Deep Reinforcement Learning for Dynamic Beamforming in Millimeter-Wave and Terahertz Bands

View at publisher Summarise with VIRAT
Authors: Siva Jothi S, M Tamilarasi, Renswick S
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The integration of Deep Reinforcement Learning (DRL) for dynamic beamforming in millimeter-wave (mmWave) and terahertz (THz) communication systems represents a transformative approach to optimizing the performance of next-generation wireless networks. These high-frequency bands offer significant bandwidth advantages but present substantial challenges, including high propagation losses, rapid channel variations, and interference in densely populated environments. DRL, with its capability to learn optimal strategies through interaction with the environment, provides an effective solution to these challenges by adapting beamforming parameters in real time. This chapter delves into the application of DRL for dynamic beamforming, focusing on key aspects such as channel state estimation, interference mitigation, and energy-efficient power control. Through a comprehensive review of current advancements, this chapter highlights case studies, the impact of stochastic channel conditions, and the scalability of DRL models in large-scale wireless networks. Furthermore, the chapter explores the trade-offs between exploration and exploitation within the DRL framework, offering insights into overcoming critical obstacles like computational complexity and real-time decision-making in mmWave and THz systems. The potential of DRL to revolutionize beamforming strategies in these frequency bands is immense, paving the way for more reliable, adaptive, and efficient wireless communication systems.

Fields of Study & Subjects

Millimeter-Wave Propagation and Modeling Advanced Wireless Communication Technologies Advanced MIMO Systems Optimization

Publication details

Pages
462–490
Publication date
18 March 2026
Language
EN
Document type
Book chapter