Deep Learning for THz Drones with Flying Intelligent Surfaces: Beam and Handoff Prediction

  title={Deep Learning for THz Drones with Flying Intelligent Surfaces: Beam and Handoff Prediction},
  author={Nof Abuzainab and Muhammad Alrabeiah and Ahmed Alkhateeb and Yalin Evren Sagduyu},
  journal={2021 IEEE International Conference on Communications Workshops (ICC Workshops)},
We consider the problem of proactive handoff and beam selection in Terahertz (THz) drone communication networks assisted with reconfigurable intelligent surfaces (RISs). Drones have emerged as critical assets for next-generation wireless networks to provide seamless connectivity and extend the coverage, and can largely benefit from operating in the THz band to achieve high data rates (such as considered for 6G). However, THz communications are highly susceptible to channel impairments and… 

Figures and Tables from this paper

Artificial Intelligence Empowered Multiple Access for Ultra Reliable and Low Latency THz Wireless Networks

A fast and centralized joint user association, radio resource allocation, and blockage avoidance by means of a novel metaheuristic-machine learning framework is documented, that maximizes the THz networks performance, while minimizing the association latency by approximately three orders of magnitude.

Machine Learning for Intelligent-Reflecting-Surface-Based Wireless Communication towards 6G: A Review

A comprehensive overview of the state-of-the-art on ML, especially on deep learning (DL)-based IRS-enhanced communication is provided, which focuses on their operating principles, channel estimation (CE), and the applications of machine learning to IRS- enhanced wireless networks.


The capacity potential of THz‐enabled drone networks is revealed, motivating channel capacity results for communication of drones at different altitudes, under ideal channel conditions with no fading and realistic channel with beam misalignment and multipath fading are provided.

Multi-cell Multi-beam Prediction using Auto-encoder LSTM for mmWave systems

This work proposes a fully data-driven approach based on a novel auto-encoder integrated long short term memory (LSTM) network, which predicts multiple beams from multiple cells, one time step in the future, and observes that predictions from the proposed network offers significantly better best beam accuracy and lower beam misalignment loss than common baseline approaches.

Handover Management for Drones in Future Mobile Networks—A Survey

The analysis and discussion of this study indicates that, by adopting intelligent handover schemes that utilizing machine learning, deep learning, and automatic robust processes, the handover problems and related issues can be reduced significantly as compared to traditional techniques.

AIRIS: Artificial intelligence enhanced signal processing in reconfigurable intelligent surface communications

The merging of AI and RIS, called AIRIS, is introduced over various signal processing topics, including environmental sensing, channel acquisition, beam-forming design, and resource scheduling, etc, and some interesting future directions are presented.

Beyond 5G RIS mmWave Systems: Where Communication and Localization Meet

It is argued that to harness the full potential of RISs, localization and communication must be tightly coupled, in sharp contrast to 5G and earlier generations, where localization was a minor additional service.

Cascaded Composite Turbulence and Misalignment: Statistical Characterization and Applications to Reconfigurable Intelligent Surface-Empowered Wireless Systems

The current contribution presents a theoretical framework for statistically characterizing cascaded composite turbulence and misalignment channels and provides an insightful outage probability upper-bound for a third scenario that considers parallel multi-RIS-empowered FSO systems.

An Overview of Signal Processing Techniques for Terahertz Communications

This tutorial overviews classical problems of waveform design and modulation, beamforming and precoding, index modulation, channel estimation, channel coding, and data detection in THz transceiver design, and focuses on ultramassive multiple-input–multiple-output (UM-MIMO) systems and reconfigurable intelligent surfaces.

Characterization of Terahertz Band Transmittance from Sea-Level to Drone Altitudes

This paper characterize the THz transmittance i.e., absorption gain using the data obtained from Line-by-Line Radiative Transfer Model (LBLRTM) tool, considering the available frequency channels selected via water-filling, altitudes from sea-level to drone altitudes and various transmission ranges, and analyzes the modeling of transmittances as a function of Frequency, Frequency, Distance and Altitude.




  • A. AlkhateebIz Beltagy
  • Computer Science
    2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
  • 2018
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 to proactively hand-over the user to another base station with highly probable LOS link.

Reconfigurable Intelligent Surface Empowered Terahertz Communication for LEO Satellite Networks

An assessment of the use of THz for the ISL, and the impact of the misalignment fading on the error performance; and numerical results demonstrate that the proposed RIS empowered THz communication solution reveals significant performance improvement introduced by the usage of RIS.

Deep Learning for Fast and Reliable Initial Access in AI-Driven 6G mmWave Networks

DeepIA, a deep neural network (DNN) framework for enabling fast and reliable initial access for AIdriven beyond 5G and 6G millimeter (mmWave) networks, reduces the IA time and outperforms the conventional IA's beam prediction accuracy.

Intelligent reflecting surface enhanced indoor terahertz communication systems

Fast Initial Access with Deep Learning for Beam Prediction in 5G mmWave Networks

It is shown that DeepIA reduces the IA time by sweeping fewer beams and significantly outperforms the conventional IA's beam prediction accuracy in both line of sight (LoS) and non-line of sight [NLoS] mmWave channel conditions.

Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6 GHz Channels

It is proved that under certain conditions, there exist mapping functions that can predict the optimal mmWave beam and blockage status directly from the sub-6 GHz channel and that a large enough neural network can predict mmWave beams and blockages with success probabilities that can be made arbitrarily close to one.

Terahertz Multi-User Massive MIMO With Intelligent Reflecting Surface: Beam Training and Hybrid Beamforming

Simulation results demonstrate that the proposed joint beam training and HB scheme is able to achieve close performance to the optimal fully digital beamforming which is implemented even under perfect channel state information (CSI).

Deep Learning for Large Intelligent Surfaces in Millimeter Wave and Massive MIMO Systems

An energy-efficient novel LIS architecture where all the LIS elements are passive except few non-uniformly distributed active elements (connected to the baseband) is proposed and an efficient solution to design the L IS reflection matrices is developed, with negligible training overhead, leveraging deep learning tools.

Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication

The adoption of a reconfigurable intelligent surface (RIS) for downlink multi-user communication from a multi-antenna base station is investigated and the results show that the proposed RIS-based resource allocation methods are able to provide up to 300% higher energy efficiency in comparison with the use of regular multi-Antenna amplify-and-forward relaying.

Terahertz Massive MIMO With Holographic Reconfigurable Intelligent Surfaces

The beam pattern of an ideal holographic RIS can be well approximated by that of an ultra-dense RIS, which has a more practical hardware architecture, and a closed-loop channel estimation (CE) scheme to effectively estimate the broadband channels that characterize THz massive MIMO systems aided by holog Graphic RISs is proposed.