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

页码：1903 / 1913

页数：11

共 29 条

[1] [Anonymous], 1997, P ACM SIGCOMM 1997 O
[2] REM: Active queue management
Athuraliya, S
Low, SH
Li, VH
Yin, QH
[J]. IEEE NETWORK, 2001, 15 (03): : 48 - 53
[3] Bequette B.W., 2003, PROCESS CONTROL MODE
[4] Eigenvalue optimisation problems via evolutionary programming
Cao, YJ
[J]. ELECTRONICS LETTERS, 1997, 33 (07) : 642 - 643
[5] A stable queue-based adaptive controller for improving AQM performance
Chang, Xiaolin
Muppala, Jogesh K.
[J]. COMPUTER NETWORKS, 2006, 50 (13) : 2204 - 2224
[6] Power system model validation for power quality assessment applications using genetic algorithm
El-Zonkoly, AM
[J]. 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
Floyd, Sally
Jacobson, Van
[J]. IEEE-ACM TRANSACTIONS ON NETWORKING, 1993, 1 (04) : 397 - 413
[10] Goldberg EE., 1989, Genetic Algorithm in Searching, Optimization, and Machine Learning

← 1 2 3 →