Fault Detection In Distribution Networks Research Articles

Fault Detection in Distribution Network with the Cauchy-M Estimate—RVFLN Method

Fault detection is an important issue in today’s distribution networks, the structure of which is becoming more complex. In this article, a data-based Cauchy distribution weighting M-estimate RVFLNs method is proposed for short-circuit fault detection in distribution networks. The proposed method detects short circuits based on current and voltage measurements. In addition, noises were added to the data to ensure the robustness of the method. The performance of the method was examined in the RTDS RTS simulator using the IEEE 33-bus-bar system model with the help of real-time simulations. The success rate of the proposed method is between 98% and 100% for low-impedance (0 ohm) short-circuit faults, depending on the fault type. The success rate of high-impedance (100 ohm) short-circuit faults, which are more difficult to detect, is between 80% and 92%, depending on the fault type.

A protection scheme based on conditional generative adversarial network and convolutional classifier for high impedance fault detection in distribution networks

• Combination of Conditional GAN with Convolutional classifier is proposed for fault detection. • Third Harmonic Angel (THA) of fault current is used as an effective feature. • Little amount of training data is used to train CGAN. • High performance of the CGAN in generation of pseudo-real data in large scale. Low level current and similarity of High Impedance Faults (HIF) in respect of characteristics to other transient events have posed a critical challenge to the protection of distribution systems. In addition, the dependency of previous methods on large amounts of training data increases the simulation error rate, and preparing this amount of data is time-consuming. In this paper, a novel scheme based on conditional generative adversarial network (CGAN) and convolutional neural network (CNN) classifier techniques is proposed, that reduces this dependency and leads to acceptable classification accuracy . In the proposed method, a small amount of data is extracted from the under-study network as the real data. Then, the third harmonic angle of the current is extracted from the real data by an adaptive linear neuron (ADALINE) as an effective feature. The CGAN is performed to produce a large amount of pseudo data. At last, the fault data is separated from other transient network events via the CNN classifier. Five different scenarios are used to evaluate the proposed method on a 13-bus IEEE network. The simulation results show that the Precision and Recall of distinguishing HIFs from other transient events is greater than 98% in all the scenarios. These results verify that the proposed scheme is very accurate despite the low dependency on input training data.

Effect of Distributed Photovoltaic Generation on Short-Circuit Currents and Fault Detection in Distribution Networks: A Practical Case Study

The increase in the installation of renewable energy sources in electrical systems has changed the power distribution networks, and a new scenario regarding protection devices has arisen. Distributed generation (DG) might produce artificial delays regarding the performance of protection devices when acting as a result of short-circuits. In this study, the preliminary research results carried out to analyze the effect of renewable energy sources (photovoltaic, wind generation, etc.) on the protection devices of a power grid are described. In order to study this problem in a well-defined scenario, a quite simple distribution network (similar to the ones present in rural areas) was selected. The distribution network was divided into three protection zones so that each of them had DG. In the Institute of Electrical and Electronic Engineers (IEEE) system 13 bus test feeder, the short-circuits with different levels of penetration were performed from 1 MVA to 3 MVA (that represent 25%, 50%, and 75% of the total load in the network). In the simulations carried out, it was observed that the installation of DG in this distribution network produced significant changes in the short-circuit currents, and the inadequate performance of the protection devices and the delay in their operating times (with differences of up to 180% in relation to the case without DG). The latter, that is, the impacts of photovoltaic DG on the reactions of protection devices in a radial distribution network, is the most relevant outcome of this work. These are the first results obtained from a research collaboration framework established by staff from ETSI Civil and the IDR/UPM Institute, to analyze the effect of renewable energy sources (as DG) on the protection devices of a radial distribution network.

Fault detection in distribution networks in presence of distributed generations using a data mining–driven wavelet transform

Here, a data mining–driven scheme based on discrete wavelet transform (DWT) is proposed for high impedance fault (HIF) detection in active distribution networks. Correlation between the phase current signal and the related details of the current wavelet transform is presented as a new index for HIF detection. The proposed HIF detection method is implemented in two subsequent stages. In the first stage, the most important features for HIF detection are extracted using support vector machine (SVM) and decision tree (DT). The parameters of SVM are optimised using the genetic algorithm (GA) over the input scenarios. In second stage, SVM is utilised to classify the input data. The efficiency of the utilised SVM-based classifier is compared with a probabilistic neural network (PNN). A comprehensive list of scenarios including load switching, inrush current, solid short-circuit faults, HIF faults in the presence of harmonic loads is generated. The performance of the proposed algorithm is investigated for two active distribution networks including IEEE 13-Bus and IEEE 34-Bus systems.

High-Impedance Fault Detection in Distribution Networks With Use of Wavelet-Based Algorithm

A new simple and effective algorithm of arcing fault detection in distribution networks with the application of a wavelet transform technique is presented in this paper. The protection algorithm developed observes the phase displacement between wavelet coefficients calculated for zero-sequence voltage and current signals at a chosen high-level frequency. The final decision in regards to feeder switching off (or alarm issuing) is met either with a deterministic logic scheme or with the use of a neural net trained especially for that purpose. The developed wavelet-based high-impedance fault (HIF) detector has been tested with Electromagnetic Transients Program-Alternative Transients Program (ATP)-generated signals, exhibiting better performance than traditionally used algorithms and methods. The protection method proposed may be used for HIF detection independent of the network neutral-point grounding mode. The scheme proved to be robust against transients generated during normal events such as feeder energizing and de-energizing as well as capacitor bank switching