Energy Efficient Placement of ML-Based Services in IoT Networks
Energy Efficient Placement of ML-Based Services in IoT Networks
复制标题
DOI：
10.1109/meditcom55741.2022.9928668
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
M. M. Alenazi-M.;B. Yosuf;S. Mohamed;T. El-Gorashi;J. Elmirghani
中科院分区：
文献类型：
--
作者：
M. M. Alenazi-M.;B. Yosuf;S. Mohamed;T. El-Gorashi;J. Elmirghani
物联网（IoT）正在寻求弥合物理世界和数字世界之间的差距。物联网的主要目标是创建智能环境和自我感知的事物，以帮助促进各种下一代服务。预计连接的传感器/事物将收集大量数据，在传统情况下，这些数据由核心网络中的大型数据中心集中处理，这将不可避免地导致过度的传输功耗以及增加的延迟开销。相反，来自工业界和学术界的研究人员提出了雾计算，以将云的能力扩展到在传感层收集数据的点。通过这种方式，可以托管在物联网传感器中的原始任务不需要一直发送到云端进行处理。在本文中，我们提出了使用混合线性规划（MILP）优化模型在云雾网络上嵌入节能的通用智能服务。我们在框架中利用虚拟化来抽象具有多个互连组件（如深度神经网络（DNN）层）的机器学习（ML）服务。不同的层组成一组通过虚拟链路互连的VM。我们研究了物联网层的单VM分配解决方案和多VM分配解决方案。结果表明，后一种解决方案更为上级，因为可以实现65%的最大功率节省。
The Internet of Things (IoT) is gaining momentum in its quest to bridge the gap between the physical and the digital world. The main goal of the IoT is the creation of smart environments and self-aware things that help to facilitate a variety of next generation services. Huge volumes of data are expected to be collected by the connected sensors/things, which in traditional cases are processed centrally by large data centers in the core network that will inevitably lead to excessive trans-portation power consumption as well as added latency overheads. Instead, fog computing has been proposed by researchers from industry and academia to extend the capability of the cloud right to the point where the data is collected at the sensing layer. This way, primitive tasks that can be hosted in IoT sensors do not need to be sent all the way to the cloud for processing. In this paper, we propose energy efficient embedding of generic smart services over a cloud-fog network using a Mixed Integer Linear Programming (MILP) optimization model. We exploit virtualization in our framework to abstract Machine learning (ML) services that have multiple interconnected components such as Deep Neural Networks (DNN) layers. The different layers are composed into a set of VMs interconnected by virtual links. We study the single VM allocation solution and the multiple VM allocation solution at the IoT layer. The results showed that the latter solution is far more superior as a maximum power saving of 65% can be achieved.