Title :
Detectable and Indicative Forward Active Network Congestion Control Algorithm
Author :
Wang, Xiao-hong ; Liu, Chong ; Qin, Min ; Huang, Min ; Wang, Jing-yang
Author_Institution :
Hebei Univ. of Sci. & Technol.
Abstract :
This paper proposes a congestion control algorithm DIFACC (detectable and indicative forward active network congestion control algorithm). DIFACC introduces the active detection and the passive indication mechanism, the random early detect (RED) queue management and the load balance technology based on the FACC. It promotes the efficient use of network resources, succeeds in avoiding the algorithm invalidation caused by the indication messages loss. A computer simulation is given to analyze the performance of the algorithms. With the analysis of performance between FACC and DIFACC, it shows that DIFACC not only resolves some problems in FACC, but also reduces the package loss rate and decreases the processing delay of packets
Keywords :
Internet; digital simulation; frame relay; queueing theory; resource allocation; telecommunication congestion control; Internet; active detection; computer simulation; detectable-indicative forward active network congestion control algorithm; load balance technology; package loss rate; passive indication mechanism; random early detect queue management; Algorithm design and analysis; Computer network management; Computer simulation; Cybernetics; Delay; Electronic mail; Load management; Machine learning; Machine learning algorithms; Packaging; Performance analysis; Performance loss; Technology management; Active network; Congestion control; DIFACC; Detection;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258995
