Optimizing Edge Computing for Internet of Drones: A Hybrid Approach Using Deep Learning and Swarm-Based Routing

Abstract

The increasing adoption of drones in various industries has led to the emergence of the Internet of Drones (IoD), where efficient data processing and real-time decision-making are critical. Edge computing has become a key enabler for IoD, offering low-latency data processing close to drone networks. However, optimizing edge computing for IoD poses challenges due to the dynamic nature of drone swarms and fluctuating network conditions. This paper proposes a hybrid approach that combines deep learning and swarm-based routing to enhance edge computing in IoD environments. The deep learning model is utilized to predict network load and resource allocation, ensuring optimal placement of edge computing tasks and improving overall system efficiency. Concurrently, swarm-based routing leverages the collective intelligence of drones to dynamically adapt routing paths, mitigating latency and packet loss while maintaining high network reliability. The hybrid approach enables more responsive and scalable communication among drones, reducing computational overhead and improving task offloading efficiency. Simulation results demonstrate that the proposed approach significantly enhances system performance, achieving lower latency, higher throughput, and better energy efficiency compared to traditional methods. By integrating deep learning for predictive resource management with swarm-based routing for dynamic adaptability, this hybrid approach addresses the unique challenges of edge computing in IoD, offering a robust solution for real-time applications such as disaster management, surveillance, and delivery services. This work contributes to the development of more efficient and intelligent IoD systems, fostering the growth of drone-based applications in smart cities