A SVM based Fault Detection and Section Identification scheme for a Hybrid AC/HVDC Transmission Line with Wind Farm Integration

Abstract

This paper proposes a support vector machine (SVM) based protection algorithm for a hybrid AC-HVDC transmission line integrated with a wind farm. The proposed scheme is able to detect faults in AC as well as the HVDC line. This scheme initiates with the acquisition of time-domain current and voltage signals at the relaying point. Further Discrete Fourier Transform is utilized for estimation of the fundamental component of current and voltage signals which are then fed as input to the SVM based fault detector and classifier. A total of three SVM classifier modules have been developed, for performing the tasks of fault detection, identification of fault phase(s) and faulty section. The Proposed scheme has been tested for various DC faults and AC faults. Simulation results ensure that the proposed scheme is efficient in accurately detecting the AC and DC faults.