Passive Islanding Detection Based on Angular Velocity Harmonic Patterns with Perceptron Neural Network

Traditional islanding detection methods present improper action when the power mismatch between generation and load in the islanding system is small. The minimum power mismatch for correct islanding detection defines the limits os a Non-Detection Zone. This paper proposes an efficient method for islanding detection based on angular velocity harmonic patterns. To accomplish this, the measured frequency is decomposed by a Fourier Transform and applied to a Perceptron artificial neural network for pattern classification. The performance of the proposed method is evaluated by tests on a modified IEEE 34 node test system. Several islanding and non-islanding cases were simulated. The proposed method achived a performance of 88.16% in the classification of harmonic patterns with a small training set. Compared with the Under/Over frequency method, the proposed method represents a performance improvement of 17%.