GA-based PID active queue management control design for a class of TCP communication networks

被引：28
作者：
Chen, Chang-Kuo [1 ]
Kuo, Hang-Hong [1 ]
Yan, Jun-Juh [2 ]
Liao, Teh-Lu [1 ]
机构：
[1] Natl Cheng Kung Univ, Dept Engn Sci, Tainan 701, Taiwan
[2] Shu Te Univ, Dept Comp & Commun, Kaohsiung 824, Taiwan
来源：
EXPERT SYSTEMS WITH APPLICATIONS | 2009年 / 36卷 / 02期
关键词：
AQM; TCP/IP; Congestion control; Genetic algorithm; PID controller; GENETIC ALGORITHMS; SYSTEM;
D O I：
10.1016/j.eswa.2007.12.003
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Active queue management (AQM) is a key congestion control scheme for reducing packet loss and improving network utilization in TCP/IP networks. This paper proposes a proportional-integral-derivative (PID) controller its an active queue manager for Internet routers. Due to the limitations of packet-dropping probability and the effects of propagation delays it, TCP networks, the TCP AQM network was modeled as a time-delayed system with a saturated input. Ail improved genetic algorithm is employed to derive optimal or near optimal PID controller gains such that it performance index of integrated-absolute error (IAE) is minimized, and thereby a stable queue length, low packet loss, and high link utilization for TCP networks are guaranteed. The performance of the proposed control scheme is evaluated in various network scenarios via a series of numerical simulations. (C) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码：1903 / 1913
页数：11
相关论文
共 29 条
[1]  
[Anonymous], 1997, P ACM SIGCOMM 1997 O
[2]   REM: Active queue management [J].
Athuraliya, S ;
Low, SH ;
Li, VH ;
Yin, QH .
IEEE NETWORK, 2001, 15 (03) :48-53
[3]  
Bequette B.W., 2003, PROCESS CONTROL MODE
[4]   Eigenvalue optimisation problems via evolutionary programming [J].
Cao, YJ .
ELECTRONICS LETTERS, 1997, 33 (07) :642-643
[5]   A stable queue-based adaptive controller for improving AQM performance [J].
Chang, Xiaolin ;
Muppala, Jogesh K. .
COMPUTER NETWORKS, 2006, 50 (13) :2204-2224
[6]   Power system model validation for power quality assessment applications using genetic algorithm [J].
El-Zonkoly, AM .
EXPERT SYSTEMS WITH APPLICATIONS, 2005, 29 (04) :941-944
[7]  
FENG W, 2002, IEEE ACM T NETWORK, V10, P89
[8]  
Floyd S., 2001, Adaptive RED: An algorithm for increasing the robustness of RED's active queue management
[9]   Random Early Detection Gateways for Congestion Avoidance [J].
Floyd, Sally ;
Jacobson, Van .
IEEE-ACM TRANSACTIONS ON NETWORKING, 1993, 1 (04) :397-413
[10]  
Goldberg EE., 1989, Genetic Algorithm in Searching, Optimization, and Machine Learning
123