Open AccessEvaluating weather influences on transmission line failure rate based on scarce fault records via a bi‐layer clustering technique
Author(s) -
Wang Yue,
Chen Lu,
Yao Meng,
Li Xinyu
Publication year - 2019
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.2019.0551
Subject(s) - cluster analysis , reliability (semiconductor) , failure rate , electric power transmission , fault (geology) , scarcity , computer science , reliability engineering , covariate , function (biology) , transmission line , econometrics , data mining , power (physics) , engineering , artificial intelligence , machine learning , mathematics , economics , telecommunications , physics , electrical engineering , quantum mechanics , seismology , evolutionary biology , biology , microeconomics , geology
In a common practice of power system reliability management, scarcity of malfunction information leads to incomplete knowledge of the failure reasons, and thus results in ambiguous failure rate models for the time being. This study proposes a methodology of quantifying weather influence on transmission line failure rate in terms of the effects of unexplained factors originating from a scarcity of weather‐fault‐correlating information. A model to quantify the referred weather influence is derived from a conceptual full failure rate model and parameterised by an exponential function. The concerned unknown parameters, besides some recourse covariates introduced to account for absent information on unexplained factors, are together trained by means of the maximum likelihood estimation based on available weather‐fault‐correlating information about both normal and failure‐causing weather conditions for pooled transmission lines. Theoretical foundation and numerical results are given for illustrating a relationship between the proposed model and traditional weather‐dependent failure rate models. Applications are also demonstrated in virtue of practical data from the Xinjiang Autonomous Region of China.