Faults in distribution networks occur unpredictably, causing a threat to public safety and resulting in power outages. Automated, efficient, and precise detection of faulty sections could be a major element in immediately restoring networks and avoiding further financial losses. Distributed generations (DGs) are used in smart distribution networks and have varied current levels and internal impedances. However, fault characteristics are completely unknown because of their stochastic nature. Therefore, in these circumstances, locating the fault might be difficult. However, as technology advances, micro-phasor measurement units (micro-PMU) are becoming more extensively employed in smart distribution networks, and might be a useful tool for reducing protection uncertainties. In this paper, a new machine learning-based fault location method is proposed for use regardless of fault characteristics and DG performance using recorded data of micro-PMUs during a fault. This method only uses the recorded voltage at the sub-station and DGs. The frequency component of the voltage signals is selected as a feature vector. The neighborhood component feature selection (NCFS) algorithm is utilized to extract more informative features and lower the feature vector dimension. A support vector machine (SVM) classifier is then applied to the decreased dimension training data. The simulations of various fault types are performed on the 11-node IEEE standard feeder equipped with three DGs. Results reveal that the accuracy of the proposed fault section identification algorithm is notable.

In this study, a practical method is proposed for determining the distance and the section of fault in power distribution system (PDS). In the suggested method, at first the possible fault points are determined using a novel impedance‐based fault location method. Since the number of these points may be more than one, thus two methods are proposed for determining the real location of fault. In the first method, the measured and recorded samples of voltages at the beginning of feeder for actual fault are compared with the stored samples of voltages which are obtained from simulating of fault at the possible fault points. The one with highest matching is the real location of fault. In the second method, frequency spectrum (FS) of voltage is defined as a suitable criterion for this purpose. Therefore the real fault point is determined by comparing and matching the FS of voltages obtained from the simulated faults and the recorded voltage for actual fault. The performance of the proposed method is evaluated in a real feeder in distribution network of Iran considering different types of faults, fault resistances, fault inception angles, real instrument transformer models and X / R ratio changes of upstream PDS network. The obtained results show that the performance of the proposed method is quite satisfactory and its accuracy is very high.

Fault location techniques play an essential role in system recovery and repair. Therefore, numerous methods have been presented for fault location in power transmission and distribution networks. The contribution of this paper is to extend the state-of-art impedance-based fault location methods to support four-wire power distribution. To make this possible an algorithm is developed. The method is obtained using principles of circuit theory and overcomes the challenges which prevent use of most fault location methods for distribution networks in practice. The paper presents the detailed equations which are used in the algorithm and how they are obtained. The satisfactory performance of the algorithm is confirmed with numerical examples using MATLAB software.