Bayesian Optimization for Radio Resource Management: Open Loop Power Control

Maggi, Lorenzo; Rial, Alvaro Valcarce; Hoydis, Jakob

doi:10.48550/arxiv.2012.08469

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we note that some recent works such as [74] proposed the use of Bayesian optimization with Gaussian processes as a potentially superior alternative to RL (in terms of convergence and interpretability), for solving radio resource management problems. However, using this technique for real-world wireless problems is prohibitive because it requires satisfying multiple conditions such as a low number of control parameters, a smooth performance function, and a low update frequency to cope with the environmental dynamics.…”

Section: B Towards Multi-task Learning and Meta-learningmentioning

confidence: 99%

Seven Defining Features of Terahertz (THz) Wireless Systems: A Fellowship of Communication and Sensing

Chaccour

Soorki

Saad

et al. 2022

IEEE Commun. Surv. Tutorials

266

111

View full text Add to dashboard Cite

Wireless communication at the terahertz (THz) frequency bands (0.1 − 10 THz) is viewed as one of the cornerstones of tomorrow's 6G wireless systems. Owing to the large amount of available bandwidth, if properly deployed, THz frequencies can potentially provide significant wireless capacity performance gains and enable high-resolution environment sensing. However, operating a wireless system at high-frequency bands such as THz is limited by a highly uncertain and dynamic channel. Effectively, these channel limitations lead to unreliable intermittent links as a result of an inherently short communication range, and a high susceptibility to blockage and molecular absorption. Consequently, such impediments could disrupt the THz band's promise of highrate communications and high-resolution sensing capabilities. In this context, this paper panoramically examines the steps needed to efficiently and reliably deploy and operate next-generation THz wireless systems that will synergistically support a fellowship of communication and sensing services. For this purpose, we first set the stage by describing the fundamentals of the THz frequency band. Based on these fundamentals, we characterize and comprehensively investigate seven unique defining features of THz wireless systems: 1) Quasi-opticality of the band, 2) THztailored wireless architectures, 3) Synergy with lower frequency bands, 4) Joint sensing and communication systems, 5) PHYlayer procedures, 6) Spectrum access techniques, and 7) Real-time network optimization. These seven defining features allow us to shed light on how to re-engineer wireless systems as we know them today so as to make them ready to support THz bands and their unique environments. On the one hand, THz systems benefit from their quasi-opticality and can turn every communication challenge into a sensing opportunity, thus contributing to a new generation of versatile wireless systems that can perform multiple functions beyond basic communications. On the other hand, THz systems can capitalize on the role of intelligent surfaces, lower frequency bands, and machine learning (ML) tools to guarantee a robust system performance. We conclude our exposition by presenting the key THz 6G use cases along with their associated major challenges and open problems. Ultimately, the goal of this article is to chart a forward-looking roadmap that exposes the necessary solutions and milestones for enabling THz frequencies to realize

show abstract

Section: B Towards Multi-task Learning and Meta-learningmentioning

confidence: 99%

Seven Defining Features of Terahertz (THz) Wireless Systems: A Fellowship of Communication and Sensing

Chaccour

Soorki

Saad

et al. 2022

IEEE Commun. Surv. Tutorials

266

111

View full text Add to dashboard Cite

show abstract

“…Here, we note that some recent works such as [72] proposed the use of Bayesian optimization with Gaussian processes as a potentially superior alternative to RL (in terms of convergence and interpretability), for solving radio resource management problems. However, using this technique for real-world wireless problems is prohibitive because it requires satisfying multiple conditions such as a low number of control parameters, a smooth performance function, and a low update frequency to cope with the environmental dynamics.…”

Section: B Towards Multi-task Learning and Meta-learningmentioning

confidence: 99%