Voltage‐based protection of microgrids using decision tree algorithms

Abstract

Summary This paper presents a protection method for microgrids by data mining of voltage disturbances. The occurrence of a fault on the system is associated with a sudden voltage depression, which is fast detected by the adaptive cumulative sum (ACUSUM) algorithm. There are other operational (no‐fault) events causing voltage depression such as motor starting, transformer energizing, and capacitor or heavy load switching. In order to discriminate between the fault and no‐fault events, one cycle of the voltage waveform is preprocessed by the short‐time Fourier transform (STFT) to extract and construct effective features of the disturbance. The features are then used in the decision trees (DTs) for the discrimination. The proposed protection method is tested for fault or no‐fault conditions of grid‐connected or islanded mode of the microgrid operation, as well as radial or meshed topology. The proposed method also identifies the fault type and faulted phase(s) for selective phase tripping. The immunity of the method against different noise levels is investigated. It is shown by the simulation study that by using only two features for symmetrical events and six features for asymmetrical events, any fault can be detected accurately.

Identification of faulted line section in microgrids using data mining method based on feature discretisation

“…For identification of the faulted line section, selection of a set of features that can describe the characteristics of input signal is very important. Therefore, a set of features (two electrical features, that is, energy and root mean square [RMS], and two statistical features, that is, mean and standard deviation [SD]) which have shown their efficiency in the classification of power quality disturbances are chosen as the classifiers input features . These features are:…”

“…There are different solutions proposed in the literature to deal with the protection challenge of microgrids, including adaptive overcurrent methods, directional element method, differential‐based methods, voltage‐based methods, and data mining‐based methods …”

“…Data mining methods are robust, fast computing, and more accurate. Therefore, they have the potential to be utilised for complex classification problems such as microgrids protection …”

“…Manohar et al propose the use of ensemble classifiers for microgrid protection. Ranjbar et al apply DT algorithms for fault detection using features of voltage waveforms considering major events that cause voltage drops in microgrids.…”

“…Among the valuable data mining‐based research works presented in References on microgrid protection, the methods of References use data mining techniques for identification of faulted line section. The method used in Reference provides accurate results for small‐scale microgrids in islanded mode with radial configuration.…”