Application of Machine Learning in Space–Air–Ground Integrated Network Data Link

Zhu, Shaofan; Wang, Shuning; Chen, Jia

doi:10.1007/978-981-15-8411-4_210

Cited by 2 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such optimization problems, typically concerned with throughput maximization, transmit power minimization, energy-efficiency maximization, etc., often aim at optimizing the network resources, e.g., user scheduling, power, spectrum optimization, etc. Recent references, however, e.g., [7], [9]- [13], show that machine learning techniques can indeed outperform conventional algorithms.…”

Section: A Motivationmentioning

confidence: 99%

“…Specifically, paper [9] points out that machine learning can be used to solve four main problems in integrated air-spaceground networks (i.e., resource management, security authentication, attack detection, and target recognition and location). Reference [7] studies the difficulties of resource optimization due to the heterogeneity of space-air-ground networks and proposes adopting machine leaning to improve the system's utility.…”

Section: A Motivationmentioning

confidence: 99%

“…PERSPECTIVE Machine learning has recently emerged as a powerful solver for optimizing wireless communications [8], [9]. Thanks to its inherent characteristics in terms of data driven, automating analytical modeling, and online processing, machine learning proves to be useful at solving complex communication optimization problems with random, dynamic channel and unpredictable users demands in time and space [8].…”

Section: Machine Learning: a Resource Allocationmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning-Based User Scheduling in Integrated Satellite-HAPS-Ground Networks

Dahrouj¹,

Li²,

Alouini³

2022

Preprint

View full text Add to dashboard Cite

Integrated space-air-ground networks promise to offer a valuable solution space for empowering the sixth generation of communication networks (6G), particularly in the context of connecting the unconnected and ultraconnecting the connected. Such digital inclusion thrive makes resource management problems, especially those accounting for load-balancing considerations, of particular interest. The conventional modelbased optimization methods, however, often fail to meet the realtime processing and quality-of-service needs, due to the high heterogeneity of the space-air-ground networks, and the typical complexity of the classical algorithms. Given the premises of artificial intelligence at automating wireless networks design, this paper focuses on showcasing the prospects of machine learning in the context of user scheduling in integrated space-air-ground communications. The paper first overviews the most relevant state-of-the art in the context of machine learning applications to the resource allocation problems, with a dedicated attention to space-air-ground networks. The paper then proposes, and shows the benefit of, one specific application that uses ensembling deep neural networks for optimizing the user scheduling policies in integrated space-high altitude platform station (HAPS)-ground networks. Finally, the paper sheds light on the challenges and open issues that promise to spur the integration of machine learning in space-air-ground networks, namely, online HAPS power adaptation, learning-based channel sensing, data-driven multi-HAPSs resource management, and intelligent flying taxisempowered systems.

show abstract

Section: A Motivationmentioning

confidence: 99%

Section: A Motivationmentioning

confidence: 99%