Integrating swarm intelligence and edge computing for autonomous multi-drone operations

Abstract

This study presents an adaptive PSO (Particle Swarm Optimization) algorithm as the foundation for a swarm intelligence approach in multi-UAV operations. The traditional PSO formula for particle velocity and position updates was modified to incorporate a variation strategy from Differential Evolution (DE), enabling UAVs to dynamically adjust their trajectories. The integration of deep reinforcement learning (DRL) further enhances the modelʼs ability to optimize task offloading and computational distribution, ensuring that UAVs function as efficient edge nodes. An experimental evaluation was conducted to assess the proposed PSO-Edge method compared to other machine learning techniques, specifically Random Forest and Support Vector Machine (SVM). The experimental setup involved a simulation environment where UAVs were tasked to monitor data and execute missions over a defined area. The hardware included an Intel Xeon Gold 6248R CPU, 128 GB RAM, and an NVIDIA Tesla V100 GPU, with the simulation executed using Python 3.8. The proposed PSO-Edge algorithm demonstrated superior performance across multiple metrics: reducing task completion time by 42.1 minutes compared to Random Forest and SVM; achieving the lowest energy consumption per task at 28.9 Wh; demonstrating efficient communication with the least latency at 0.15 seconds; and achieving the highest task accuracy at 96%. The results confirm that the PSO-Edge method outperforms traditional machine learning approaches in task efficiency, energy consumption, communication latency, and accuracy. This highlights the benefits of integrating edge computing with the PSO algorithm, establishing it as a robust solution for multi-UAV operations. The findings have significant implications for optimizing UAV-based applications, particularly in environments requiring dynamic adaptation and efficient resource management