Situation-Aware Channel Covariance Prediction for Massive MIMO Systems

The BS acquires the user locations with different levels of uncertainty, which are in turn leveraged to predict the channel statistics for downlink beamforming design.

Key ideas

  • Developing a beam design approach adaptive to the level of location uncertainty
  • Leveraging deep learning to denoise locations using wireless uplink channels
  • leveraging machine learning to predict downlink channel statistics
  • Downlink beamforming design using the predicted downlink channel statistics
  • Achieving robustness against location uncertainty
  • Adaptive beamforming design for high mobility FDD massive MIMO systems


  • Achieve rate robustness for highly-mobile users in FDD Massive MIMO systems
  • Reduce the channel estimation overhead in FDD massive MIMO systems
  • Denoise locations using wireless channel knowledge

More information about this research direction

Paper: Abdelrahman Taha and Ahmed Alkhateeb, “Situation-Aware Channel Covariance Prediction for Deep Learning Aided Massive MIMO Systems,” in Proc. of Asilomar Conference on Signals, Systems, and Computers (ACSSC), 2020, pp. 1342-1346.

Abstract: Designing efficient massive MIMO systems operating in a frequency-division duplexing (FDD) mode is one of the main intriguing research directions in the last decade. One of the main design challenges is reducing the huge training overhead incurred from acquiring the downlink channel knowledge at the base station. This challenge is even more prominent when serving highly-mobile users with high levels of location uncertainty. In this paper, we propose a novel situation-aware channel covariance prediction solution for downlink beamforming design. The proposed solution acquires imperfect knowledge of uplink and downlink channels and user location in the learning phase. In the operation phase, the proposed solution acquires only uplink channel estimates to predict a denoised location, which is then used to predict the downlink channel covariance matrix, for downlink beamforming design. Simulation results show the proposed solution achieves robust performance against uncertainty in the location information and imperfection in the downlink channel knowledge, both acquired in the learning phase, which makes it promising for supporting highly-mobile applications.


author={Taha, Abdelrahman and Alkhateeb, Ahmed},

booktitle={2020 54th Asilomar Conference on Signals, Systems, and Computers},

title={Situation-Aware Channel Covariance Prediction for Deep Learning Aided Massive MIMO Systems},






To reproduce the results in this paper:

Simulation codes (based on DeepMIMO v1):

Coming soon

These simulations use the DeepMIMO scenarios:
Example: Steps to generate the results in this figure
  1. Coming soon.

Having questions or feedback?

Send an email to 


Or post your question in the DeepMIMO forum