DDPG Performance in THz Communications over Cascaded RISs: A Machine Learning Solution to the Over-Determined System | IEEE Conference Publication | IEEE Xplore

DDPG Performance in THz Communications over Cascaded RISs: A Machine Learning Solution to the Over-Determined System

Publisher: IEEE

Abstract:

THz technology is considered a key element in 6G wireless communication because it provides ultra-high bandwidths, considerable capacities, and significant gains. However...View more

Abstract:

THz technology is considered a key element in 6G wireless communication because it provides ultra-high bandwidths, considerable capacities, and significant gains. However, wireless systems operating at high frequencies are faced with uncertainty and highly dynamic channels. Reflecting intelligent surfaces (RISs) can increase the range of the THz communication links and boost the rate at the receiver. In contrast to the existing literature, we investigate the scenario of multiple access multi-hop (cascaded) RISs uplink THz networks in a correlated channel environment. We show that our inspected cascaded RIS system is over-determined and that the rate maximization optimization problem is non-convex. To this end, we derive a closed-form expression of the received power and derive an analytical solution based on pseudo-inverse to obtain optimum RISs’ phase shifts that maximize the received signal power and hence increase the rate. In addition, we utilize deep reinforcement learning (DRL), which is capable of solving non-convex optimization problems, to obtain the optimum cascaded RISs’ phase shifts at the receiver taking into account the situation of the spatially correlated channels. Simulation results demonstrate that the DRL algorithm achieves higher rates than the mathematical sub-optimal method and the case of randomized phases.
Date of Conference: 19-23 June 2023
Date Added to IEEE Xplore: 21 July 2023
ISBN Information:

ISSN Information:

Publisher: IEEE
Conference Location: Marrakesh, Morocco

Funding Agency:


I. Introduction

THZ frequency bands (100 GHz - 10 THz) are considered cornerstones in the 6G communication networks. THz-frequencies are favorable to support ultra-high bandwidths and significant data rates. These frequency bands can potentially provide considerable performance gains and significant capacities. Nonetheless, the transition towards the real and practical implementation of THz networks suffers from molecular losses, highly dynamic and varying channels, short-range links and communication distances, and the reliance on line-of-sight (LOS) or narrow-beam links [1], [2]. To optimize the achievable data rate at the receiver (Rx), this research paper examines the reflecting intelligent surface (RIS) as a modern technology and promising solution. The RIS is a two-dimensional (2D) electromagnetic surface, precisely metasurface, that constitutes a large number of semi-passive scattering elements. Every element can be controlled via a software-defined behavior to adjust the electromagnetic properties (i.e. phase-shift) of the reflection of the incident radio frequency (RF) signals upon the RIS elements [3], [4]. Thus, the RIS can instantly amend the wireless propagation channel to improve the signal transmission, boost the received signal power, and suppress the interference at the Rx. Therefore, it improves the data rate in a cost-effective and energy-efficient behavior and provides an innovative means to attain the 6G Key performance indicators (KPIs) [5], [6].

References

References is not available for this document.