Multi-Goal Feature Selection Function in Binary Particle Swarm Optimization for Power System Stability Classification

Abstract

The input feature is vital for power system stability classification. Feature selection can reduce the size of the input feature, making classifier training easier, and the small size of the input feature subset also reduces the cost of purchasing sensor measurement equipment. Therefore, feature selection works require an efficient seeking method. Binary Particle Swarm Optimization (BPSO) is a simple and easy-to-implement evolutionary calculation technique. While the classification accuracy of BPSO is essential, it is also needed to drive the algorithm to minimize the number of variables. The proposed approach is to apply a multi-objective function to help the BPSO algorithm identify the subset of features that can achieve the minimum number of variables and the highest classification accuracy. The k-nearest neighbor classifier is employed in the experiments to evaluate the classification performance on the IEEE 39-bus dataset.