Author(s)

Zhang Yang, Chen Yundi, Wang Yixin, Li Li, Bai Hongshan

Corresponding Author

Zhang Yang

Abstract

With the development of distributed generation (DG), island detection is an important technology for distributed generation. This paper proposes the use of wavelet transform and BP neural network, combined with passive detection method for island detection. By extracting the voltage at the point of common coupling (PCC) and the current value output by the inverter, wavelet transform is used as the input of the BP neural network, and the occurrence of the island is determined by pattern recognition. The method can effectively improve the island detection speed and reduce the Non-detection zone (NDZ). In addition, since the method does not require the addition of a disturbance signal, it does not affect the power quality.

Keywords

Island detection; multi-inverter grid-connected; Wavelet transform; BP Neural Network; Pattern Recognition