eduzhai > Applied Sciences > Engineering >

Linear and Deep Neural Network-based Receivers for Massive MIMO Systems with One-Bit ADCs

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 13 pages

Abstract: The use of one-bit analog-to-digital converters (ADCs) is a practicalsolution for reducing cost and power consumption in massiveMultiple-Input-Multiple-Output (MIMO) systems. However, the distortion causedby one-bit ADCs makes the data detection task much more challenging. In thispaper, we propose a two-stage detection method for massive MIMO systems withone-bit ADCs. In the first stage, we propose several linear receivers based onthe Bussgang decomposition, that show significant performance gain overexisting linear receivers. Next, we reformulate the maximum-likelihood (ML)detection problem to address its non-robustness. Based on the reformulated MLdetection problem, we propose a model-driven deep neural network-based(DNN-based) receiver, whose performance is comparable with an existing supportvector machine-based receiver, albeit with a much lower computationalcomplexity. A nearest-neighbor search method is then proposed for the secondstage to refine the first stage solution. Unlike existing search methods thattypically perform the search over a large candidate set, the proposed searchmethod generates a limited number of most likely candidates and thus limits thesearch complexity. Numerical results confirm the low complexity, efficiency,and robustness of the proposed two-stage detection method.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×