We investigate cellular networks supported by on-street parked vehicles, termed as Vehicular Relay Nodes (VeRN), which have been proposed to boost performance and scale the network to varying demands. We study the problems of Call Admission and Call Assignment, which are key to efficient operation. To achieve an efficient and practical solution, we propose to decouple this problem and solve it via two weakly-coupled algorithms. For Admission, we formulate a non-trivial Markov Decision Process, introducing a dynamic operator that stochastically accounts for the possible assignments. For the Assignment problem, we derive a local Deep Reinforcement Learning algorithm using Imitation Learning, while introducing several novel improvements. Performance evaluation shows that these strategies offer a significant improvement over baselines.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Call Admission and Assignment in Cellular Networks with Vehicular Relay Nodes


    Contributors:
    Levy, Ran (author) / Levy, Hanoch (author)


    Publication date :

    2021-09-01


    Size :

    441574 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On the Value of Vehicular Relay Nodes in Cellular Networks

    Lavi, Nadav / Levy, Hanoch | IEEE | 2017


    Joint admission and association in vehicular networks

    Ekanayake, E. (Ekanayake) | BASE | 2019

    Free access

    Optimal call admission to a mobile cellular network

    Saquib,M. / Yates,R. / Rutgers Univ.,Electrical and Computer Engng.Dep.,Wireless Information Network Lab.,US | Automotive engineering | 1995


    JOINT CALL ADMISSION CONTROL FOR MULTI-MODE TERMINALS IN HETEROGENEOUS CELLULAR NETWORKS

    Reddy, T Varun Kumar / Teja, Ponnada S S Siva | BASE | 2013

    Free access

    Two-tier cellular communication systems with enhanced vehicular-based primary nodes

    Henry, Samer / Alsohaily, Ahmed / Sousa, Elvino | IEEE | 2016