Cloud-Fog-Edge Collaborative Computing for Sequential MIoT Workflow: A Two-Tier DDPG-Based Scheduling Framework

TL;DR

This paper introduces a hierarchical DDPG-based scheduling framework for MIoT workflows across cloud, fog, and edge layers, effectively reducing makespan and handling complex, large-scale healthcare tasks.

Contribution

It presents a novel two-tier reinforcement learning framework that decomposes scheduling decisions into global and local controls for MIoT workflows.

Findings

Outperforms baseline scheduling methods as workflow complexity increases.

Demonstrates ability to learn effective long-term scheduling strategies.

Reduces workflow makespan in heterogeneous cloud-fog-edge environments.

Abstract

The Medical Internet of Things (MIoT) demands stringent end-to-end latency guarantees for sequential healthcare workflows deployed over heterogeneous cloud-fog-edge infrastructures. Scheduling these sequential workflows to minimize makespan is an NP-hard problem. To tackle this challenge, we propose a Two-tier DDPG-based scheduling framework that decomposes the scheduling decision into a hierarchical process: a global controller performs layer selection (edge, fog, or cloud), while specialized local controllers handle node assignment within the chosen layer. The primary optimization objective is the minimization of the workflow makespan. Experiments results validate our approach, demonstrating increasingly superior performance over baselines as workflow complexity rises. This trend highlights the frameworks ability to learn effective long-term strategies, which is critical for complex, large-scale MIoT scheduling scenarios.