Detection and classification of DC and feeder faults in DC microgrid using new morphological operators with multi class AdaBoost algorithm

Abstract

DC microgrids with energy storage systems based on photovoltaic (PV) and wind energy are gaining popularity as a means to offer users with reliable supply in either a stand-alone or grid connected mode. However, because DC and AC side faults have similar current–voltage profiles, developing a viable safety strategy for the proposed integrated DC microgrid is difficult. Traditional protection techniques based on pre-defined thresholds are unable to discriminate between DC and AC side faults, and so fail to offer independent control actions in both circumstances. In this context, new morphological operators with improved AdaBoost algorithm is proposed for detecting and classifying the AC and DC side faults in the proposed DC microgrid. To explore this, current signals are captured at the DC bus of the proposed integrated DC microgrid. The captured signals comprise background noise which is eliminated by dilation erosion difference operator (DEDO) and opening closing difference (OCDO) operators. The two operators work together to meet the accurate fault detection to avoid nuisance tripping by multiscale operation of structuring element (SE). For effective outcomes the multiple scales are optimized by sparse kurtosis (SK) index. The optimized scales are passes through target features to retrieve the data. The acquired data is sent into the multi-class AdaBoost approach, which recognizes faults by modifying the distribution of data and iteratively adjusting the weight of each instance. The proposed system's efficacy is tested using the MATLAB/Simulink platform under various operating situations such as load variation, irradiation and fault resistance changes. The proposed algorithm's superiority is demonstrated by comparing it to existing approaches using confusion matrix (CM) parameters.