Multi-Agent Deep Reinforcement Learning for Joint Task Offloading and Resource Allocation in IIoT with Dynamic Priorities

The rapid growth of Industrial Internet of Things (IIoT) terminals has resulted in tasks exhibiting increased concurrency, heterogeneous resource demands, and dynamic priorities, significantly increasing the complexity of task scheduling in edge computing. Cloud–edge–end collaborative computing leverages cross-layer task offloading to alleviate edge node resource contention and improve task scheduling efficiency. However, existing methods generally neglect the joint optimization of task offloading, resource allocation, and priority adaptation, making it difficult to balance task execution and resource utilization under resource-constrained and competitive conditions. To address this, this paper proposes a two-stage dynamic-priority-aware joint task offloading and resource allocation method (DPTORA). In the first stage, an improved Multi-Agent Proximal Policy Optimization (MAPPO) algorithm integrated with a Priority-Gated Attention Module (PGAM) enhances the robustness and accuracy of offloading strategies under dynamic priorities; in the second stage, the resource allocation problem is formulated as a single-objective convex optimization task and solved globally using the Lagrangian dual method. Simulation results show that DPTORA significantly outperforms existing multi-agent reinforcement learning baselines in terms of task latency, energy consumption, and the task completion rate.