Presentation 2003/12/12
An Intelligent State-Dependent Routing Scheme for Multicast Traffic
PHAM VAN Tien, Yoshiaki TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This study introduces Reinforcement Learning (RL) to solve the problem of Call Admission Control (CAC) and Routing for multicast connections in networks serving multiple service classes. The network system is trained to find out the optimal control policy that brings up the highest amount of reward in long-run. For a manageable solution and realizable training time, decomposition is carried out. To demonstrate the prominence of RL-based routing against MOSPF (Multicast extension to Open Shortest Path First) protocol, which is a routing protocol with high performance among available ones, we consider different criteria, including reward rate and call drop rate in simulations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CAC / Routing / Multicast / Reinforcement Learning / Reward
Paper # NS2003-211,PN2003-39
Date of Issue

Conference Information
Committee NS
Conference Date 2003/12/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Network Systems(NS)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Intelligent State-Dependent Routing Scheme for Multicast Traffic
Sub Title (in English)
Keyword(1) CAC
Keyword(2) Routing
Keyword(3) Multicast
Keyword(4) Reinforcement Learning
Keyword(5) Reward
1st Author's Name PHAM VAN Tien
1st Author's Affiliation Global Information and Telecommunication Institute, Waseda University()
2nd Author's Name Yoshiaki TANAKA
2nd Author's Affiliation Global Information and Telecommunication Institute, Waseda University:Advanced Research Institute for Science and Engineering, Waseda University
Date 2003/12/12
Paper # NS2003-211,PN2003-39
Volume (vol) vol.103
Number (no) 506
Page pp.pp.-
#Pages 4
Date of Issue