Open AccessEarly warning method for transmission line galloping based on SVM and AdaBoost bi‐level classifiers
Author(s) -
Wang Jian,
Xiong Xiaofu,
Zhou Ning,
Li Zhe,
Wang Wei
Publication year - 2016
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2016.0140
Subject(s) - support vector machine , warning system , adaboost , electric power transmission , transmission line , classifier (uml) , computer science , artificial intelligence , engineering , machine learning , simulation , telecommunications , electrical engineering
Transmission line galloping often causes structural and electrical failures, which is a serious threat to the security of transmission systems. Through analysing the influence factors of galloping, it reveals that weather conditions are the most significant excitation factors and conductors of any voltage level and region may gallop when the apt‐galloping weather conditions are satisfied. This study proposes an early warning method for transmission line galloping based on support vector machine (SVM) and AdaBoost bi‐level classifiers. First, a prediction model of apt‐galloping weather conditions based on an SVM classifier is built through data mining of historical weather parameters in regions where galloping frequently occurred. When the forecast weather conditions of a particular region satisfy the apt‐galloping weather conditions, the conductor type, cross‐section and span of transmission line are further considered to realise early warning of galloping through an AdaBoost classifier. Finally, the historical galloping events of a power grid are adopted to verify the validity of the proposed methods. The test results indicate that both the accurate classification rate and accurate warning rate are above 90%, whereas the missed warning rate is below 10%. The models are suitable for early warning of transmission line galloping and can provide important decision support for operation staff of power grid.