Multiclass- SVM Relay for Microgrid Protection

Our approach to microgrid protection in this paper uses a classification approach using multi-class Support Vector Machine (SVM) for improving the accuracy in relay coordination. Without the need for using any extensive communication facility, the proposed approach utilizes  local information to identify the corresponding SVM class to coordinate the relays to maintain the Coordination Time Interval (CTI) within the desired limits. The SVM relay has been implemented on 200-MHz TMS320F28377S, 32-bit floating point microcontroller and tested on a 4-bus distribution system. A prototype of the proposed relay has been tested on a 400V 4-Bus laboratory type microgrid system by creating different types of faults. The results obtained show that the proposed relay outperforms conventional relaying schemes reported in the literature.

References:

Vinod V and U J Shenoy, “An adaptive relay based on curve fitting technique for micro-grid protection,” IEEE International conference on Power Electronics, Smart Grid and Renewable Energy (PESGRE 2020), January 2-4, 2020 , Cochin, India.

Vinod V and U J Shenoy, “Implementation of Support Vector Machine Based Relay Coordination Scheme for Distribution System with Renewables,” IEEE Journal of Emerging and Selected Topics in Industrial Electronics, April 2021, DOI: 10.1109/JESTIE.2020.3014875.