AI-Enhanced Offloading in Edge Computing: When Machine Learning Meets Industrial IoT
AI-Enhanced Offloading in Edge Computing: When Machine Learning Meets Industrial IoT
复制标题
边缘计算中的人工智能增强卸载：当机器学习遇到工业物联网时
DOI：
10.1109/mnet.001.1800510
复制
发表时间：
2019
期刊：
影响因子：
9.3
通讯作者：
Yue Yanlin
中科院分区：
文献类型：
--
作者：
Sun Wen;Liu Jiajia;Yue Yanlin
工业物联网（IIoT）通过结合人工智能（AI）和大数据技术实现智能工业运营。支持AI的框架通常需要即时和私有的基于云的服务来处理和聚合制造数据。因此，将智能集成到边缘计算中无疑是一个有前途的发展趋势。然而，边缘智能给边缘服务器带来了异构性，不仅在计算能力方面，而且在服务准确性方面。大多数关于边缘计算中卸载的工作都集中在寻找功率延迟权衡，忽略了边缘服务器提供的服务准确性以及IIoT设备所需的准确性。在这方面，在本文中，我们将介绍一种具有协作边缘和云计算的智能计算架构。基于该计算架构，提出了一种AI增强的卸载框架，以实现服务准确性最大化，该框架将服务准确性视为除延迟之外的新度量，并智能地将流量分发到边缘服务器或通过适当的路径分发到远程云。一个案例研究进行迁移学习，以显示所提出的框架的性能增益。
The Industrial Internet of Things (IIoT) enables intelligent industrial operations by incorporating artificial intelligence (AI) and big data technologies. An AI-enabled framework typically requires prompt and private cloud-based service to process and aggregate manufacturing data. Thus, integrating intelligence into edge computing is without doubt a promising development trend. Nevertheless, edge intelligence brings heterogeneity to the edge servers, in terms of not only computing capability, but also service accuracy. Most works on offloading in edge computing focus on finding the power-delay trade-off, ignoring service accuracy provided by edge servers as well as the accuracy required by IIoT devices. In this vein, in this article we introduce an intelligent computing architecture with cooperative edge and cloud computing for IIoT. Based on the computing architecture, an AI enhanced offloading framework is proposed for service accuracy maximization, which considers service accuracy as a new metric besides delay, and intelligently disseminates the traffic to edge servers or through an appropriate path to remote cloud. A case study is performed on transfer learning to show the performance gain of the proposed framework.