Title :
FPGA based router for cognitive packet networks
Author :
Hey, Laurence A. ; Cheung, Peter Y K ; Gellman, Michael
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. London
Abstract :
Cognitive packet networks are a neural network based intelligent networking concept. While the current software implementation of CPN has been shown to provide improved quality of service over traditional IP networks, the current algorithms do not lend themselves to hardware. The largest barrier is the decision making random neural network update algorithm. A proposed simplification and speed up of the RNN, and an implementation of a proof-of-concept CPN router on an FPGA are presented. It is shown that the simplified RNN update algorithm is seven times faster than the original algorithm, and provides a moderate increase in data rates for a typical flow
Keywords :
IP networks; field programmable gate arrays; neural nets; packet switching; quality of service; telecommunication network routing; FPGA based router; IP networks; RNN update algorithm; cognitive packet networks; field programmable gate arrays; quality of service; random neural network; software implementation; Decision making; Field programmable gate arrays; IP networks; Intelligent networks; Neural network hardware; Neural networks; Quality of service; Recurrent neural networks; Software algorithms; Software quality;
Conference_Titel :
Field-Programmable Technology, 2005. Proceedings. 2005 IEEE International Conference on
Conference_Location :
Singapore
Print_ISBN :
0-7803-9407-0
DOI :
10.1109/FPT.2005.1568586