developing an evolutionary game model that takes into account the various factors that affect the electric vehicle’s response and travel time. Secondly, a number of charging station sample data is generated and analyzed using a convolutional neural framework. The capacity of the stations is then calculated by taking into account the different incentive measures offered by the power grid.. Furthermore, an optimal power flow model considering fault risk constraints and charging and discharging capacity constraints is established in the power grid or power grid subsystem to adjust the generator output and charging station power to realize the safe dispatching of the power grid. The simulation example shows that this method can fully consider the influence of traffic networks in the participation of EVs in power grid fault prevention, which is more reasonable.

Quasi Z-Source Direct Matrix Converter for Enhanced Resilience to Power Grid Faults in Permanent Magnet Synchronous Motor Applications

In this paper, a voltage control system for a PMSM motor based on the QZSDMC converter is proposed, which allows operation in both buck and boost modes as a possible method to make the drive resistant to power grid voltage sags. The authors presented a method for measuring and transforming the output voltage from QZS, enabling the use of a PI controller to control the voltage supplied to the DMC converter. The publication includes simulation and experimental studies comparing the operation of a PMSM motor powered by DMC and the proposed QZSDMC with voltage regulation. Simulation studies confirm the drive with QZSDMC resistance to voltage sags up to 80% of the rated value. Experimental studies demonstrate the correct operation of PMSM even with a power grid voltage amplitude equal to 40% of the rated value.

Research on data-driven model for power grid fault diagnosis fusing topological quantification information

In increasingly complex power grid operation scenarios and fault modes, rapid and accurate fault identification is highly important for improving the reliability of power systems. Faced with the massive amount of available power grid data, the rapid development of artificial intelligence technology provides a powerful tool for power grid fault diagnosis. However, existing data-driven diagnosis methods lack quantitative power grid topology change representations, cannot integrate power grid fault topology with alarm information, and have limited effectiveness in terms of diagnosing complex faults. To address these issues, a data-driven power grid fault diagnosis model that integrates topological quantitative features is proposed. By studying the changes in the topological connection relationships of equipment before and after a power grid fault and the topological connectivity in a power failure zone, based on the basic topological network indicators in graph theory, a representation of the quantitative features of the power grid fault topology is achieved, and these quantitative features and the alarm information are integrated to construct a data-driven power grid fault diagnosis model. The model uses the light gradient boosting machine algorithm to determine the types of complex faults and accurately identify faulty equipment, addressing the lack of model diagnosis effects considered in previous studies. Finally, the accuracy and effectiveness of the model are verified by using simulated fault cases.

Model Predictive Control on Transient Flux Linkage and Reactive Power Compensation of Doubly Fed Induction Wind Generator

For weak grid scenario with high new energy proportion, large fluctuations of load are prone to cause low-voltage ride through. Moreover, stator transient magnetic flux will cause overvoltage and overcurrent problems in the rotor of doubly fed induction generator. Based on model predictive control, a control strategy for transient flux linkage and reactive power compensation is proposed. Firstly, regarding the issue of reactive power allocation of grid side converters (GSC) and rotor side converters (RSC), an allocation strategy is derived under minimizing winding energy loss on case of low-voltage ride through, enabling the wind energy conversion system to provide reactive power support during grid voltage recovery process. Meanwhile, an improved mixed second- and third-order generalized integrator (MSTOGI) phase-locked loop (PLL) is used to extract the positive and negative sequence components of the power grid voltage, further for RSC control. Secondly, in response to power grid faults, considering the influence of stator DC transient flux and negative sequence flux components on rotor current, by injecting rotor transient compensation current and stator flux feedforward compensation into RSC, the rotor impulse voltage and loop current are reduced. Moreover, combined with model predictive control algorithm, a control strategy of rotor current is designed. Finally, a simulation platform is built to validate the effectiveness of the proposed method based on comparing with several traditional vector control low-voltage ride through methods.

Hypertuned-YOLO for interpretable distribution power grid fault location based on EigenCAM

Ensuring the reliability of electrical distribution networks is a pressing concern, especially given the power outages due to surface contamination on insulating components. Surface contamination can elevate surface conductivity, thereby resulting in failures that can lead to power shutdowns. Addressing this challenge, this paper proposes an approach for real-time monitoring of electrical distribution grids to prevent such incidents. A hypertuned version of the you only look once (YOLO) model is tailored for this application. We refine the model's hyperparameters by integrating a genetic algorithm to maximize its detection performance. The EigenCAM technique enhances the visual interpretability of the model's outcomes, providing operators with actionable insights for maintenance and monitoring tasks. Benchmark tests reveal that the proposed Hypertuned-YOLO outperforms Detectron (Masked R-CNN), YOLOv5, and YOLOv7 models. The Hypertuned-YOLO achieves an F1-score of 0.867 and a mAP@0.5 of 0.922, validating its robustness and efficacy.

Analysis and research on short-circuit current characteristics and grid access faults of wind farms with multi-type fans

As the grid-connected capacity of a large number of wind farms continues to increase, their short-circuit current will have a great impact on protection. Therefore, accurate short-circuit current calculation is beneficial for correct protection action evaluation. Considering the issues related to the diversity of wind turbine types in wind farms and the inability to accurately simulate the failure transient process in previous studies, this research focuses on investigating the impact of control strategies during faults on the transient process of wind turbines. In this paper, the single-machine equivalent model of doubly-fed induction generators (DFIG) and permanent magnet synchronous machine (PMSM) is established by considering the types of wind turbines, and the calculation method of short-circuit current of hybrid wind farms is further proposed by using the classification aggregation equivalent effect method. The accuracy of short-circuit current calculation proposed in this article was verified on RTDS, and a power grid fault analysis method suitable for wind farm connection was proposed based on the characteristics of equivalent circuits of DFIG and PMSM during fault steady-state.

