Autonomous smart routing for network QoS

被引:55
作者
Gelenbe, E [1 ]
Gellman, M [1 ]
Lent, R [1 ]
Liu, PX [1 ]
Su, P [1 ]
机构
[1] Univ London Imperial Coll Sci Technol & Med, Dept Elect & Elect Engn, London SW7 2BT, England
来源
INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING, PROCEEDINGS | 2004年
关键词
D O I
10.1109/ICAC.2004.1301368
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We present an autonomous adaptive quality of service (QoS) driven network system called a "Cognitive Packet Network" (CPN), which adaptively selects paths so as to offer best effort QoS to the end users based on user defined QoS. CPN uses neural network based reinforcement learning to make routing decisions separately at each node. Measurements on an experimental test-bed are provided to show how the system responds to the choice of QoS goals. We also discuss and evaluate an extension of CPN that uses a genetic algorithm to generate and maintain paths from previously discovered information by matching their "fitness" with respect to the desired QoS.
引用
收藏
页码:232 / 239
页数:8
相关论文
共 9 条
[1]   Putting More Genetics into Genetic Algorithms [J].
Burke, Donald S. ;
De Jong, Kenneth A. ;
Grefenstette, John J. ;
Ramsey, Connie Loggia ;
Wu, Annie S. .
EVOLUTIONARY COMPUTATION, 1998, 6 (04) :387-410
[2]   LEARNING IN THE RECURRENT RANDOM NEURAL NETWORK [J].
GELENBE, E .
NEURAL COMPUTATION, 1993, 5 (01) :154-164
[3]  
Gelenbe E, 2001, PERFORMANCE AND QOS OF NEXT GENERATION NETWORKING, P3
[4]   Reinforcement learning with internal expectation for the random neural network [J].
Halici, U .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2000, 126 (02) :288-307
[5]   QoS routing for anycast communications: Motivation and an architecture for DiffServ networks [J].
Hao, F ;
Zegura, EW ;
Ammar, MH .
IEEE COMMUNICATIONS MAGAZINE, 2002, 40 (06) :48-56
[6]  
Holland JH, 1992, ADAPTATION NATURAL A, DOI DOI 10.7551/MITPRESS/1090.001.0001
[7]  
Lui JCS, 2001, PERFORMANCE AND QOS OF NEXT GENERATION NETWORKING, P263
[8]  
Rumelhart D.E., 1985, Learning internal representations by error propagation, DOI [DOI 10.7551/MITPRESS/5236.001.0001, 10.1016/b978-1-4832-1446-7.50035-2]
[9]  
Sutton R. S., 1988, Machine Learning, V3, P9, DOI 10.1023/A:1022633531479