Graph-Embedded Multi-Agent Learning for Smart Reconfigurable THz MIMO-NOMA Networks
- 8 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 40 (1) , 259-275
Abstract
With the accelerated development of immersive applications and the explosive increment of internet-of-things (IoT) terminals, 6G would introduce terahertz (THz) massive multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) technologies to meet the ultra-high-speed data rate and massive connectivity requirements. Nevertheless, the unreliability of THz transmissions and the extreme heterogeneity of device requirements pose critical challenges for practical applications. To address these challenges, we propose a novel smart reconfigurable THz MIMO-NOMA framework, which can realize customizable and intelligent communications by flexibly and coordinately reconfiguring hybrid beams through the cooperation between access points (APs) and reconfigurable intelligent surfaces (RISs). The optimization problem is formulated as a decentralized partially-observable Markov decision process (Dec-POMDP) to maximize the network energy efficiency, while guaranteeing the diversified users’ performance, via a joint RIS element selection, coordinated discrete phase-shift control, and power allocation strategy. To solve the above non-convex, strongly coupled, and highly complex mixed integer nonlinear programming (MINLP) problem, we propose a novel multi-agent deep reinforcement learning (MADRL) algorithm, namely graph-embedded value-decomposition actor-critic (GE-VDAC) , that embeds the interaction information of agents, and learns a locally optimal solution through a distributed policy. Numerical results demonstrate that the proposed algorithm achieves highly customized communications and outperforms traditional MADRL algorithms.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation Program of China (61801333)
- Young Elite Scientists Sponsorship Program by the China Association for Science and Technology (CAST) 2019
- Natural Science Foundation General Program of Hubei Province (2020CFB633)
- National Natural Science Foundation of China Enterprise Innovation Development Key Project (U19B2004)
- China Scholarship Council
This publication has 31 references indexed in Scilit:
- Multiple-Antenna-Assisted Non-Orthogonal Multiple AccessIEEE Wireless Communications, 2018
- Nonorthogonal Multiple Access for 5G and BeyondProceedings of the IEEE, 2017
- Capacity Comparison Between MIMO-NOMA and MIMO-OMA With Multiple Users in a ClusterIEEE Journal on Selected Areas in Communications, 2017
- Adaptive Hybrid Precoding for Multiuser Massive MIMOIEEE Communications Letters, 2016
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Channel Modeling and Capacity Analysis for Electromagnetic Wireless Nanonetworks in the Terahertz BandIEEE Transactions on Wireless Communications, 2011
- Stochastic Network Optimization with Application to Communication and Queueing SystemsSynthesis Lectures on Communication Networks, 2010
- Scattering Analysis for the Modeling of THz Communication SystemsIEEE Transactions on Antennas and Propagation, 2007
- Probability Inequalities Related to Markov's TheoremThe American Statistician, 2002
- OPTIMAL PAYOFF FUNCTIONS FOR MEMBERS OF COLLECTIVESAdvances in Complex Systems, 2001