A universal islanding detection technique for distributed generation using pattern recognition

Research output: Contribution to journalArticlepeer-review

162 Scopus citations


Anti-islanding protection methods, proposed in the literature, are distributed generation (DG) type dependent or in other words work efficiently for a specific DG type (synchronous or inverter based). In this paper, we investigate the possibility of developing an efficient universal islanding detection method that can be applied to both inverter and synchronous-based DG. The proposed method relies on extracting a group of features, from measured data simulated for both types of DGs, from which the best features are selected for islanding detection. A random forest (RF) classification technique is used to detect islanding and non-islanding situations with an objective of minimizing the non-detection zone as well as avoiding nuisance DG tripping during non-islanding conditions. Islanding and non-islanding cases were generated for the IEEE 34-bus system and used to train and test the proposed technique. In the paper, k-fold cross-validation was used in order to test the accuracy of the proposed algorithm for detecting islanding. The results show that the proposed methodology has zero non-detection zone, high accuracy, and fast response when applied to both types of DGs independently of the size of the island. Among the various classification approaches investigated, the RF technique proved to be the most efficient approach for the proposed islanding detection method.

Original languageBritish English
Article number6839084
Pages (from-to)1985-1992
Number of pages8
JournalIEEE Transactions on Smart Grid
Issue number4
StatePublished - Jul 2014


  • Decision tree
  • inverter-based distributed generator
  • islanding detection
  • naïve Bayes
  • neural network
  • random forest (RF)
  • support vector machine (SVM)
  • synchronous-based distributed generator


Dive into the research topics of 'A universal islanding detection technique for distributed generation using pattern recognition'. Together they form a unique fingerprint.

Cite this