A Tutorial on Ultra-Reliable and Low-Latency Communications in 6G: Integrating Domain Knowledge into Deep Learning

Abstract

As one of the key communication scenarios in the 5th and also the 6th generation (6G) cellular networks, ultra-reliable and low-latency communications (URLLC) will be central for the development of various emerging mission-critical applications. The state-of-the-art mobile communication systems do not fulfill the end-to-end delay and overall reliability requirements of URLLC. A holistic framework that takes into account latency, reliability, availability, scalability, and decision-making under uncertainty is lacking. Driven by recent breakthroughs in deep neural networks, deep learning algorithms have been considered as promising ways of developing enabling technologies for URLLC in future 6G networks. This tutorial illustrates how to integrate theoretical knowledge (models, analysis tools, and optimization frameworks) of wireless communications into different kinds of deep learning algorithms for URLLC. We first introduce the background of URLLC and review promising network architectures and deep learning frameworks in 6G. To better illustrate how to improve learning algorithms with theoretical knowledge, we revisit model-based analysis tools and cross-layer optimization frameworks for URLLC. Following that, we examine the potential of applying supervised/unsupervised deep learning and deep reinforcement learning in URLLC and summarize related open problems. Finally, we provide simulation and experimental results to validate the effectiveness of different learning algorithms and discuss future directions.

A Reliable Reinforcement Learning for Resource Allocation in Uplink NOMA-URLLC Networks

“…For emerging NOMA-URLLC applications, long-term reliable optimization of resource allocation to improve the latency, reliability, and data rates is challenging but important [26]- [28].…”

“…Therefore, the total complexity is as (trace-table+ Weighted matrix of DQN), as O(τ (S × A) + Q(s, a; θ DQN )).Where the complexity of trace table is based on the number of states and action that is calculated as O(τ (S×A)). The weighted matrix is experience memory that is based on the experiences from(28). Therefore the worst case complexity of the weighted matrix is computed as O((θ)).…”

User-centric Cell-free Massive MIMO Networks: A Survey of Opportunities, Challenges and Solutions

“…Another incentive for distributed resource allocation is the increased density for the deployed DUs, which yields a large load on the fronthaul. In addition, the strict low-latency requirements for future mobile networks [239] necessitates implementing intelligence at the network access. The attractive features like self- organization and optimization discussed previously also motivates such approach.…”

6G Internet of Things: A Comprehensive Survey

“…In the 6G era, it is expected to achieve URLLC for supporting future IoT services through low-latency and reliable connectivity [64], [65]. For example, mURLLC is expected to support the timely and highly reliable delivery of massive health data for facilitating remote healthcare, aiming to provide better medical services to patients in the remote areas and also reduce regional imbalance in the health workforce.…”