eduzhai > Applied Sciences > Engineering >

DRL-Based QoS-Aware Resource Allocation Scheme for Coexistence of Licensed and Unlicensed Users in LTE and Beyond

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 30 pages

Abstract: In this paper, we employ deep reinforcement learning to develop a novel radioresource allocation and packet scheduling scheme for different Quality ofService (QoS) requirements applicable to LTEadvanced and 5G networks. Inaddition, regarding the scarcity of spectrum in below 6GHz bands, the proposedalgorithm dynamically allocates the resource blocks (RBs) to licensed users ina way to mostly preserve the continuity of unallocated RBs. This would improvethe efficiency of communication among the unlicensed entities by increasing thechance of uninterrupted communication and reducing the load of coordinationoverheads. The optimization problem is formulated as a Markov Decision Process(MDP), observing the entire queue of the demands, where failing to meet QoSconstraints penalizes the goal with a multiplicative factor. Furthermore, anotion of continuity for unallocated resources is taken into account as anadditive term in the objective function. Considering the variations in bothchannel coefficients and users requests, we utilize a deep reinforcementlearning algorithm as an online and numerically efficient approach to solve theMDP. Numerical results show that the proposed method achieves higher averagespectral efficiency, while considering delay budget and packet loss ratio,compared to the conventional greedy min-delay and max-throughput schemes, inwhich a fixed part of the spectrum is forced to be vacant for unlicensedentities.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...