Binary cat swarm optimization versus binary particle swarm optimization for transformer health index determination

In this research, we present a discrete version of cat swarm optimization that is used to build an optimization model based on support vector machines (SVM). This model is undertaken to select the best transformer tests that can be utilized to classify transformer health index into three categories; thus, improving the reliability of identifying the transformer condition within the power system. The performance of the binary cat swarm optimization is compared to binary particle swarm optimization technique, and results show that the binary cat swarm optimization based SVM model is capable of obtaining an improved and reliable classification results with a reduced number of transformer tests utilized as inputs.