The landscape of industrial communication systems is rapidly evolving, driven by the proliferation of Industrial IoT (IIoT) devices, increased automation, and the convergence of operational and information technologies. This evolution introduces greater complexity, with diverse requirements in latency, reliability, scalability, and mobility, calling for advanced planning and decision-support tools. In this work, we address the needs of IIoT applications requiring ultra-reliable low-latency communication and mobility support. Instead of relying on 5G ultra-reliable low-latency communications (URLLC), we thoroughly investigate an alternative option, less covered in the existing literature, based on the IETF 6TiSCH architecture and short-range communications. In particular, we propose Highly-Reliable Real-Time Scheduling for 6TiSCH (6HRRT), a novel algorithm designed for mobile IIoT scenarios. By combining intelligent resource allocation with optimized redundancy strategies, 6HRRT achieves reliability up to 99.999% and latencies of tens of milliseconds for applications with heterogeneous requirements. Simulation results show that 6HRRT consistently outperforms state-of-the-art 6TiSCH solutions, particularly under mixed workloads and stringent requirements, ensuring robust real-time performance in IIoT environments.
M. Pettorali, Francesca Righetti, Paolo Bellavista et al.· IEEE Open Journal of the Com...· 0 citations
While deploying hierarchical vision models to process mission-critical tasks, UAV edge systems must adaptively update the models to sustain inference reliability under low-level environmental corruption. However, existing work has overlooked the optimal timing for model updates, the impracticality of relying on real-time expert labels, and the significant bandwidth and energy constraints of UAVs. This paper proposes a joint model update scheduling and resource allocation framework, aiming to maximize long-term semantic fidelity and resource efficiency of UAV edge intelligence systems. To address the challenge of label-free semantic evaluation, we formulate the Online Semantic Disagreement Rate (OSDR) as a proxy for timely update triggering, thereby enabling fine-grained Sensitivity-Aware Structural Synchronization (SASS). Furthermore, to overcome the curse of dimensionality in hybrid action spaces and effectively bound long-term energy budgets, we propose a Lyapunov-guided discrete reinforcement learning algorithm that performs action space dimensionality reduction and transforms constraints into virtual queue stability problems. The reported experimental results, based on real traffic traces, demonstrate that the proposed framework consistently outperforms representative baselines in semantic recovery efficiency and update triggering precision, by satisfying long-term energy budget and by reducing average risk backlog by up to 33.3\% in the dynamic environmental corruption scenario.
Feng He, Alireza Furutanpey, Paolo Bellavista et al.· 0 citations
The proposed approach separates the research-infrastructure layer, which exposes and manages distributed resources, from the application layer, where Cyber-Physical workflows are organized according to an Edge-Fog-Cloud pattern in which placement, timing, and data provenance are treated as first-class experimental concerns.
Fabio Orazio Mirto, Giuseppe Tricomi, L. D’Agati et al.· 0 citations
