A Classification Approach Using Support Vector Machines to Prevent Distance Relay Maloperation Under Power Swing and Voltage Instability

Distance relays, in the power transmission systems, are susceptible to the maloperation under certain system events, such as power swings and voltage instability, which drive the apparent impedance trajectories into the protection zones of the relay. Fast and reliable detection of the symmetrical faults, occurring during power swings, poses another challenge to operation of the distance relays. This paper introduces a new classification and protection scheme based on support vector machines (SVMs) for offering supervisory control to the operation of the conventional distance relays. The proposed scheme segregates the power system events into faults, power swings, and voltage instability. This paper also proposes a new index, called the relay ranking index, for identifying the relays most vulnerable to the maloperation due to power swings and voltage instability. The proposed SVM classifiers can work in unison with the conventional distance relay unit. The performance of the proposed scheme has been tested on a nine-bus WSCC system and 39-bus New England system.