A Resilient Distributed Pareto-Based PSO for Edge-UAVs Deployment Optimization in Internet of Flying Things

Area of Science:

• Computer Science
• Robotics
• Network Engineering

Background:

• Particle Swarm Optimization (PSO) is a common technique for optimizing Unmanned Aerial Vehicle (UAV) deployment.
• Existing methods often struggle with multi-objective optimization in dynamic environments.

Purpose of the Study:

• To propose a framework for optimizing edge-enabled UAV deployment using Pareto-PSO.
• To address data collection scenarios requiring autonomous UAV operation and onboard distributed optimization.

Main Methods:

• A novel framework utilizing Pareto-PSO for multi-objective optimization of UAV deployment.
• Autonomous UAVs executing distributed multi-objective PSO onboard.
• Performance evaluation using convergence time, throughput, and coverage area metrics.

Main Results:

• Pareto-PSO achieved the highest throughput and largest coverage envelope.
• The method demonstrated moderate and scalable convergence times.
• Vector-valued objective treatment in Pareto-PSO proved advantageous.

Conclusions:

• The proposed Pareto-PSO framework offers an effective solution for real-time, scalable, and energy-aware edge-UAV deployment.
• This approach is well-suited for dynamic Internet of Flying Things environments.
• Optimizing coverage, latency, and energy consumption simultaneously is feasible and beneficial.