Application of Support Vector Machine Classification to Enhanced Protection Relay Logic in Electric Power Grids

S the power systems in the United States become increasingly large, complex, and interconnected, the traditional relays are proving to be inadequate during conditions prior and during the blackouts. Smart relays, which are more intelligent, are therefore needed to meet the security and reliability needs of the future power grid. The goal of classification of smart relays is to build a model which can discriminate the normal conditions from the fault conditions based on the measurements which can be obtained locally. In this paper we propose a decision algorithm based on applying support vector machine (SVM) classification in protection relays. Our proposed method is both efficient and provably scalable.