Radio resource allocation optimization of space-terrestrial link based on reinforcement learning

Ping Ji; Nan Xu; Baiyan Wang; Xiang Li

doi:10.1117/12.3050022

18 November 2024 Radio resource allocation optimization of space-terrestrial link based on reinforcement learning

Ping Ji, Nan Xu, Baiyan Wang, Xiang Li

Proceedings Volume 13398, Fourth International Conference on Optics and Communication Technology (ICOCT 2024); 1339817 (2024) https://doi.org/10.1117/12.3050022
Event: Fourth International Conference on Optics and Communication Technology (ICOCT 2024), 2024, Nanjing, China

Abstract

The space-terrestrial integration network is undoubtedly the most significant engineering project today, while the space-terrestrial link is the bottleneck that constrain the network performance. The conventional methods of radio resource allocation of space-terrestrial link still play a dominant role, but improved approaches are needed to discover opportunities for enhancing the spectrum efficiency. Based on the analysis of future needs, a reinforcement learning assistance algorithm is proposed as an effective way to optimize the radio resource allocation of space-earth link. First, Markov decision process is constructed based on the characteristic of downlink resource allocation, then the resource allocation model is trained by using Q-learning. Simulation results show that the model could effectively enhance the spectrum efficiency.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ping Ji, Nan Xu, Baiyan Wang, and Xiang Li "Radio resource allocation optimization of space-terrestrial link based on reinforcement learning", Proc. SPIE 13398, Fourth International Conference on Optics and Communication Technology (ICOCT 2024), 1339817 (18 November 2024); https://doi.org/10.1117/12.3050022

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available