Hybrid islanding detection with optimum feature selection and minimum NDZ

Abstract

Summary Integration of the distributed generators into a distribution system encounters various system issues, and out of those islanding detection is 1 of the major protection problems to focus on. Many detection schemes have been proposed in the recent past, which possess a nondetection zone (NDZ) and usually neglect to provide a justification for the selected detecting features among all possible measures. Sensitive feature selection and minimization of NDZ are the 2 major objectives of this study. This paper comprises of 2 operational modes of designed IEEE 13‐bus test feeder (offline mode and online mode of operation). The offline mode of system operation focuses on selecting the optimal feature vectors using the proposed “modified multiobjective differential evolution algorithm” coupled with an extreme learning machine classifier. The modified multiobjective differential evolution algorithm‐extreme learning machine is applied to find out 2 optimum feature vectors, one by considering accuracy and minimal features and another one by dependability with a single feature as its objective functions. The online mode concentrates on the proposed new hybrid islanding detection method comprised of both passive and active detection techniques. Passive technique implements a decision tree designed by using the obtained accuracy‐based feature vector. Decision tree triggers the active method on suspecting the runtime instances as non‐islanding events to reduce the NDZ. Active method uses the obtained dependability‐based feature vector as an injecting parameter. The test results indicate the efficiency and accuracy of the proposed approach under different circumstances of power mismatch.

A review on real‐time simulation and analysis methods of microgrids

“…[12][13][14][15][16][17][18][19][20][21][22][23][24]36 Islanded Consumers loads are supplied uninterrupted without electrical connection of microgrid and main grid. [21][22][23][24][25][26][27][28][29][30][31][32][33][34] Transition Process of islanding microgrid by upstream switches at the PCC during disturbances in main grid or resynchronization with the main grid once the disturbance is removed [36][37][38][39][40] FIGURE 2 Sample reconfiguration process flowchart 45…”

Data inheritance–based updating method and its application in transient frequency prediction for a power system

“…24,25 In this paper, the wrapper approach 26 is adopted, and the genetic algorithm is taken as its search algorithm. However, the features selected by the existing theory of power system tend to be redundant.…”

A hybrid islanding detection technique for inverter‐based distributed generator units

“…As discussed above, active and passive techniques have some advantages and disadvantages. In order to have their benefits, combining these two groups of methods creates a different category called hybrid methods . Based on the VU parameter as a passive and VPA as an active method, a new hybrid method is suggested here.…”

“…In order to have their benefits, combining these two groups of methods creates a different category called hybrid methods. [13][14][15] Based on the VU parameter as a passive and VPA as an active method, a new hybrid method is suggested here. The implementation of the VPA technique relies on adding the difference between the instant and nominal VPA to the abc-to-dqo block.…”