Blockage Prediction and Proactive Handoff


Using beam sequences and recurrent neural networks to proactively predict future mmWave link blockages before they happen, which allows proactive network decisions, e.e., proactive handoff

Key ideas

  • Predicting mmWave link blockages before they happen
  • Leveraging gated recurrent units for a variable beam sequence solution 


  • Enhancing network reliability and latency with proactive blockage prediction
  • Enabling proactive hand-off and beam switching 

More information about this research direction

Paper: A. Alkhateeb, I. Beltagy and S. Alex, “Machine Learning for Reliable mmWave Systems: Blockage Prediction and Proactive Handoff,” 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2018, pp. 1055-1059.

Abstract: The sensitivity of millimeter wave (mmWave) signals to blockages is a fundamental challenge for mobile mmWave communication systems. The sudden blockage of the line-of-sight (LOS) link between the base station and the mobile user normally leads to disconnecting the communication session, which highly impacts the system reliability. Further, reconnecting the user to another LOS base station incurs high beam training overhead and critical latency problem. In this paper, we leverage machine learning tools and propose a novel solution for these reliability and latency challenges in mmWave MIMO systems. In the developed solution, the base stations learn how to predict that a certain link will experience blockage in the next few time frames using their observations of adopted beamforming vectors. This allows the serving base station to proactively hand-over the user to another base station with highly probable LOS link. Simulation results show that the developed deep learning based strategy successfully predicts blockage/hand-off in close to 95% of the times. This reduces the probability of communication session disconnection, which ensures high reliability and low latency in mobile mmWave systems.

author={Alkhateeb, Ahmed and Beltagy, Iz and Alex, Sam},
booktitle={2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)},

To reproduce the results in this paper:

Simulation codes (based on DeepMIMO v1):

Coming soon

These simulations use the DeepMIMO scenarios:

Coming soon

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