Title :
Neural network controller for queueing in packet switch networks
Author :
Xiao-Dong Ji ; De-Jung Wang
Author_Institution :
Beijing Univ. of Posts & Telecommun., China
Abstract :
Packet switching is an important technology in broadband ISDN (B-ISDN). The authors propose neural networks architecture for two kinds of queueing in packet switch networks to gain maximum throughput. First they introduce a new energy function for the input queueing. Then they propose a modified input smoothing scheme, which can obtain higher throughput than the standard input smoothing scheme, and its control by neural network. Finally, computer simulation results are given.<>
Keywords :
B-ISDN; channel capacity; neural nets; packet switching; queueing theory; switching networks; telecommunication traffic; telecommunications control; B-ISDN; broadband ISDN; computer simulation; energy function; input queueing; maximum throughput; modified input smoothing scheme; neural network controller; neural networks architecture; packet switch networks; queueing; Computer architecture; Equations; Intelligent networks; Neural networks; Neurons; Packet switching; Smoothing methods; Switches; Telecommunication switching; Throughput;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.327959
