eduzhai > Applied Sciences > Engineering >

Multi-Agent Double Deep Q-Learning for Beamforming in mmWave MIMO Networks

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: Beamforming is one of the key techniques in millimeter wave (mmWave)multi-input multi-output (MIMO) communications. Designing appropriatebeamforming not only improves the quality and strength of the received signal,but also can help reduce the interference, consequently enhancing the datarate. In this paper, we propose a distributed multi-agent double deepQ-learning algorithm for beamforming in mmWave MIMO networks, where multiplebase stations (BSs) can automatically and dynamically adjust their beams toserve multiple highly-mobile user equipments (UEs). In the analysis, largestreceived power association criterion is considered for UEs, and a realisticchannel model is taken into account. Simulation results demonstrate that theproposed learning-based algorithm can achieve comparable performance withrespect to exhaustive search while operating at much lower complexity.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×