Title :
Novel method for mid-long term runoff forecasting
Author_Institution :
Nanchang Inst. of Technol., Nanchang, China
Abstract :
In order to improve water management efficiency of hydro system, a three-layer feed-forward back-propagation network based on data mining is proposed for min and long term runoff forecasting. The proposed network is trained with 52 years (1952-2003) actual data of one hydro power plant of Jiangxi province and is tested for target year (2004-2006). 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.
Keywords :
backpropagation; data mining; feedforward; forecasting theory; neural nets; data mining; hydro power plant; hydro system; mid-long term runoff forecasting; three-layer feed-forward back-propagation network; water management efficiency; Artificial neural networks; Computational modeling; Data mining; Data models; Forecasting; Neurons; Predictive models; artificial neural networks; back-propagation algorithm; data mining; runoff forecastin;
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
DOI :
10.1109/ICCASM.2010.5623232
