Traffic Simulation in Ad Hoc Network of Flying UAVs with Generative AI Adaptation

TL;DR

This paper models traffic in UAV ad hoc networks and demonstrates AI-based adaptation of communication channels, analyzing packet loss dependencies and implementing adaptive data transmission to improve network performance.

Contribution

It introduces an AI-driven method for adapting communication channels in UAV ad hoc networks, based on modeling and analyzing packet loss dependencies.

Findings

Packet loss depends on packet size, transmission power, frequency, and UAV density.

AI adaptation reduces packet loss and optimizes power and transaction size over time.

The model and adaptive algorithm are implemented in code for practical use.

Abstract

The purpose of this paper is to model traffic in Ad Hoc network of Unmanned Aerial Vehicles and demonstrate a way for adapting communication channel using Artificial Intelligence. The modeling was based on the original model of Ad Hoc network including 20 Unmanned Aerial Vehicles. The dependences of packet loss on the packet size for different transmission powers, on the packet size for different frequencies, on Unmanned Aerial Vehicles flight area and on the number of Unmanned Aerial Vehicles were obtained and analyzed. The implementation of adaptive data transmission is presented in the program code. The dependences of packet loss, power and transaction size on time during Artificial Intelligence adaptation are shown.