Neural Networks Based mmWave Massive MIMO Beam Codebooks


Learning hardware-compatible beam codebooks via self-supervision

Key ideas

  • Learning directly the phase configurations of the analog phase shifters which respects the non-convex hardware constraint
  • Proposing two different learning paradigms, i.e., supervised and self-supervised codebook learning methodologies
  • Demonstrating and empirically verifying the underlying clustering structure of the beam codebook learning problem


  • Learning small-sized site-specific beam codebook, e.g., SSB codebook, to reduce the initial access latency
  • Learning codebooks that adapt to the surrounding radio propagation environments
  • Learning optimized beam patterns for arrays with unknown, non-uniform geometries
  • Enabling online and fast codebook adaptation in the highly dynamic environments

More information about this research direction

Paper: Muhammad Alrabeiah, Yu Zhang and Ahmed Alkhateeb, “Neural networks based beam codebooks: learning mmWave massive MIMO beams that adapt to deployment and hardware,” in IEEE Transactions on Communications, vol. 70, no. 6, pp. 3818-3833, June 2022.

Abstract: Millimeter wave (mmWave) and massive MIMO systems are intrinsic components of 5G and beyond. These systems rely on using beamforming codebooks for both initial access and data transmission. Current beam codebooks, however, generally consist of a large number of narrow beams that scan all possible directions, even if these directions are never used. This leads to very large training overhead. Further, these codebooks do not normally account for the hardware impairments or the possible non-uniform array geometries, and their calibration is an expensive process. To overcome these limitations, this paper develops an efficient online machine learning framework that learns how to adapt the codebook beam patterns to the specific deployment, surrounding environment, user distribution, and hardware characteristics. This is done by designing a novel complex-valued neural network architecture in which the neuron weights directly model the beamforming weights of the analog phase shifters, accounting for the key hardware constraints such as the constant-modulus and quantized-angles. This model learns the codebook beams through online and self-supervised training avoiding the need for explicit channel state information. This respects the practical situations where the channel is either unavailable, imperfect, or hard to obtain, especially in the presence of hardware impairments. Simulation results highlight the capability of the proposed solution in learning environment and hardware aware beam codebooks, which can significantly reduce the training overhead, enhance the achievable data rates, and improve the robustness against possible hardware impairments.

author={Alrabeiah, Muhammad and Zhang, Yu and Alkhateeb, Ahmed},
journal={IEEE Transactions on Communications},
title={Neural Networks Based Beam Codebooks: Learning mmWave Massive MIMO Beams That Adapt to Deployment and Hardware},

To reproduce the results in this paper:

Simulation codes (based on DeepMIMO v1):
These simulations use the DeepMIMO scenarios:

Having questions or feedback?

Send an email to 


Or post your question in the DeepMIMO forum