Research on Forecast of Ultra-short-term Load under the Influence of Electric Railway

DOI

10.2991/icetis-13.2013.18How to use a DOI?

Keywords

ultrashort-term load forecast; wavelet theory; scaling function; support vector machine

Abstract

Railway is an important infrastructure of the state, national main artery and popular means of transport .With the gradually maturity of high-speed railway technology of China, the proportion of load of electric railway in the national power consumption load. As the electric railway load is characterized by high variation frequency, large fluctuation and poor periodicity, it causes a great influence on the forecast of local load. To solve this problem, this paper proposes a method of first treating the data by scale through wavelet analysis and then selecting partially similar day to forecast various loads in different frequencies with more load forecast models and improves wavelet svm forecast method to make the approximation under single scale in the past proceed in more scales and improve the partial approximation ability of this method. This method is used to forecast the ultrashort-term load of power system, the experiment result shows that the load forecast result precision of this method reaches above 97%, effectively improving the forecast prevision of load under the influence of interference factors.

Copyright

© 2013, 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  - Ruifeng An
AU  - Jiming Du
PY  - 2013/06
DA  - 2013/06
TI  - Research on Forecast of Ultra-short-term Load under the Influence of Electric Railway
BT  - Proceedings of the 2013 the International Conference on Education Technology and Information System (ICETIS 2013)
PB  - Atlantis Press
SP  - 74
EP  - 80
SN  - 1951-6851
UR  - https://doi.org/10.2991/icetis-13.2013.18
DO  - 10.2991/icetis-13.2013.18
ID  - An2013/06
ER  -