mlp based islanding detection using histogram analysis for wind turbine distributed generation

due to increase distributed generations, islanding is an important concern for these resources. personnel and equipment safety issues are main reasons to detection of islanding. several techniques based on passive and active detection schemes have been proposed previously. although passive schemes have a large non-detection zone (ndz), concerns have been raised about active methods because of their degrading effect on power quality. reliably detecting this condition is regarded by many as an ongoing challenge because existing methods are not entirely satisfactory. this paper proposes a histogram analysis method using a multi layer perceptron (mlp) neural network approach for islanding detection in grid-connected wind turbines. the main objective of the proposed approach is to reduce the ndz and to maintain the output power quality unchanged. in addition, this technique can also overcome the problem of setting detection thresholds which is inherent in existing techniques. the method proposed in this study has a small non-detection zone and is capable of detecting islanding accurately within the minimum standard time. moreover, for those regions which require better visualization, the proposed approach can serve as an efficient aid for better detecting grid-power disconnection.