A high-performance DRL-based mobile edge offloading for elastic satellite network

Tianhao Lin; Zhiyong Luo

doi:10.1117/12.2668016

28 June 2023 A high-performance DRL-based mobile edge offloading for elastic satellite network

Tianhao Lin, Zhiyong Luo

Proceedings Volume 12720, 2022 Workshop on Electronics Communication Engineering; 1272009 (2023) https://doi.org/10.1117/12.2668016
Event: 2022 Workshop on Electronics Communication Engineering (WECE 2022), 2022, Xi'an, China

Abstract

With the development of satellite technology, satellite communication can realize reliable communication with long-distance and large-scale coverage. However, satellite resources are now relatively scarce. To address this feature, this paper focuses on designing a reasonable and efficient elastic network model and prioritizing tasks with Mobile Edge Computing (MEC) technology to maximize the use of satellite node resources while handling urgent tasks promptly. Task offloading is a key technology for MEC, and the required parameters for modeling and optimizing target designs can be obtained through the resource virtualization function in the architecture of elastic satellite network. In addition, users can make efficient offloading decisions among servers on this architecture. We focus on the optimal delay model for a multi-user multi-edge server scenario with priority, i.e., the Software-defined Multi-priority Task Offloading Model (SMTOM). The optimization objective of the scenario is then reduced to a Mixed Integer Nonlinear Programming (MINLP) problem, for which Deep Reinforcement Learning (DRL)-Based Dynamic Task Offloading (DDTO) algorithm is used to solve the task offloading problems in satellite scenarios. The DDTO algorithm improves the average delay performance by 81%, 93%, and 84% compared to the random offloading algorithm, the local offloading algorithm, and the greedy algorithm, respectively.

Citation Download Citation

Tianhao Lin and Zhiyong Luo "A high-performance DRL-based mobile edge offloading for elastic satellite network", Proc. SPIE 12720, 2022 Workshop on Electronics Communication Engineering, 1272009 (28 June 2023); https://doi.org/10.1117/12.2668016

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