Skip to main navigation Skip to search Skip to main content

Efficient Resource Management Based on DQN in LEO Satellite Edge Computing System

  • School of Electronics and Information Engineering, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a low earth orbit (LEO) satellite edge computing architecture is proposed by placing the mobile edge computing (MEC) servers on the LEO satellites to provide computing services for ground users. To solve the offloading decision and resource allocation problems in multi-user, multi-LEO satellite and multi-task scenario, we propose a computation offloading algorithm based on deep reinforcement learning (DRL), derive the sub-optimal power allocation scheme, and obtain the optimal MEC resource allocation scheme through convex optimization algorithm. Simulation results show that the proposed algorithm achieves excellent convergence effect and system performance.

Original languageEnglish
Title of host publication2023 IEEE Globecom Workshops, GC Wkshps 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages135-140
Number of pages6
ISBN (Electronic)9798350370218
DOIs
StatePublished - 2023
Externally publishedYes
Event2023 IEEE Globecom Workshops, GLOBECOM Workshop 2023 - Kuala Lumpur, Malaysia
Duration: 4 Dec 20238 Dec 2023

Publication series

Name2023 IEEE Globecom Workshops, GC Wkshps 2023

Conference

Conference2023 IEEE Globecom Workshops, GLOBECOM Workshop 2023
Country/TerritoryMalaysia
CityKuala Lumpur
Period4/12/238/12/23

Keywords

  • DRL
  • LEO satellite
  • convex optimization
  • edge computing

Fingerprint

Dive into the research topics of 'Efficient Resource Management Based on DQN in LEO Satellite Edge Computing System'. Together they form a unique fingerprint.

Cite this