DocumentCode :
2507358
Title :
Neural network control of shared ATM buffer
Author :
Reljin, Irini S. ; Reljin, Branimir D.
Author_Institution :
PTT Coll., Belgrade, Serbia
fYear :
2002
fDate :
2002
Firstpage :
107
Lastpage :
112
Abstract :
Assuming the shared buffer in ATM node with bursty input traffic, we have derived a new competitive neural network algorithm for buffer management. The algorithm is an extended version of the previous one, based on input prebuffers solution. The cell loss rate obtained is considerably lower comparing to the round-robin control in such a case. The interarrival times of output streams are considered by fractal/multifractal analysis, as well.
Keywords :
asynchronous transfer mode; fractals; neurocontrollers; telecommunication congestion control; telecommunication network management; ATM node; buffer management; bursty input traffic; cell loss rate; competitive neural network algorithm; fractal analysis; multifractal analysis; neural network control; output stream interarrival times; shared ATM buffer; Asynchronous transfer mode; B-ISDN; Communication system traffic control; Delay; Fractals; Neural networks; Round robin; Scheduling; Throughput; Traffic control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2002. NEUREL '02. 2002 6th Seminar on
Print_ISBN :
0-7803-7593-9
Type :
conf
DOI :
10.1109/NEUREL.2002.1057978
Filename :
1057978
Link To Document :
بازگشت