Абстрактный

Online Dynamic Assessment

Subashini.A, Aishwarya.M, Bhuvenswari.R, Manjuparkavi.R

A data mining approach using ensemble decisiontrees (DTs) learning is proposed for online dynamic security assessment (DSA), with the objective of mitigating the impactof possibly missing PMU data. Specifically, multiple small DTsare first trained offline using a random subspace method. Inparticular, the developed random subspace method exploits thehierarchy of wide-area monitoring system (WAMS), the locationalinformation of attributes, and the availability of PMU measurements,so as to improve the overall robustness of the ensemble to missing data. Then, the performance of the trained small DTs isre-checked by using new cases in near real-time. In online DSA,viable small DTs are identified in case of missing PMU data, anda boosting algorithm is employed to quantify the voting weightsof viable small DTs. The security classification decision for onlineDSA is obtained via a weighted voting of viable small DTs. A casestudy using the IEEE 39-bus system demonstrates the effectiveness of the proposed approach.