No abstract

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 of the island. A decision-tree classifier is trained to categorize the transient generating events as "islanding" or "non-islanding." The feature vectors required for classification were extracted from the transient current and voltage signals through discrete wavelet transform. The proposed technique is tested on a medium-voltage distribution system with multiple distributed generators. The results indicate that this technique can accurately detect islanding events very fast.

Part I of this paper describes the design and implementation of an islanding detection method based on transient signals. The proposed method utilizes discrete wavelet transform to extract features from transient current and voltage signals. A decision-tree classifier uses the energy content in the wavelet coefficients to distinguish islanding events from other transient generating events. The verification tests performed in Part I, for a two generator test system having a synchronous generator and a wind farm, showed more than 98% classification accuracy with 95% confidence and a response time of less than two cycles. In Part II, the proposed methodology is applied to an extended test system with a voltage-source converter-based dc source. The proposed relay's performance is compared with the existing passive islanding detection methods under different scenarios. Furthermore, the effect of noise on the performance of the proposed method is studied. The transient-based islanding detection methodology exhibits very high reliability and fast response compared to all other passive islanding detection methods and shows that the relay can be designed with a zero nondetection zone for a particular system.

No abstract

No abstract