2019 IEEE Global Communications Conference (GLOBECOM) 2019
DOI: 10.1109/globecom38437.2019.9013851
|View full text |Cite
|
Sign up to set email alerts
|

Unsupervised Deep Learning for Ultra-Reliable and Low-Latency Communications

Abstract: In this paper, we study how to solve resource allocation problems in ultra-reliable and low-latency communications by unsupervised deep learning, which often yield functional optimization problems with quality-of-service (QoS) constraints. We take a joint power and bandwidth allocation problem as an example, which minimizes the total bandwidth required to guarantee the QoS of each user in terms of the delay bound and overall packet loss probability. The global optimal solution is found in a symmetric scenario.… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
30
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
3

Relationship

2
5

Authors

Journals

citations
Cited by 17 publications
(30 citation statements)
references
References 22 publications
0
30
0
Order By: Relevance
“…To find the solution of constrained functional optimization problems, unsupervised learning techniques are proposed in [6,8,9]. A constrained optimization problem can be transformed into an unconstrained problem by using the Lagrangian approach.…”
Section: B Functional Optimization Using Unsupervised Learning and Rmentioning
confidence: 99%
See 2 more Smart Citations
“…To find the solution of constrained functional optimization problems, unsupervised learning techniques are proposed in [6,8,9]. A constrained optimization problem can be transformed into an unconstrained problem by using the Lagrangian approach.…”
Section: B Functional Optimization Using Unsupervised Learning and Rmentioning
confidence: 99%
“…In practice, there may also exist constraints imposed on a function averaged over the environment's status, e.g., average power constraints or average data rate constraints, as shown in P2. For more general wireless optimization problems, the "variables" to be optimized consist of both functions and variables, as exemplified by jointly optimizing a multi-timescale policy [6].…”
Section: A Learning Variable Optimization Without Labelsmentioning
confidence: 99%
See 1 more Smart Citation
“…Most DNN training techniques are not immediately usable here as the latency requirements of the system pose constraints in the optimization problem [16]. Recent advancements apply techniques from both reinforcement learning and deep learning for control-aware scheduling in simple systems [12]- [14] and traditional wireless systems with latency constraints [17], [18]. Learning-based scheduling policies are well suited for URLLC and control as the computational complexity at each scheduling round is very low and can furthermore be implemented model-free when system dynamics and communication models are unknown.…”
Section: Introductionmentioning
confidence: 99%
“…Update θJ , θg, θc by (7) and update θ f , θ λ , ξ by (8). 10: end for So far, we have implicitly assumed that the policy to be learned is continuous (i.e., f (h) is a continuous function of h), and learn its parameterized formf (h; θ f ) as a deterministic policy in both model-based and model free unsupervised learning frameworks.…”
mentioning
confidence: 99%