Time Granularity Transformation of Time Series Data for Failure Prediction of Overhead Line

2016 International Conference on Communication, Image and Signal Processing

物理学;无线电电子学;计算机科学

Ma, Yan^1 ; Zhu, Wenbing^1 ; Yao, Jinxia^1 ; Gu, Chao^1 ; Bai, Demeng^1 ; Wang, Kun^2

State Grid Shandong Electric Power Research Institute, Jinan

250002, China^1

Shandong Zhongshi Yitong Group Co. Ltd., Jinan

250002, China^2

关键词: Association analysis;    Big data platforms;    Failure prediction;    Logistic regression algorithms;    Meteorological data;    Prediction accuracy;    Short-term variations;    Time granularities;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/787/1/012031/pdf
DOI  :  10.1088/1742-6596/787/1/012031

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In this paper, we give an approach of transforming time series data with different time granularities into the same plane, which is the basis of further association analysis. We focus on the application of overhead line tripping. First all the relative state variables with line tripping are collected into our big data platform. We collect line account, line fault, lightning, power load and meteorological data. Second we respectively pre-process the five kinds of data to guarantee the integrality of data and simplicity of analysis. We use a representation way combining the aggregated representation and trend extraction methods, which considers both short term variation and long term trend of time sequence. Last we use extensive experiments to demonstrate that the proposed time granularity transformation approach not only lets multiple variables analysed on the same plane, but also has a high prediction accuracy and low running time no matter for SVM or logistic regression algorithm.