Feature selection for transient stability assessment based on kernelized fuzzy rough sets and memetic algorithm

TL;DR

This paper introduces a novel feature selection method combining kernelized fuzzy rough sets and a memetic algorithm to improve transient stability assessment in power systems, leveraging real-time wide-area measurement data.

Contribution

It proposes a new feature selection approach that avoids information loss and enhances search efficiency using KFRS and a hybrid memetic algorithm for power system stability analysis.

Findings

Validated on New England 39-bus system

Effective in selecting optimal features for stability assessment

Improved classification capability and search efficiency

Abstract

A new feature selection method based on kernelized fuzzy rough sets (KFRS) and the memetic algorithm (MA) is proposed for transient stability assessment of power systems. Considering the possible real-time information provided by wide-area measurement systems, a group of system-level classification features are extracted from the power system operation parameters to build the original feature set. By defining a KFRS-based generalized classification function as the separability criterion, the memetic algorithm based on binary differential evolution (BDE) and Tabu search (TS) is employed to obtain the optimal feature subsets with the maximized classification capability. The proposed method may avoid the information loss caused by the feature discretization process of the rough-set based attribute selection, and comprehensively utilize the advantages of BDE and TS to improve the solution quality and search efficiency. The effectiveness of the proposed method is validated by the application results on the New England 39-bus power system and the southern power system of Hebei province.