loading page

A Robust Routing Strategy based on Deep Reinforcement Learning for Mege Satellite Constellations
  • Ke Chu,
  • Sixi Cheng,
  • Zhu Lidong (GE)
Ke Chu
University of Electronic Science and Technology of China

Corresponding Author:202122220314@std.uestc.edu.cn

Author Profile
Sixi Cheng
UESTC
Author Profile
Zhu Lidong (GE)
University of Electronic Science and Technology of China
Author Profile

Abstract

The development of mega constellations inevitably brings various problems for the development of routing techniques. Most of the existing work considers end-to-end delay and load balancing problems, while the analysis of routing strategies in case of link performance degradation is neglected, and an optimization approach applicable to mega satellite networks is not developed. In this letter, we propose a robust routing strategy based on deep reinforcement learning (RRS-DRL) that regards the Age of Information (AoI) of packets as an optimization target, and ensures the effectiveness of message transmission throughout the network. Extensive simulation results show that our proposed RRS-DRL algorithm obtains a lower average AoI across the network and better utilization of the resources than the traditional shortest path algorithm, significantly increasing the robustness of the constellation.
01 Mar 2023Submitted to Electronics Letters
02 Mar 2023Submission Checks Completed
02 Mar 2023Assigned to Editor
24 Mar 2023Reviewer(s) Assigned
02 Apr 2023Review(s) Completed, Editorial Evaluation Pending
07 Apr 2023Editorial Decision: Revise Major
07 May 20231st Revision Received
10 May 2023Submission Checks Completed
10 May 2023Assigned to Editor
10 May 2023Review(s) Completed, Editorial Evaluation Pending
15 May 2023Editorial Decision: Accept