作者: N. W. A. Lidula , A. D. Rajapakse
DOI: 10.1109/TPWRD.2010.2053724
关键词: Feature vector 、 Distributed generation 、 Discrete wavelet transform 、 Feature extraction 、 Pattern recognition 、 Artificial intelligence 、 Voltage 、 Engineering 、 Electrical network 、 Islanding 、 Signal processing
摘要: A novel, pattern-recognition-based approach for fast detection of power islands in a distribution network is investigated. The proposed method utilizes transient signals generated during an islanding event to detect the formation island. decision-tree classifier trained categorize generating events as “islanding” or “non-islanding.” feature vectors required classification were extracted from current and voltage through discrete wavelet transform. technique tested on medium-voltage system with multiple distributed generators. results indicate that this can accurately very fast.