Cognitive packet networks: QoS and performance

被引:55
作者
Gelenbe, E [1 ]
Lent, R [1 ]
Montuori, A [1 ]
Xu, ZG [1 ]
机构
[1] Univ Cent Florida, Sch Elect Engn & Comp Sci, Orlando, FL 32816 USA
来源
MASCOTS 2002: 10TH IEEE INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS, AND SIMULATION OF COMPUTER AND TELECOMMUNICATIONS SYSTEMS, PROCEEDINGS | 2002年
关键词
quality of service; reinforcement learning; cognitive packet networks; voice over IP;
D O I
10.1109/MASCOT.2002.1167055
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Reliability, security, scalability and QoS (Quality-of-Service) have become key issues as we envision the future Internet. This paper presents the "Cognitive Packet Network (CPN)" architecture in which intelligent peer-to-peer routing is carried out with the help of "smart packets" based on best-effort QoS goals. Since packetized voice has stringent QoS requirements, we then discuss the choice of a "goal" and "reward" function for this application and present experiments we have conducted for "voice over CPN". Its performance is detailed via several measurements, and the resulting QoS is compared with that of the IP routing protocol under identical conditions showing the gain resulting from the use of CPN.
引用
收藏
页码:3 / 9
页数:7
相关论文
共 12 条
[1]  
[Anonymous], DELIVERING VOICE IP
[2]   Function approximation with spiked random networks [J].
Gelenbe, E ;
Mao, ZH ;
Li, YD .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (01) :3-9
[3]   LEARNING IN THE RECURRENT RANDOM NEURAL NETWORK [J].
GELENBE, E .
NEURAL COMPUTATION, 1993, 5 (01) :154-164
[4]   Measurement and performance of a cognitive packet network [J].
Gelenbe, E ;
Lent, R ;
Xu, ZG .
COMPUTER NETWORKS, 2001, 37 (06) :691-701
[5]   Simulation with learning agents [J].
Gelenbe, E ;
Seref, E ;
Xu, ZG .
PROCEEDINGS OF THE IEEE, 2001, 89 (02) :148-157
[6]   Networks with cognitive packets [J].
Gelenbe, E ;
Lent, R ;
Xu, ZG .
8TH INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS AND SIMULATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS, PROCEEDINGS, 2000, :3-10
[7]  
GELENBE E, 2002, P IEEE ASWN PAR JUL
[8]  
GELENBE E, 1999, P IEEE ICTAI C TOOLS
[9]   Reinforcement learning with internal expectation for the random neural network [J].
Halici, U .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2000, 126 (02) :288-307
[10]   THE USE OF LEARNING ALGORITHMS IN TELEPHONE TRAFFIC ROUTING - A METHODOLOGY [J].
NARENDRA, KS ;
MARS, P .
AUTOMATICA, 1983, 19 (05) :495-502