A Wind Power Forecasting Method Based on Improved Support Vector Machine

Hong Chang Ke; Hui Wang; De Gang Kong

doi:10.4028/www.scientific.net/AMM.556-562.1964

Paper Titles

Study on the Specific Harmonic Suppression of Active Power Filter
p.1945

Speeding up Based on the Process Optimization of High Voltage Business Expanding
p.1950

Analysis of Theory and Model of Background Magnetic Field of High-Spinning Projectile
p.1954

Design and Simulation of Breaking Time Sequence for DC Circuit Breaker with a Current-Limiting Inductance
p.1959

A Wind Power Forecasting Method Based on Improved Support Vector Machine
p.1964

Heat Transfer Enhancement by Ultrasound Pressure Waves in Liquid Water: A Cooling Method for New Electronic Components
p.1968

Design of Program about the LED Digital Clock Based on Atmega16 Microcontroller and DS1302
p.1975

The Design and Implementation of Zero-Angle Memory Device about the Radar of Ship-Borne Based on Proximity Switch
p.1979

Development of the Mobile Power Supply System with Stabilizing Voltage and Frequency, UPS, Intelligent Charging
p.1983

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 556-562A Wind Power Forecasting Method Based on Improved...

A Wind Power Forecasting Method Based on Improved Support Vector Machine

Abstract:

For the deficiencies of traditional wind forecasting method, a wind forecasting method based on improved support vector machine which support any parameters input. The method can compatible with many different types and magnitude data and construct a loop iteration mechanism, based on the wind farm's own situation which constantly prompts to enter the wind speed, season, temperature, humidity, light until it reaches the desired accuracy. For wind power consumptive capacity, the method proposed can obtain the maximum, minimum wind parameters and the range of variation, diverse support vector machine regression model can be produced by learning, which can predict the future of wind energy within a period of time. The method can improve the quality of wind power and grid scheduling, for maintaining grid stability has a very important role.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 556-562)

Pages:

1964-1967

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.556-562.1964

Citation:

Cite this paper

Online since:

May 2014

Authors:

Hong Chang Ke*, Hui Wang, De Gang Kong

Keywords:

Support Vector Machine (SVM), Wind Forecasting, Wind Power Consumptive

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Y. Zhang, X. F. Liu, Q. Li. Water Conservancy & Electric Power Machinery, 2007, 5: 72-75.

Google Scholar

[2] Y. Z. Lei, W. S. Wang, Y. H. Yin, H. Z. Dai. Power System Technology, 2002, 26(5): 10-14.

Google Scholar

[3] L. Mark, Ahlstrom, M. Robert, Zavadil. Transmission and Distribution Conference & Exhibition, 2005, 5: 1-5.

Google Scholar

[4] C. W. Potter, N. Michael. Very Short Term Wind Forecasting for Tasmanian Power Generation, IEEE TRANSACTIONS ON POWER SYSTEMS, 2006, 21(2): 965-972.

DOI: 10.1109/tpwrs.2006.873421

Google Scholar

[5] M. Alexiadis, P. Dokopoulos, H. Sahsamanoglou. Solar Energy, 1998, 63(1): 61-68.

DOI: 10.1016/s0038-092x(98)00032-2

Google Scholar

[6] Y. Zhang, Z. W. Gao. The load forecasting of electric energy based on time sequence and neural network[J]. Journal Harbin Univ. Sci. & Tech, 2003, 8 (1): 30-36.

Google Scholar

[7] R. Karki, P. Hu, R. Billinton. A Simplified Wind Power Generation Model for Reliability Evaluation, IEEE Transactions on Energy Conversion, 2006, 21(2): 533-540.

DOI: 10.1109/tec.2006.874233

Google Scholar