Skip to main navigation Skip to search Skip to main content

Customer information system data pre-processing with feature selection techniques for non-technical losses prediction in an electricity market

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Non-technical losses (NTL) identification and prediction are important tasks for many utilities. Data from customer information system (CIS) can be used for NTL analysis. However, in order to accurately and efficiently perform NTL analysis, the original data from CIS need to be pre-processed before any detailed NTL analysis can be carried out. In this paper, we propose a feature selection based method for CIS data pre-processing in order to extract the most relevant information for further analysis such as clustering and classifications. By removing irrelevant and redundant features, feature selection is an essential step in data mining process in finding optimal subset of features to improve the quality of result by giving faster time processing, higher accuracy and simpler results with fewer features. Detailed feature selection analysis is presented in the paper. Both time-domain and load shape data are compared based on the accuracy, consistency and statistical dependencies between features. ©2006 IEEE.
Original languageEnglish
Title of host publication2006 International Conference on Power System Technology, POWERCON2006
PublisherIEEE
ISBN (Print)1424401119, 9781424401116
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 International Conference on Power System Technology, POWERCON2006 - Chongqing, China
Duration: 22 Oct 200626 Oct 2006

Publication series

Name2006 International Conference on Power System Technology, POWERCON2006

Conference

Conference2006 International Conference on Power System Technology, POWERCON2006
PlaceChina
CityChongqing
Period22/10/0626/10/06

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

  • Data mining
  • Feature selection
  • Load profiling
  • Non-technical loss (NTL) analysis

Fingerprint

Dive into the research topics of 'Customer information system data pre-processing with feature selection techniques for non-technical losses prediction in an electricity market'. Together they form a unique fingerprint.

Cite this