A DevSecOps-Driven Hybrid Reinforcement Learning and Swarm Intelligence for Secured Communication in Unmanned Vehicles to Everything (V2E) Framework

Abstract

Multi Unmanned Aerial Vehicles (MUAVs) networks, often referred to as Flying Ad Hoc Networks (FANETs), are
increasingly employed in applications such as disaster management, surveillance, and precision agriculture due to their flexibility and rapid deployment capabilities. However, the highly dynamic topology, limited energy resources, and vulnerability to security threats pose significant challenges to reliable and secure communication. To address these issues, this paper proposes a DevSecOps-driven hybrid framework that integrates topology-aware Q-learning, deep reinforcement learning, and swarm intelligence for secure and adaptive communication in multi-UAV networks. The proposed framework combines Q-learning-based path selection with Topology-Aware Reinforcement Learning for Decision Making (TARL-DM) to enable intelligent routing and dynamic adaptation to network changes. Additionally, a Swarm Intelligence-based Adaptive Communication (SIAC) module is incorporated to optimize cooperative behavior among UAVs, improving network scalability. To ensure continuous security and system robustness, a DevSecOps framework is integrated, enabling real-time monitoring, threat detection, and secure deployment of updates. The system is modelled using a multi-UAV network model, incorporating realistic mobility patterns, data generation processes, and transmission delay considerations. The proposed hybrid approach enhances communication reliability, reduces latency, and improves adaptability under dynamic network conditions while maintaining strong security guarantees. The performance of the proposed framework was evaluated using key metrics, including mission time, system utility, packet delivery ratio (PDR), end-to-end (E2E) delay, variation with speed, energy consumption, coverage rate, outage probability, and routing overhead, with results presented through comprehensive analytical charts. This work demonstrates that the integration of reinforcement learning, swarm intelligence, and DevSecOps principles provides a scalable and secure solution for nextgeneration UAV communication systems.