Multi-Objective PSO for Control-Loop Tuning of DFIG Wind Turbines with Chopper Protection and Reactive-Current Injection

The control systems for the variable-speed wind turbine based on the Doubly Fed Induction Generator (DFIG) pose some tuning challenges. The performance and stability of DFIG wind turbines during faults in power grids are directly related to their controller settings. This work investigates how incorporating protection via a braking-Chopper controller connected to the DC link (DC Chopper) and a reactive-current injection during the PI-tuning process affects the performance of DFIG wind turbines during electrical faults. For the tuning process, the Multi-Objective-Particle-Swarm-Optimization (MOPSO) algorithm was used. Thus, two different approaches adopting this methodology were investigated, considering sequential and simultaneous tuning. The results showed that sequential tuning presented a better performance in relation to the reactive-current injection and lower amplitude deviations of the electrical quantities during and after the fault. On the other hand, simultaneous tuning reached damping of the mechanical oscillations faster and presented better performance of the protection system.

Design of an intelligent decision model for power grid fault location and isolation based on topology analysis

Detecting and isolating power grid faults quickly and efficiently ensures a constant power flow. The lack of speed and accuracy in conventional approaches to fault management highlights the importance of creating a smart decision model. The suggested approach uses topology analysis to better localize and isolate faults, reducing downtime and boosting grid performance. Real-time fault detection, precise fault location identification, and choosing the best isolation schemes are all difficulties in power grid fault management. Furthermore, significant issues need innovative solutions, such as managing the grid's complexity, responding to changing load conditions and guaranteeing cyber security. The present research unveils a new approach combining the Intelligent Decision Model integrated with the Supervisory Control and Data Acquisition system (SC-DAS). Here, Real-time decision-making, control, and monitoring are made possible by the SC-DAS system, which mediates between the intelligent decision model and the physical grid. In SC-DAS, Phasor Measurement Units (PMUs) are used for the real-time monitoring of the grid's electrical properties, which are collected using SCADA (Supervisory Control and Data Acquisition) systems. Further, SC-DAS uses decision-making models for instantaneous modifications and remedial measures of the grid's functioning. The grid's reliability uses Topological DAS for fault detection, localization, and isolation. Topological DAS represents a revolutionary approach that could significantly improve power grid reliability, reduce interruption frequency, and boost overall system performance in microgrids and renewable energy sources. The grid layouts, load circumstances, and fault scenarios used in the simulations help to improve the decision-making strategies in a controlled environment.

Study on smart grid fault detection based on ZigBee and MapX technologies

As the complexity of the power system and the increasing demand for electricity continue to rise, ensuring the reliability and stability of the power system becomes critically important. This study utilizes ZigBee communication modules to establish a sensor network for real-time monitoring of the power system's status and employs MapX technology to achieve geographic information visualization of the power system. Through an improved RBF-PCA-WFCM algorithm, grid data can be dimensionally reduced, enabling simulation training tailored to grid loads, resulting in more accurate algorithm analysis and optimization. This paper introduces fault localization and diagnostic methods, as well as clustering optimization algorithms, to achieve fault monitoring, analysis, and identification in the smart power grid. Research findings demonstrate that the intelligent power grid data analysis and fault detection system based on ZigBee and MapX technologies can enhance the reliability of the power system and better support the increasing demands of the evolving field of electricity.

Research on the Control Method of the PV Grid-Connected Inverter under an Asymmetrical Power Grid Fault

The negative-sequence current component and harmonic components generated when an asymmetrical fault occurs in the power grid seriously affect the normal operation of the photovoltaic (PV) grid-connected inverter. In order to suppress the negative-sequence current component and the harmonic component of the grid-connected current, and to meet the normal grid-connected operation requirements of the PV grid-connected inverter when asymmetrical faults occur in the grid, this paper proposes the proportional integral double-resonant (PI-DR) current controller, which consists of the PI controller and double-resonant controllers. The PI-DR current controller can directly control the negative-sequence current component and the grid-connected current harmonic component in the output current in the forward synchronous rotating coordinate system, without decomposing the positive and negative sequence currents. The PI-DR current controller ensures that the PV grid-connected inverter can realize normal grid-connected operation and improves the quality of the power when an asymmetrical fault occurs in the power grid. MATLAB/Simulink experiments show that the PI-DR current controller can improve the dynamic characteristics of the PV grid-connected inverter and improve the operating capability of the system when an asymmetrical fault occurs in the power grid.

Power grid fault event reasoning based on entity extraction model of knowledge map

In the initial construction process of smart grid dispatching control system in power grid dispatching control center, because different subsystems are in decentralized development, independent operation and independent management, it is easy to reduce data interconnection, which leads to difficulties in data sharing and restricts the information level of the system. The data is multi-source, and the data format is inconsistent, resulting in the application problems that the data can not be shared, accessed, managed, analyzed and mined in real time among different subsystems. In order to solve the problems of data sharing and mining, this paper constructs a knowledge map entity extraction model to study the power grid fault events. Based on the knowledge map theory, the structured and unstructured data related to power grid dispatching are processed to improve the application efficiency of data. Cleaning the preprocessed data to obtain the corresponding entity value and attribute value. The knowledge extraction model of power grid fault event reasoning knowledge mapping is constructed, and the power grid fault event reasoning knowledge edge mapping system is designed to extract the relationship between events and complete data storage. The experimental results show that the text prediction degree of the proposed model is high, which can reach more than 95; The accuracy is 96.71%, the recall rate is 94.88%, and the F1 value is 9.27%. This proves the feasibility of this study, in order to provide data and theoretical support for intelligent management and real-time dispatching of power grid.