Computing offloading policy for training effectiveness of space-air-ground integrated network

Yuxuan Zhao; Kuntuo Zhu; Jiawei Su; Shiqi Cheng; Kui Liu

doi:10.1117/12.3009150

29 December 2023 Computing offloading policy for training effectiveness of space-air-ground integrated network

Yuxuan Zhao, Kuntuo Zhu, Jiawei Su, Shiqi Cheng, Kui Liu

Author Affiliations +

Proceedings Volume 12976, Eighth Asia Pacific Conference on Optics Manufacture and Third International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2023); 129761B (2023) https://doi.org/10.1117/12.3009150
Event: 8th Asia Pacific Conference on Optics Manufacture & 3rd International Forum of Young Scientists on Advanced Optical Manufacturing, 2023, Shenzhen, China

Abstract

Edge computing has become indispensable in the context of wireless network communication, particularly in scenarios with strained computing resource such as remote areas or areas where ground communication disruptions are prevalent. It significantly enhances the service quality of ground terminal devices. This paper proposes a Space-Air-Ground Integrated Network(SAGIN) edge computing model. However, the limited computational resources pose challenges to crucial aspects such as edge server deployment, edge server computing resource allocation, and offloading strategies in such scenarios, becoming pivotal in boosting network service capabilities. To address this, we explore different deep reinforcement learning algorithms to train the model towards optimizing system objectives. Among them, the Soft-Actor-Critic (SAC) deep reinforcement learning algorithm demonstrates superior applicability to such model problems, improving training effectiveness by approximately 18% compared to the DDPG algorithm (calculated using average reward value). The edge computing offloading technique also serves as a crucial foundation for future edge computing cross-domain interconnections and distributed task collaboration.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuxuan Zhao, Kuntuo Zhu, Jiawei Su, Shiqi Cheng, and Kui Liu "Computing offloading policy for training effectiveness of space-air-ground integrated network", Proc. SPIE 12976, Eighth Asia Pacific Conference on Optics Manufacture and Third International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2023), 129761B (29 December 2023); https://doi.org/10.1117/12.3009150

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Satellites

Unmanned aerial vehicles

Performance modeling

Machine learning

Detection and tracking algorithms

Mathematical optimization

Deep learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years