Identification of a complex control object with frequency characteristics obtained experimentally with its dynamic neural network model

2015 ◽  
Vol 76 (4) ◽  
pp. 650-657
Author(s):  
A. G. Shumikhin ◽  
A. S. Boyarshinova
2014 ◽  
Vol 1008-1009 ◽  
pp. 709-713 ◽  
Author(s):  
Chuang Li ◽  
Zhi Qiang Liang ◽  
Min You Chen

Neural network is widely used in the load forecasting area,but the traditional methods of load forecasting usually base on static model,which cannot change as time goes on. And the accuracy is worse and worse. To solve the problem, a dynamic neural network model for load forecasting is proposed .By way of introduce Error discriminant function, to control the error of load forecasting and dynamically modify the predicting model. Through the contrast of the short-term load forecasting result based on static neural network model and dynamic neural network model proposed, the error of load forecasting is decrease effectively.


Sign in / Sign up

Export Citation Format

Share Document