Surviving Most Relevant Features on Transient Trajectories Data by Dyadic 24-Way Hybrid Feature Selection Algorithm for Transient Stability Prediction

Abstract

Designing an effective feature selection scheme (FSS) is an inevitable solution for top-level balancing contrastive-correlated indices, namely transient processing time (TPT) and transient prediction accuracy (TPA) on transient stability assessment (TSA). Achieving low TPT and high TPA have a tight relationship in selecting the most relevant transient point features (MRTPFs) survived by applying comprehensive FSS on $m$ -variate transient trajectory features ( $m$ VTTFs). Hence, we introduce dyadic 24-way hybrid FSS (D24WHFSS) to select MRTPFs from $m$ VTTFs. The D24WHFSS comprises 24 permutations of the chained four-stage hybrid structure called 24-way hybrid FSS (24WHFSS). The 24WHFSS raised by bi-incremental wrapper mechanism (bi-IWM) contains incremental wrapper subset selection (IWSS) and IWSS with replacement (IWSSr). Each hybrid scenario is equipped with symmetric uncertainty (SU) (filter phase) and dual support vector-based classifiers (DSVCs) (wrapper phase). Embedded DSVCs into IWSS/ IWSSr include kernel support vector machine ( $k$ SVM) and $k$ -twin SVM ( $k$ TWSVM). By plugging dual kernel function pairs (DKFPs) into DSVCs, 24-way $^{\mathrm {SU}}$ bi-IWM $^{\mathrm {DSVCs}}$ is exerted in the varied twofold repetition (dyadic 24WHFSS). In the first KFP (KFP1), the radial basis function (RBF) is situated in the DSVCs of bi-IWM. In KFP2, the dynamic time warping (DTW) and polynomial (Poly) kernels are used in 24-way $^{\mathrm {SU}}$ bi-IWM $^{\mathrm {DSVCs}}$ that the DTW and Poly kernels plugged into $^{\mathrm {SU}}$ IWSS $^{k\mathrm {SVM}}/^{\mathrm {SU}}$ IWSSr $^{k\mathrm {SVM}}$ and $^{\mathrm {SU}}$ IWSS $^{k\mathrm {TWSVM}}/^{\mathrm {SU}}$ IWSSr $^{k\mathrm {TWSVM}}$ , respectively. Finally, the efficacy of D24WHFSS-based MRTPFs in TSA is evaluated via cross-validation. The results show that D24WHFSS has a TPA of 99.25 % and a TPT of 102.607 milliseconds for TSA.

Keywords

• Hybrid feature selection scheme
• most relevant transient point features
• transient stability assessment