Intelligent CAC and routing for multi-point connections

Pham Van Tien, Franz Rammig, Yoshiaki Tanaka

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This study introduces Reinforcement Learning (RL) to solve the problem of Cull Admission Control (CAC)&Routing for multi-point connections in networks serving multiple service classes. The network system is trained to find out the optimal control policy which brings up the highest amount of reward in long-run. For a manageable solution and realizable training time, decomposition of network and connections into link level is implemented. To demonstrate the prominence of RL-based routing against MOSPF (Multicast extension to Open Shortest Path First) protocol, a routing protocol with high performance among available ones, we consider different criteria, including reward rate, call drop rate, and link usage rate.

    Original languageEnglish
    Title of host publicationProceedings of the International Conference on Communications in Computing, CIC'04
    EditorsB.J. d'Auriol
    Pages194-200
    Number of pages7
    Publication statusPublished - 2004
    EventProceedings of the International Conference on Communications in Computing, CIC'04 - Las Vegas, NV
    Duration: 2004 Jun 212004 Jun 24

    Other

    OtherProceedings of the International Conference on Communications in Computing, CIC'04
    CityLas Vegas, NV
    Period04/6/2104/6/24

      Fingerprint

    Keywords

    • CAC
    • Multi-point connection
    • Reinforcement learning
    • Reward
    • Routing

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Van Tien, P., Rammig, F., & Tanaka, Y. (2004). Intelligent CAC and routing for multi-point connections. In B. J. d'Auriol (Ed.), Proceedings of the International Conference on Communications in Computing, CIC'04 (pp. 194-200)