The integration of the distributed power generation into a distribution system comes with several system problems. One of the teething problems related to system protection is islanding detection. Various anti-islandi...
详细信息
The integration of the distributed power generation into a distribution system comes with several system problems. One of the teething problems related to system protection is islanding detection. Various anti-islanding techniques based on feature evaluation were proposed in the recent past. However, they overlook the need for justifying the selection of a particular detection feature among all the possible measures. In this study, a wrapper feature selection approach is proposed where a modified multi-objective differentialevolutionalgorithm is coupled with a kernel-based extreme learning machine classifier. To select the optimum features, five standard objective functions have been considered, such as dependability, security, accuracy, F-measure, and the number of features. About 1864 cases have been generated from the designed IEEE 13 bus system to extract the sensitive features. IEEE 1547 standards have been considered while designing and testing the IEEE 13 bus system against islanding. The selected optimal features detect the islanded condition decisively for both synchronous and inverter-based distributed generators. The features also validate their performance under noisy environment accurately with lesser computational time.
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 hav...
详细信息
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.
暂无评论