SDRA-IIoT: A Security-Aware Dynamic Resource Allocation Framework for IIoT in Fog Computing

Abstract

Industrial Internet of Things (IIoT) applications in smart manufacturing generate dynamic and latency-sensitive workloads that challenge conventional fog-cloud resource allocation methods. To address this problem, this paper proposes SDRA-IIoT, a predictive and multi-objective orchestration framework for smart manufacturing applications deployed across IIoT, fog, and cloud layers. The framework integrates surrogate workload estimation, MOPSO-based placement optimization, security-aware filtering, QoS-aware validation, and adaptive load balancing within a unified runtime allocation process. SDRA-IIoT is implemented in iFogSim and evaluated against Hybrid Fuzzy-DQN and IoT DRL Offloading under a common simulation setting using repeated-run analysis over five random seeds. Experimental results show that SDRA-IIoT achieves the best overall service-level performance, reducing makespan to $164.43 \pm 13.99 \mathrm{~ms}$, lowering average response latency to $334.18 \pm 160.87 \mathrm{~ms}$, improving resource utilization efficiency to $89.02 \pm 0.55 \%$, and decreasing the deadline miss rate to 8.35±4.02%. These results demonstrate the effectiveness of predictive and multi-objective fog-cloud orchestration for industrial resource management.