Islanding detection for inverter-based DG coupled with using an adaptive neuro-fuzzy inference system

This paper investigates a new integrated diagnostic system for islanding detection by means of a neuro-fuzzy approach for grid-connected inverter-based distributed generation. Islanding is one important concern for grid connected distributed resources due to personnel and equipment safety. Several methods based on passive and active detection scheme have been proposed. While passive schemes have a large non-detection zone (NDZ), concern has been raised on active method due to its degrading power quality effect. Reliably detecting this condition is regarded by many as an ongoing challenge as existing methods are not entirely satisfactory. The main emphasis of the proposed scheme is to reduce the NDZ to as close as possible and to keep the output power quality unchanged. In addition, this technique can also overcome the problem of setting the detection thresholds inherent in the existing techniques. In this study, we propose to use a hybrid intelligent system called ANFIS (the adaptive neuro fuzzy inference system) for islanding detection. The simulations results, carried out by MATLAB/Simulink, shows that the proposed method has a small non-detection zone. Also, this method is capable of detecting islanding accurately within the minimum standard time. Moreover, for those regions which are in need of a better visualization, the proposed approach would serve as an efficient aid such that the mains power disconnection can be better distinguished.

► Can detect islanding at nearly 0% active and reactive power imbalance.
► Reduce the non-detection zone to as close as possible and to keep the output power quality unchanged.
► Can also overcome the problem of setting the detection thresholds inherent in the existing techniques.