Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

FedRDR: Federated Reinforcement Distillation-Based Routing Algorithm in UAV-Assisted Resilient Networks for Communication Infrastructure Failures

Version 1 : Received: 17 October 2023 / Approved: 18 October 2023 / Online: 18 October 2023 (04:25:06 CEST)

A peer-reviewed article of this Preprint also exists.

Li, J.; Liu, A.; Han, G.; Cao, S.; Wang, F.; Wang, X. FedRDR: Federated Reinforcement Distillation-Based Routing Algorithm in UAV-Assisted Networks for Communication Infrastructure Failures. Drones 2024, 8, 49, doi:10.3390/drones8020049. Li, J.; Liu, A.; Han, G.; Cao, S.; Wang, F.; Wang, X. FedRDR: Federated Reinforcement Distillation-Based Routing Algorithm in UAV-Assisted Networks for Communication Infrastructure Failures. Drones 2024, 8, 49, doi:10.3390/drones8020049.

Abstract

Communication infrastructures may be partially or completely destroyed due to the natural disasters, especially the disruption of a few critical network devices, leading to the collapse of communication services.To address this issue, we constructed a layered, multi-domain data transmission architecture based on a UAV-assisted resilient network. Initially, the UAV controllers perceived the network status and learning the temporal- spatial characteristics of air-to-ground networks links. Subsequently, we developed a multi-domain routing algorithm based on federated reinforcement distillation, called FedRDR, enhancing the generalization capabilities of routing decision model through the augmentation of training data samples.We conducted simulation experiments, and the results indicate that the FedRDR algorithm has an average communication data volume of approximately 45.3KB between each domain controller and server. Compared to parameter transmission through the federated reinforcement learning algorithm, FedRDR can reduce the amount of transmitted parameters by approximately 29\%. Therefore, the FedRDR routing algorithm promotes knowledge transfer, accelerates the training process of intra-domain intelligent agents, and decreases the communication data volume between domain controllers and servers.

Keywords

Routing Decision; UAV-MEC; Software Defined Network(SDN); Federated Reinforcement Distillation

Subject

Computer Science and Mathematics, Computer Networks and Communications

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.