Assessment of an adaptive neuro fuzzy inference system for islanding detection in distributed generation

This paper proposes a new integrated diagnostic system for islanding detection by means of an adaptive neuro-fuzzy inference system (ANFIS). Islanding detection and prevention are mandatory requirements for grid connected distributed generation (DG) systems. Several methods based on passive and active detection scheme have been proposed. While passive schemes have a large non detection zone (NDZ), the concern has been raised on active method due to their 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. This approach utilizes different parameters such as rate of change of frequency and rate of change of power and uses them as the input sets for training a neuro-fuzzy inference system for intelligent islanding detection. To validate the feasibility of this approach the method has been validated through several conditions and different loading, switching operation and network conditions. Simulation studies show that the ANFIS-based algorithm detects islanding situation more accurately than other algorithms and found to work effectively in the situations where other methods fail. Moreover, for those regions which are in need of a better visualization, the proposed approach would serve as an efficient aid such that the main power disconnection can be better distinguished.