Saved in:
Bibliographic Details
Main Authors: Lozano-Cuadra, Federico, Soret, Beatriz
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.17666
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929412411228160
author Lozano-Cuadra, Federico
Soret, Beatriz
author_facet Lozano-Cuadra, Federico
Soret, Beatriz
contents This paper introduces a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach for routing in Low Earth Orbit Satellite Constellations (LSatCs). Each satellite is an independent decision-making agent with a partial knowledge of the environment, and supported by feedback received from the nearby agents. Building on our previous work that introduced a Q-routing solution, the contribution of this paper is to extend it to a deep learning framework able to quickly adapt to the network and traffic changes, and based on two phases: (1) An offline exploration learning phase that relies on a global Deep Neural Network (DNN) to learn the optimal paths at each possible position and congestion level; (2) An online exploitation phase with local, on-board, pre-trained DNNs. Results show that MA-DRL efficiently learns optimal routes offline that are then loaded for an efficient distributed routing online.
format Preprint
id arxiv_https___arxiv_org_abs_2402_17666
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing
Lozano-Cuadra, Federico
Soret, Beatriz
Machine Learning
Information Theory
This paper introduces a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach for routing in Low Earth Orbit Satellite Constellations (LSatCs). Each satellite is an independent decision-making agent with a partial knowledge of the environment, and supported by feedback received from the nearby agents. Building on our previous work that introduced a Q-routing solution, the contribution of this paper is to extend it to a deep learning framework able to quickly adapt to the network and traffic changes, and based on two phases: (1) An offline exploration learning phase that relies on a global Deep Neural Network (DNN) to learn the optimal paths at each possible position and congestion level; (2) An online exploitation phase with local, on-board, pre-trained DNNs. Results show that MA-DRL efficiently learns optimal routes offline that are then loaded for an efficient distributed routing online.
title Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2402.17666