Research on Recognition and Correction of Power System Load Singular Data Based on Wavelet Analysis

DOI

10.2991/emcs-17.2017.420How to use a DOI?

Keywords

Singular data; Wavelet analysis; Singularity detection; Load forecasting; Power system

Abstract

Traditional singular data identification and correction methods process data roughly and cannot accurately deal with the shortcomings of singular data, this paper proposes a singular data identification and correction method based on wavelet analysis, which uses the localization properties of wavelet analysis in terms of time domain and frequency domain with the "micro" features of signals. First of all, wavelet analysis is conducted to extract the high frequency component signal as well as characterization of random noise, combined with probability statistical method to analyze the high frequency component signals, determine the occurrence time of singular data and finally eliminate singular data. The linear interpolation method is used to supplement the correction. A large number of examples show that the method is correct and effective.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Chao Hong
AU  - Xiangshu Ye
PY  - 2017/03
DA  - 2017/03
TI  - Research on Recognition and Correction of Power System Load Singular Data Based on Wavelet Analysis
BT  - Proceedings of the 2017 7th International Conference on Education, Management, Computer and Society (EMCS 2017)
PB  - Atlantis Press
SP  - 2229
EP  - 2234
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcs-17.2017.420
DO  - 10.2991/emcs-17.2017.420
ID  - Hong2017/03
ER  -