Open AccessSurrogate‐splits ensembles for real‐time voltage stability assessment in the presence of missing synchrophasor measurements
Author(s) -
Adewole Adeyemi Charles,
Tzoneva Raynitchka
Publication year - 2017
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2016.0431
Subject(s) - phasor measurement unit , boosting (machine learning) , electric power system , phasor , units of measurement , artificial intelligence , classifier (uml) , margin (machine learning) , missing data , computer science , ensemble learning , voltage , machine learning , stability (learning theory) , data mining , pattern recognition (psychology) , engineering , power (physics) , physics , quantum mechanics , electrical engineering
This paper proposes a new machine learning approach in the presence of missing measurements using surrogate‐splits ensembles for real‐time voltage stability assessment comprising of the classification of the operating state of the power system, and the prediction of the power system's margin to voltage collapse. The proposed approach applied the Boosting and Bagging machine learning methods in the design of the ensemble models required for the classification and regression tasks, respectively, based on the feature attributes obtained from synchrophasor measurements. The performance of the trained classifiers and regressors was evaluated for the case of missing phasor measurement unit (PMU) measurements. Robust classifier and regressor models immune to missing PMU measurements were afterwards developed using the surrogate‐splits technique. The validity of the proposed approach was tested using the New England 39‐bus test system. The experimental results obtained validate the effectiveness of the proposed method for various operating scenarios and contingencies even in the presence of missing PMU measurements.