Multi-Parameter Optimization Using Metaheuristic Algorithms to Improve Uncrewed Aerial Vehicles’ Wireless Communications: A Performance Analysis
Uncrewed aerial vehicles (UAVs) require robust communication for operational reliability. Recent research has explored artificial intelligence techniques, particularly metaheuristic algorithms, to address this challenge. However, studies on enhancing communication robustness through metaheuristic mu...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11021645/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Uncrewed aerial vehicles (UAVs) require robust communication for operational reliability. Recent research has explored artificial intelligence techniques, particularly metaheuristic algorithms, to address this challenge. However, studies on enhancing communication robustness through metaheuristic multi-parameter optimization along the flight path remain limited. To bridge this gap, we investigate the impact of optimizing five key parameters—carrier frequency, transmit power, modulation scheme, speed, and altitude—on minimizing bit error rate (BER) in UAV communication. This five-parameter optimization is defined as Approach 1. For comparison, a reduced three-parameter optimization is evaluated, excluding speed and altitude, as Approach 2. Seven metaheuristic algorithms were applied to both approaches, and the performance was evaluated via convergence and processing times. All algorithms achieved BERs of <inline-formula> <tex-math notation="LaTeX">$10^{-5}$ </tex-math></inline-formula> or lower. Approach 1 caused significant speed and altitude variations in 100 milliseconds, leading to impractical acceleration demands. In contrast, Approach 2 produced more stable and feasible results by constraining the dynamics of the UAV. On average, in Approach 1, the whale optimization algorithm had the shortest convergence time, while ant colony optimization was the slowest. In Approach 2, particle swarm optimization converged fastest, while gray wolf optimization was slowest. Across both approaches, the genetic algorithm achieved the lowest processing time, and ant colony optimization the highest. This study highlights the importance of realistic UAV motion constraints in optimization and provides guidance on selecting metaheuristic algorithms that balance convergence speed and computational efficiency to improve communication reliability. Following an in-depth discussion, several directions for future research are proposed. |
|---|---|
| ISSN: | 2169-3536 |