Short-Term Output Forecasting Model of Photovoltaic Electric Field Based on Wavelet Transform

Bo Chen; Yuan Li

doi:10.4028/www.scientific.net/AMM.734.781

Paper Titles

Fuzzy PID Control Strategy in the Application of the MPPT
p.755

Hybrid System for Photovoltaic Power Generation and Power Quality Control
p.759

Maximum Power Point Tracking for the Micro-Scale Photovoltaic Power System
p.771

Research on Peak Capacity of Distributed Photovoltaic Generation Based on Voltage Deviation Model in Distribution Network
p.775

Short-Term Output Forecasting Model of Photovoltaic Electric Field Based on Wavelet Transform
p.781

Improvement of the Load Process of Pb Batteries Connected to a Photovoltaic System
p.787

Properties of Sputtered-n-nc-Si:Er/p-Si Heterojunction Solar Cells
p.791

Obtainable P-Type ZnO Film Doped with Li by Sol-Gel Method
p.796

A Hybrid Damping Method for LCL-Filter Based Grid-Tied Inverter
p.805

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 734Short-Term Output Forecasting Model of...

Short-Term Output Forecasting Model of Photovoltaic Electric Field Based on Wavelet Transform

Abstract:

As the meteorological parameter of numeric weather forecast model has systematic error, which leads to the restriction of forecast precision for photovoltaic electric field, the paper put forward a short-term output forecasting model of photovoltaic electric field based on wavelet transform. Wavelet transform algorithm that using 4 series of sym6 wavelet decomposition conducts a dynamic correction to the wind speed data outputted by numerical weather forecasting. Through combining other meteorological data, it formed a new amended meteorological data collection used to forecast the photovoltaic power; according to the two training set of both the original and the amended meteorological data, two prediction model based on original and amended neural network outputted by photovoltaic plant power are established. By comparing the measured data and model analysis data within a same period, it shows that the amended model can significantly reduce the RMSE of predict results and decrease the error from 70.66% to 70.66%, and increase the relative accuracy from 70.66% to 70.66%.

You might also be interested in these eBooks

Electronics, Automation and Engineering of Power Systems

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 734)

Pages:

781-786

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.734.781

Citation:

Cite this paper

Online since:

February 2015

Authors:

Bo Chen*, Yuan Li

Keywords:

Neural Network, Photovoltaic Array Output, Wavelet Transform (WT)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] F. J. L. Alfredo, M. J. Andrés1 and F. Alberto1: Renew. Energy Vol. 44 (2012), pp.311-317.

Google Scholar

[2] Shi, Jie, Lee, Wei-Jen, Liu, Yongqian: IEEE Trans Ind Appl Vol. 48 (2012), pp.1064-1069.

Google Scholar

[3] F. Laurentiu, B. Blanka, G. M. Andrei: J. Renewable Sustainable Energy Vol. 5 (2013).

Google Scholar

[4] Chang, Wen-Yeau: Appl. Mech. Mater. Vol. 479-480 (2014), pp.585-589.

Google Scholar

[5] C. Marco1, D. A. Eleonora, L. Beatrice1: Intelligent Decis. Technol Vol. 6 (2012), pp.197-210.

Google Scholar

[6] D.G. Maria Grazia, C. Paolo Maria, M. Maria: IET Sci. Meas. Technol. Vol. 8 (2014), pp.90-97.

Google Scholar

[7] N. Dongxiao, J. Ling, X. Xiaomin, W. Peng: Sensors Transducers Vol. 159 (2013), pp.138-142.

Google Scholar

[8] C. Changsong, D. Shanxu, Y. Jinjun: Diangong Jishu Xuebao Vol. 24 (2009), pp.153-158.

Google Scholar

[9] O. Nevzat1, K. Ismail, G. Gökhan: WSEAS Trans. Circuits Syst. Vol. 8 (2009), pp.719-728.

Google Scholar

[10] Z. Songlin, M. Meiqin, S. Jianhui: Taiyangneng Xuebao Vol. 33 (2012), pp.452-456.

Google Scholar