Wide Area Power System Protection Using a Learning Vector Quantization Network

Ganesh K. Venayagamoorthy, Missouri University of Science and Technology
Mahyar Zarghami

This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1331

There were 23 downloads as of 27 Jun 2016.


This paper presents a wide area monitoring and protection technique based on a learning vector quantization (LVQ) neural network. Phasor measurements of the power network buses are monitored continuously by a LVQ network in order to alert the control room operators of possible faults. The proposed scheme could be used in a wide area monitored network to provide remedial action when primary local protection schemes for transmission lines fail to function. This technique could also be extended to the actuation of the secondary protection schemes, hence, preserving the integrity of the power network especially when the faults are spreading over a wide area network to the other areas of the system. The scheme has been applied to a two-area power system in this paper and the LVQ results show that it is a promising scheme for system protection against partial or total blackouts or brown outs.