Computer Science ›› 2019, Vol. 46 ›› Issue (6A): 392-396.

• Big Data & Data Mining • Previous Articles     Next Articles

Fault Prediction of Power Metering Equipment Based on GBDT

LIU Jin-shuo1, LIU Bi-wei2, ZHANG Mi3, LIU Qing4   

  1. School of Cyber Science and Engineering,Wuhan University,Wuhan 430070,China1;
    School of Computer Science,Wuhan University,Wuhan 430070,China2;
    China Electric Power Research Institute,Beijing 100089,China3;
    Electric Power Science & Research Institute of Tianjin Electric Power Company,Tianjin 300041,China4
  • Online:2019-06-14 Published:2019-07-02

Abstract: The fault risk prediction of power metering equipment can reduce the loss caused by the fault risk of the national grid.Firstly,the data preprocessing and feature selection are carried out.Secondly,the GBDT-based fault categories,fault subclasses and equipment life cycle prediction are designed.Finally,the validity and advancement of the designed model are verified.Data used in the experiment are provided by China Electric Power Research Institute.The experimental results show that the prediction accuracy of the six fault types by using the proposed algorithm is 90.56%,the recall rate is 92.95%,and the F1 value is 91.71%.Compared with regression,BP neural network,Adaboost and decision tree algorithm,the gradient lifting decision tree algorithm has the best performance under parameter tuning conditions.

Key words: Data cleaning, GBDT, Measurement risk prediction

CLC Number: 

  • TP206+.3
[1]LIU J S.Analyzing Electricity Consumption via Date Mining .Journal of Wuhan University,2015,12(10):7-8.
[2]NIKOVSKI D N,WANG Z,ESENTHER A,et al.Smart meter data analysis for power theft detection∥Machine Learning and Data Mining in Pattern Recognition.Springer Berlin Heidelberg,2013.
[3]SAHOO S,NIKOVSKI D,MUSO T,et al.Electricity theft detection using smart meter data ∥IEEE Innovative Smart Grid Technologies Conference.2015:1-5.
[4]DEPURU S,et al.Support Vector Machine Based Data Classification for Detection of Electricity Theft .Power Systems Conference & Exposition,2011:1-8.
[5]ZAKARIA Z,LO K L.Two-stage fuzzy clustering approach for load profiling∥2009 Proceedings of the 44th International Universities Power Engineering Conference (UPEC).IEEE,2009.
[9]BIDOKI S,MAHMOUDI-KOHAN N,GERAMI S.Comparison of several clustering methods in the case of electrical load curves classification ∥IEEE Electrical Power Distribution Networks.2011:1-7.
[10]MONEDERO I,et al.Detection of Frauds and Other Non-technical Losses in A Power Utility Using Pearson Networks and Decision Trees .International Journal & Energy Systems,2012,34(1):90-98.
[1] CHEN Dan-hong, PENG Zhang-lin, WAN De-quan, YANG Shan-lin. Identification and Segmentation of User Value in Crowdsourcing Platforms:An Improved RFMModel [J]. Computer Science, 2022, 49(4): 37-42.
[2] WANG Jun, WANG Xiu-lai, PANG Wei, ZHAO Hong-fei. Research on Big Data Governance for Science and Technology Forecast [J]. Computer Science, 2021, 48(9): 36-42.
[3] LIU Zhen-peng, SU Nan, QIN Yi-wen, LU Jia-huan, LI Xiao-fei. FS-CRF:Outlier Detection Model Based on Feature Segmentation and Cascaded Random Forest [J]. Computer Science, 2020, 47(8): 185-188.
[4] XU He, WU Hao, LI Peng. Design of Temporal-spatial Data Processing Algorithm for IoT [J]. Computer Science, 2020, 47(11): 310-315.
[5] WANG Xiao-xia, SUN De-cai. Q-sample-based Local Similarity Join Parallel Algorithm [J]. Computer Science, 2019, 46(12): 38-44.
[6] SUN De-cai and WANG Xiao-xia. MapReduce Based Similarity Self-join Algorithm for Big Dataset [J]. Computer Science, 2017, 44(5): 20-25.
[7] GU Yun-hua, GAO Bao, ZHANG Jun-yong and DU Jie. RFID Data Cleaning Algorithm Based on Tag Velocity and Sliding Sub-window [J]. Computer Science, 2015, 42(1): 144-148.
[8] WANG Wan-liang,GU Xi-ren and ZHAO Yan-wei. RFID Uncertain Data Cleaning Algorithm Based on Dynamic Tags [J]. Computer Science, 2014, 41(Z6): 383-386.
[9] CHEN Jing-yun,ZHOU Liang and DING Qiu-lin. Cleaning Method Research of RFID Data Stream Based on Improved Kalman Filter [J]. Computer Science, 2014, 41(3): 202-204.
[10] . Data Cleaning and its General System Framework [J]. Computer Science, 2012, 39(Z11): 207-211.
[11] . Realization of Data Cleaning Based on Editing Rules and Master Data [J]. Computer Science, 2012, 39(Z11): 174-176.
[12] CAO Jian-jun,DIAO Xing-chun,WANG Ting,WANG Fang-xiao. Research on Domain-independent Data Cleaning: A Survey [J]. Computer Science, 2010, 37(5): 26-29.
[13] HU Yan-li,ZHANG Wei-ming. Theory of Conditional Functional Dependencies and its Application for Improving Data Quality [J]. Computer Science, 2009, 36(12): 115-118.
[14] HU Yan-li , ZHANG Wei-ming, LUO Xu-hui ,XIAO Wei-dong , TANG Da-quan. Dependencies Theory and its Application for Repairing Inconsistent Data [J]. Computer Science, 2009, 36(10): 11-15.
[15] . [J]. Computer Science, 2007, 34(3): 141-144.
Full text



No Suggested Reading articles found!