Closed-Loop Network Control for Industrial Edge Computing: A Telemetry-Driven and AI-Based Approach for Latency-Critical Applications in Private 5G

This letter presents a closed-loop network control mechanism for industrial edge computing environments using private 5G networks. The proposed solution integrates real-time telemetry collected from a programmable data plane with an AI-based prediction model to proactively manage network resources and prioritize latency-sensitive traffic. To validate the approach, a Proof-of-Concept was developed using a real industrial video distribution application deployed on a virtualized testbed with P4-enabled switches. Experimental results show that the proposed mechanism significantly reduces end-to-end latency and jitter, achieving improvements of up to 41.04% and 75.17%, respectively, compared to baseline configuration without control mechanisms. The findings highlight the AI-enhanced telemetry-driven control effectiveness to ensure the Quality-of-Service requirements of delay-sensitive applications in Industry 4.0.