Open Collections

Application of wavelet transform to electricity price forecasting

University of British Columbia

In order to improve the overall efficiency of electric power industry, since 1990's, deregulation of power industry has been implemented around the world by introducing competitions in generation, wholesale and retail sectors. The process of determining electricity price of electricity market is closely coupled with the process of power system operation and this results in an extremely volatile electricity price. This volatile electricity price not only brings unprecedented risk to customers but also brings more uncertainties and difficulties to power system operation, as electricity price also affects the behavior of generation, transmission and demand sections in electricity market. Therefore, modeling and forecasting electricity price is a very important topic. Aiming at developing a simple, affordable and accurate electricity price forecasting model for electricity consumers, this thesis studies the mechanism of electricity price behavior, explores the feasibility of applying wavelet transform to electricity forecasting, and tries to improve the performance of short-term (one day ahead) electricity price forecasting. The difficulty of forecasting electricity price includes price spikes and random changes. In this research, we have tried to solve this difficulty with wavelet transform and our simulation results show that wavelet transform is able to handle the spikes and random changes in electricity price and substantially improve the performance of electricity forecasting.

Text

2009-12-23

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/17080

Electrical and Computer Engineering

University of British Columbia

UBCV

DSpace