A Pattern Recognition Approach for Detecting Power Islands Using Transient Signals—Part I: Design and Implementation

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.

Impact of Islanding Detection Time Duration on the Stable Operation of a Synchronous Generator Controlled Microgrid

“…Considering both, reliability and response time, transfer trip schemes or use of fast islanding detection methods such as the transients based islanding detection method proposed in [25] would be more suited for microgrids with reliability objectives. The conclusions are drawn for a substation level microgrid with a synchronous generator and no energy storage.…”

“…The detection time depends on the communication method, and in general it is in-between 30 ms and 200 ms [23,24]. A new methodology based on transient signals that uses discrete wavelet transform and pattern recognition techniques has shown a detection time less than two cycles, while being highly reliable in detecting islands [20,25].…”

A Universal Islanding Detection Technique for Distributed Generation Using Pattern Recognition

“…Second, a feature selection algorithm is used to determine the most effective combination of features that can be used to detect islanding accurately and that can be applied to both the Inverter-based DG and the Synchronousbased DG. The sequential feature selection methods, such as the Forward Feature Selection (FFS) and the Backward Feature Selection (BFS), are used to select the best features [29,30] to be used for islanding detection. At the end, the Random Forest algorithm is used to distinguish islanding from non-islanding events.…”

Shifting of research trends in islanding detection method - a comprehensive survey

“…Owing to this boost algorithm, 100% accuracy is reached with negligible NDZ. [89] used DWT and DT for ID based on extracted current and voltage transient features for a medium voltage distribution system incorporating multiple DGs. The detection time is 24 ms with 99.22% accuracy and 95% confidence.…”