To meet low latency and real-time monitoring demands of IoT-eHealth, fog computing is envisioned as a key technology to offer elastic computing resource at the edge of networks. In this context, eHealth devices can offload collected healthcare data or computational expensive tasks to a nearby fog server. However, the mobility of the eHealth devices may make the connection between them to fog servers uncertain, resulting in possible migration between fog servers. In order to evaluate the impact of this uncertainty on decision-making for offloading and resource allocation, we formulate the task offloading problem as a Multi-Stage Stochastic Programming (MSSP), with aim of minimizing the total latency of offloading to determine whether to offload or not, how much workload to offload, how much computing resource to allocate, as well as whether to migrate or not. Different from the previous MSSP based work focusing on the workload assignment only, the proposed MSSP examines joint decisions of offloading, resource allocation, and migration, advancing the understanding of the interactions among these decisions. Furthermore, to reduce the computational complexity of MSSP, we design an efficient sub-optimal offloading policy based on Sample Average Approximation, called SAA-MSSP. We conduct extensive simulation experiments to validate the effectiveness of SAA-MSSP. The results show that SAA-MSSP can converge to a near-optimal solution quickly.

中文翻译：

---

雾启用物联网电子健康的基于多阶段随机编程的卸载策略

为了满足 IoT-eHealth 的低延迟和实时监控需求，雾计算被设想为在网络边缘提供弹性计算资源的关键技术。在这种情况下，eHealth 设备可以将收集的医疗保健数据或计算昂贵的任务卸载到附近的雾服务器。但是，eHealth 设备的移动性可能会使它们与雾服务器之间的连接不确定，从而导致雾服务器之间可能发生迁移。为了评估这种不确定性对卸载和资源分配决策的影响，我们将任务卸载问题表述为多阶段随机规划（MSSP），旨在最小化卸载的总延迟以确定是否卸载与否，要卸载多少工作负载，要分配多少计算资源，以及是否迁移。与之前基于 MSSP 的工作仅关注工作负载分配不同，拟议的 MSSP 审查卸载、资源分配和迁移的联合决策，促进对这些决策之间相互作用的理解。此外，为了降低 MSSP 的计算复杂度，我们设计了一种基于样本平均近似的高效次优卸载策略，称为 SAA-MSSP。我们进行了大量的模拟实验来验证 SAA-MSSP 的有效性。结果表明，SAA-MSSP 可以快速收敛到接近最优的解。增进对这些决策之间相互作用的理解。此外，为了降低 MSSP 的计算复杂度，我们设计了一种基于样本平均近似的高效次优卸载策略，称为 SAA-MSSP。我们进行了大量的模拟实验来验证 SAA-MSSP 的有效性。结果表明，SAA-MSSP 可以快速收敛到接近最优的解。增进对这些决策之间相互作用的理解。此外，为了降低 MSSP 的计算复杂度，我们设计了一种基于样本平均近似的高效次优卸载策略，称为 SAA-MSSP。我们进行了大量的模拟实验来验证 SAA-MSSP 的有效性。结果表明，SAA-MSSP 可以快速收敛到接近最优的解。