Novel Fault Location Method for Power Systems Based on Attention Mechanism and Double Structure GRU Neural Network

Abstract

Fault location is one of the most essential techniques to maintain the stable operation of power systems. A fast and accurate fault location allows operators to restore power grids faster and avoid economic losses. Conventional methods rely on expert knowledge to extract the necessary features (e.g. DWT, DFT). For large systems, more coupling effects of transmission lines require more complex feature engineering, and incomplete features can easily introduce large errors. To overcome this, a deep learning approach without manual feature extraction is introduced to the fault location model under big data application. Towards this end, in the proposed method, the attention mechanism, the Bi-GRU and a dual structure network are applied to analyze the current data from different perspectives. Complete information for the fault features is extracted for the fault location. Based on a time series model and benefit from the ability to internally acquire the information architecture of faulty line, the established model is adaptive to the power grids with very complex topologies. Simulation results indicate that the proposed double-structure model reduces the maximum error and is less affected by noise. In comparison with different structures and different models, the proposed method shows better performance in IEEE 39-bus system.

A New Approach to the Fault Location Problem: Using the Fault’s Transient Intermediate Frequency Response

“…This is evident in the fact that there are currently no centralised fault location methodologies available in transmission or distribution grid protections [3], [4], [5]. As such, there is still ongoing research to improve each technique into a reliable and applicable methodology [6], [7], [8].…”

“…From equations (3)-(4) it is possible to see that the initial conditions V 1 (t f ), V 2 (t f ), φ 1 (t f ) and φ 2 (t f ) are defined by the fault's occurrence time t f . The frequency of each transient response however, is dependent exclusively on the fault location according to equations ( 5)- (6).…”

Large-Scale Sequential Learning for Recommender and Engineering Systems

“…Traditional data-driven methods for fault localization, such as travelling-wave [Parsi et al, 2020] and impedance based ones [Aucoin and Jones, 1996], require high grid observability and sampling rates that are technically challenging and expensive for bulky systems [Sundararajan et al, 2019] or even known distribution of renewables [Owen et al, 2019. Another line of algorithms leverages deep neural networks capabilities [Li et al, 2019, Li and Deka, 2021a, Zhang et al, 2020a, Misyris et al, 2020; however, these methods suffer from high requirements on the amount of phasor-measurement unit data. The latter lead to inability to make a accurate and timely detection in time-changing environment that is intrinsic for extreme weather events and, therefore, compromises power grid security.…”

A Single-Terminal Fault Location Method for HVDC Transmission Lines Based on a Hybrid Deep Network

“…With the rapid development of artificial intelligence, machine learning has begun to be applied to various tasks in the electrical engineering field, such as load forecasting [18], optimal scheduling [19], fault diagnosis [20], etc. Machine learning-based methods are considered to be a tool for performing soft computing in fault location [21]. Shallow neural networks were used to distinguish fault locations considering different fault types [22].…”

“…These recurrent networks as a regressor can be used for fault location. In Reference [21], Bi-GRU was used to identify faulty lines and locate faults in a distribution network. However, considering the unobvious identification of traveling wave characteristics caused by HIF, it may not be able to solve the problem of the scenario of considering large transition resistance.…”