Skip to main navigation Skip to search Skip to main content

A semi-supervised anomaly detection method for wind farm power data preprocessing

  • Yifan Zhou
  • , Wei Hu
  • , Yong Min
  • , Le Zheng
  • , Baisi Liu
  • , Rui Yu
  • , Yu Dong
  • Tsinghua University
  • State Grid Corporation of China

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Scopus citations

Abstract

Wind farm power data is an essential data source for characteristics analysis of wind farms, and its precision highly influences the operation and control of wind power. Existing methods for abnormal wind power data detection are mainly based on supervised or unsupervised algorithms, which may suffer from huge effort consumption on artificial label-setting or improvable detection precision respectively. In this paper, a semi-supervised anomaly detection method based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is proposed. Supervision from a limited number of labelled data is utilized to guide the anomaly detection process. Simulation based on realistic wind farm power data from China is performed to verify the method validity. The simulation results illustrate that the proposed method can obtain a satisfactory performance on avoiding false dismissals and false alarms among irregular-shaped wind power clusters, as well as an improved distinguishing ability around the confusing boundaries between normal and abnormal data.

Original languageEnglish
Title of host publication2017 IEEE Power and Energy Society General Meeting, PESGM 2017
PublisherIEEE Computer Society
Pages1-5
Number of pages5
ISBN (Electronic)9781538622124
DOIs
StatePublished - Jan 29 2018
Event2017 IEEE Power and Energy Society General Meeting, PESGM 2017 - Chicago, United States
Duration: Jul 16 2017Jul 20 2017

Publication series

NameIEEE Power and Energy Society General Meeting
Volume2018-January
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Conference

Conference2017 IEEE Power and Energy Society General Meeting, PESGM 2017
Country/TerritoryUnited States
CityChicago
Period07/16/1707/20/17

Keywords

  • Anomaly detection
  • Data mining
  • Density-Based Spatial Clustering of Applications with Noise (DBSCAN)
  • Semi-supervised learning
  • Wind farm power data preprocessing

Fingerprint

Dive into the research topics of 'A semi-supervised anomaly detection method for wind farm power data preprocessing'. Together they form a unique fingerprint.

Cite this