Detection And Classification Of Disturbances In A Renewable Energy Integrated Power System

Abstract

Detection and classification of disturbances such as faults and power quality issues in transmission lines and distribution systems are among the important aspects of power system protection for which different methodologies are suggested by various researchers. However, the aforementioned problems are made more difficult by deregulation, the increasing penetration of renewable energy sources in the power grid and the complexity of the smart grid. Therefore, the development of an intelligent disturbances diagnosis and surveillance system that is accomplish of detecting and classifying various kinds of faults and power quality disturbances is driven by the interests of power engineers and researchers. This work devoted to introduce methods to be utilize for detection and classification of fault and power quality disturbances specific to renewable energy integrated power system. A comprehensive assessment of various approaches is presented, with a critical analysis of their shortcomings. The present study intends to make any necessary improvements to the aforementioned issues while using all research findings from the literature as a footnote and source of motivation. The major focus of the entire work is efficient, quick and precise detection and classification of various kinds of faults and power quality disturbances in the system. The voltage and current signals in real-time systems carry all the information necessary for operation, therefore it is quite challenging to input the raw signals into a set of rules and criteria that can interpret the underlying messages they carry. newlineAdvanced signal processing and feature extraction approaches are proposed for fault detection and classification in this work. The voltage and current signals are sampled in the first stage and then processed using the proposed methodologies. The characteristics employed by the fault detector and classifier respectively, are then extracted in the following phase. This is the principal mechanism used for detecting and classifying the disturbances in the sy