Disseminacao de mensagens DTN com base em grupos de interesses

TL;DR

This paper proposes a machine learning-based group routing method for Delay Tolerant Networks, demonstrating that larger interest-based groups improve message delivery rates up to 100% in simulations.

Contribution

It introduces a novel group formation approach using machine learning for DTN routing, enhancing delivery rates by leveraging social interest groups.

Findings

Larger groups increase message delivery rate, reaching 100%.

Group-based routing improves delivery delay and hop count.

Simulation results validate the effectiveness of interest-based grouping.

Abstract

Recent works explore social characteristics of nodes to improve message delivery rate in Delay Tolerant Networks (DTN). This work uses machine learning techniques to create node groups organized by common interests. Messages are sent to target groups, and from there to the final destination. Simulation results using The ONE simulator show that the larger the group size the higher the message delivery rate, that reaches 100% in some cases. The paper also presents results related to the groups of interest such as message delivery rat, delivery delay and an average number of hops to deliver messages. The overall results indicate that group-based routing is a promising research filed.