eduzhai > Applied Sciences > Engineering >

AnciNet An Efficient Deep Learning Approach for Feedback Compression of Estimated CSI in Massive MIMO Systems

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 13 pages

Abstract: Accurate channel state information (CSI) feedback plays a vital role inimproving the performance gain of massive multiple-input multiple-output(m-MIMO) systems, where the dilemma is excessive CSI overhead versus limitedfeedback bandwith. By considering the noisy CSI due to imperfect channelestimation, we propose a novel deep neural network architecture, namelyAnciNet, to conduct the CSI feedback with limited bandwidth. AnciNet extractsnoise-free features from the noisy CSI samples to achieve effective CSIcompression for the feedback. Experimental results verify that the proposedAnciNet approach outperforms the existing techniques under various conditions.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×