Fog computing and the Internet of Things (IoT) have revolutionized healthcare monitoring systems, enabling real-time health data collection and transmission while overcoming cloud computing limitations. However, efficiently selecting fog nodes for application modules with varying deadline requirements and ensuring adherence to quality of service (QoS) criteria pose significant challenges due to resource constraints and device limitations. In this paper, we present a novel two-layered hierarchical design for fog devices, leveraging cluster aggregation to optimize the selection of fog nodes for healthcare applications. We introduce three efficient algorithms to minimize system latency and reduce energy consumption in fog computing environments. Our proposed model is rigorously evaluated using the iFogSim toolkit and compared with cloud-based and latency-aware model [Mahmud R, Ramamohanarao K, Buyya R in ACM Transactions on Internet Technology.19, 2018, 10.1145/3186592]. In four distinct network topologies, our model exhibits an average latency reduction of at least 87% and energy consumption reduction of at least 76% when compared to the Cloud-based model. Similarly, when compared to the Latency-aware model proposed in [Mahmud R, Ramamohanarao K, Buyya R in ACM Transactions on Internet Technology. 19, 2018, 10.1145/3186592], our model showcases a minimum reduction of 43% in average latency and 27% in energy consumption. Our contribution lies in addressing the complexity of selecting fog nodes for application modules with diverse deadline requirements, while ensuring QoS. This work advances the field of real-time healthcare monitoring systems, promising substantial improvements in efficiency and effectiveness.

雾计算和物联网 (IoT) 彻底改变了医疗保健监控系统，实现了实时健康数据收集和传输，同时克服了云计算的局限性。然而，由于资源限制和设备限制，为具有不同期限要求的应用模块有效地选择雾节点并确保遵守服务质量（QoS）标准提出了重大挑战。在本文中，我们提出了一种新颖的雾设备两层分层设计，利用集群聚合来优化医疗保健应用的雾节点选择。我们引入了三种有效的算法来最大限度地减少雾计算环境中的系统延迟并降低能耗。我们提出的模型使用 iFogSim 工具包进行了严格评估，并与基于云和延迟感知的模型进行了比较 [Mahmud R, Ramamohanarao K, Buyya R in ACM Transactions on Internet Technology.19, 2018, 10.1145/3186592]。在四种不同的网络拓扑中，与基于云的模型相比，我们的模型平均延迟减少至少 87%，能耗减少至少 76%。同样，与 ACM Transactions on Internet Technology 中的 [Mahmud R、Ramamohanarao K、Buyya R] 中提出的延迟感知模型相比。 2018 年 10 月 19 日，10.1145/3186592]，我们的模型显示平均延迟至少减少了 43%，能耗至少减少了 27%。我们的贡献在于解决了为具有不同期限要求的应用模块选择雾节点的复杂性，同时保证了 QoS。这项工作推动了实时医疗保健监控系统领域的发展，有望大幅提高效率和有效性。