DocumentCode :
3349353
Title :
A Novel Approach for Wind Speed Forecasting Based on EMD and Time-Series Analysis
Author :
Xing-Jie Liu ; Zeng-Qiang Mi ; Bai Lu ; Wu Tao
Author_Institution :
Dept. of Electr. Eng., North China Electr. Power Univ., Baoding
fYear :
2009
fDate :
27-31 March 2009
Firstpage :
1
Lastpage :
4
Abstract :
Wind speed forecasting is significant to the security and stability of electric power system. Aiming to forecast wind speed more efficiently, a hybrid forecasting method based on empirical mode decomposition(EMD) and time-series analysis has been presented in this paper. Employing the EMD technique to decompose the original data into a residue and many intrinsic mode function(IMF) components, which represent the oscillation modes embedded in the data. Afterwards each IMF is modeled and forecasted using time-series analysis, so does the residue. The forecasting value for each decomposed component is summarized as that for the original data. A set of wind speed data from a given wind farm were modeled using the proposed method and the forecasted data were compared to those of measured wind speed as well as those calculated with other conventional methods. The results obtained indicate that the building model is simple and the forecasting precision has been greatly improved using the proposed method.
Keywords :
power generation reliability; time series; weather forecasting; wind power; empirical mode decomposition; intrinsic mode function; power generation reliability; time-series analysis; wind farms; wind speed forecasting; Hybrid power systems; Load forecasting; Power system reliability; Power system security; Power system stability; Predictive models; Time series analysis; Wind energy; Wind forecasting; Wind speed;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power and Energy Engineering Conference, 2009. APPEEC 2009. Asia-Pacific
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-2486-3
Electronic_ISBN :
978-1-4244-2487-0
Type :
conf
DOI :
10.1109/APPEEC.2009.4918088
Filename :
4918088
Link To Document :
بازگشت