In this paper, decision tree (DT)-based preventive and corrective control methods are proposed to enhance the dynamic security of power systems against the credible contingencies causing transient instabilities. Preventive and corrective controls such as generation rescheduling and load shedding schemes, respectively, are developed based on the security regions and boundaries that are calculated in the space of appropriate decision variables. The security regions and boundaries are determined by the rules of DTs that are developed by the generated knowledge bases. This work also involves improving the accuracy of security boundaries as well as the optimal solutions for the fuel cost and load shedding optimization problems encountered in the preventive and corrective controls. The methods are implemented on the Entergy power system model.Index Terms-Corrective control, dynamic security assessment, preventive control.
Detailed security analysis for contingencies ( = 1 2 3 . . .) in a real-time setting is still a great challenge due to the significant computational burden. This paper takes advantage of phasor measurement units (PMUs) and decision trees (DTs) to develop a real-time security assessment tool to assess four important post-contingency security issues, including voltage magnitude violation (VMV), thermal limit violation (TV), voltage stability (VS) and transient stability (TS). The proposed scheme is tested on the Salt River Project (SRP) power system represented by a series of operating conditions (OCs) during a representative day. The properly trained DTs demonstrate excellent prediction performance. Robustness tests for the offline trained DTs are performed on a group of changed OCs that were not included for training the DTs and the idea of tuning critical system attributes for preventive controls is also presented to improve system security.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.