Wavelet ANN Based Monthly Runoff Forecast

Abstract:

A wavelet artificial neural network to forecasting monthly runoff is proposed. The monthly runoff series is firstly decomposed to sub-series on different time scales, and each sub-series is modeled. The weights of the network are replaced by wavelet functions and are corrected by conjugate gradient method in the training iteration. Then the proposed network is trained with 49 years (1952-2000) actual data of one hydro power plant of Jiangxi province and is tested for target year (2001-2003). Finally, some actual results for mid and long term water inflow forecasting are obtained and which show the proposed method has a good precision for forecasting.

• Periodical: Applied Mechanics and Materials (Volume 421)
• Pages: 803-807
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.421.803
• Online since: September 2013
• Authors: Hui Jun Xu
• Keywords: Artificial Neural Network (ANN), Runoff Forecast, Wavelet Analysis

References

[1] Chen Shouyu, Integrative analysis theory mode and method to long-term hydrologic forecast, Jurnal of Hydraulic Engineering, 1997, 8: pp.15-21.

[2] Kyung BS, Young SB, Dug HH, Gilsoo J (2005) Short-term load forecasting for the holidays using fuzzy linear regression method. IEEE Trans Power System 20: 96-101.

DOI: 10.1109/pes.2005.1489152

[3] Bishop. C. M, Neural networks and their applications, Rev. Sci. Intrum. vol. 65, no. 6, p.1803–1832, (1994).

[4] Hornik. K, Stinchcombe. M. and White. H, Multilayer feed-forward networks are universal approximators, Neural Networks, vol. 2, p.359–366, (1989).

DOI: 10.1016/0893-6080(89)90020-8

[5] Sun Yankui, Wavelet analysis and its application. Tsinghua University Press, Beijing, China, (2005).