Abstract
Real-time transient stability assessment (TSA) of power systems based on mining system dynamic response has been widely considered by scholars. In this regard, extracting the most discriminative transient features (MDTFs) to achieve high-performance transient stability prediction (TSP) should be regarded as a fundamental issue in the transient learning strategy. In fact, MDTFs extraction is raised to make a trade-off between paradoxically intertwined indices, namely the accuracy and processing time of TSP. To this end, we offer a bi-mode hybrid feature selection scheme called BMHFSS for extracting MDTFs in high dimensional transient multivariate time series (TMTS). First, we used the TMTS, which are effective features on TSA. Next, the trajectory-based filter-wrapper mode (TFWM) is applied on TMTS to surmount the curse of dimensionality in two phases. In the filter phase, statistical and intrinsic characteristics of the TMTS in the form of agglomerative hierarchical clustering (AHC) are measured, and relevant TMTS (RTMTS) is selected according to obtained weight. In the wrapper phase, the RTMTS is entered into the trihedral kernel-based approach, including both fuzzy imperialist competitive algorithm (FICA) and incremental wrapper subset selection (IWSS) to find the intersected most RTMTS (IMRTMTS). As a complementary step, the filter-wrapper scenario in point-based mode (PFWM) is conducted for selecting MDTFs per time series in IMRTMTS. Finally, the aggregated MDTFs (AMDTFs) are tested to verify their efficacy for TSP based on cross-validation. The results show that the proposed framework has prediction accuracy greater than 98 % and a processing time of 52.94 milliseconds for TSA.
Highlights
The public vital utilities like water, telecom, natural gas, transportation, and oil reached conjunction with electric power
We consider three efficient kernels plugged into Support vector machine (SVM) to feed the FICAIWSS for selecting MRTMTS as follows: (a) Standard Gaussian radial basis function (GRBF) [20]: GRBF kernel as K ( x, x ) in (15) is defined as (18): Tip: all values depicted in this figure is numerical examples and are not real results
Called relevant transient multivariate time series (TMTS) (RTMTS), RTMTS entered to wrapper phase, including both fuzzy imperialist competitive algorithm (FICA) and incremental wrapper subset selection (IWSS) in the form of the trihedral kernel-based approach to find the intersected most RTMTS (IMRTMTS)
Summary
The public vital utilities like water, telecom, natural gas, transportation, and oil reached conjunction with electric power. Making the literature review on the FSP-based TSA studies shows this fact that the FSS applied by scholars on transient space including two approaches: 1) information theory/filter-based approach; for example, in Reference [4], the extended Relief-based feature selection algorithm called ReliefF finds the most sensitive features via relevance index for monitoring rotor fault on induction motors. Regardless of proposed well-suited solutions against the FSP in high dimensional transient space; in this paper, designing an inclusive FSS scheme is on the agenda regarding the following two aspects: a) In previous studies on FSP-based TSA, selecting optimal features is triggered via point-based data type characteristic of dynamic responses. In other words, selecting the best-laid feature set is the necessary concern to achieve high-performance (time and accuracy) on TSP This challenge can be solved via conducting the FSS process in the form of a bi-mode scenario.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
