Enhancing Adaptive Beamforming in 3D Space Through Self-Improving Neural Network Techniques

Ioannis Mallioras, Traianos V. Yioultsis, Nikolaos V. Kantartzis, Pavlos I. Lazaridis, Zaharias D. Zaharis

Research output: Contribution to journalArticlepeer-review

Abstract

In the rapidly evolving domain of wireless networks, adaptive beamforming stands as a cornerstone for achieving higher data rates, enhanced network capacity, and reduced latency. This study introduces a novel integration of deep neural networks (NNs) into adaptive beamforming, specifically for uniform planar arrays (UPAs). We embark on an exploration of different NN architectures (a deep feedforward NN, a gated recurrent unit, and a long short-term memory based recurrent NN) and hyperparameter tuning techniques (grid search, Bayesian optimization, and genetic algorithm) to assemble a model that yields the most promising zero forcing beamforming performance. This thorough examination not only unveils the most prominent model but also highlights the most efficient hyperparameter tuning method. A comprehensive dataset generated using the null steering beamforming algorithm applied to an 8× 8 UPA, serves as the bedrock for training these networks. Our evaluation benchmarks the NN-based beamformers against traditional methods, assessing them on crucial metrics such as beamforming competence, response time, and adaptability under various noise and interference scenarios. A significant innovation of this research is the introduction of a continual learning approach, enhancing the NN beamformers' performance in dynamically changing environments. This self-improving algorithm represents a stride towards more adaptable and efficient beamforming, showcasing improvement on underperforming scenarios without compromising accuracy. Our findings demonstrate the potential of neural networks in reshaping the future of adaptive beamforming, offering a blend of speed and precision that is paramount in modern wireless networks.

Original languageEnglish
Article number10438855
Pages (from-to)1340-1357
Number of pages18
JournalIEEE Open Journal of the Communications Society
Volume5
Early online date16 Feb 2024
DOIs
Publication statusPublished - 4 Mar 2024

Cite this