Machine Learning Based Adaptive Fault Diagnosis considering Hosting Capacity Amendment in Active Distribution Network

Augmentation of distributed energy resources (DERs) safely in the distribution system termed as hosting capacity (HC) is one of the prominent needs to achieve energy sufficiency with minimum emission. However, any amendment in HC over premeditated injection sets up challenges in the perspective of situational awareness (SA) of networks for precise decision-making related to fault prediction and location. In this work, the author(s) propose histogram-based gradient boost (HGB) algorithm, an accurate machine learning (ML) technique for fault type detection and localization. Due to the unique characteristic of noise cancelation, spectral-kurtosis is utilized for the extraction of features of the faulted transient signals. For improvement of competence of the process, optimized feature importance values are considered. In order to study the efficacy of the proposed method, HC of the network is altered, leading to the up- gradation of network parameters. These upgraded parameters are used for retraining the proposed ML algorithm for desired SA, leading to updated perception, comprehension, projection, and accurate decision making. The entire analysis is tested on reconfigured IEEE-33 bus distribution system developed in Typhoon HIL real-time simulator. The proposed methodology is also compared with existing literature to platform its excellence.