当前位置: X-MOL 学术Softw. Pract. Exp. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Edge-adaptable serverless acceleration for machine learning Internet of Things applications
Software: Practice and Experience ( IF 3.5 ) Pub Date : 2020-12-17 , DOI: 10.1002/spe.2944
Michael Zhang 1 , Chandra Krintz 1 , Rich Wolski 1
Affiliation  

Serverless computing is an emerging event-driven programming model that accelerates the development and deployment of scalable web services on cloud computing systems. Though widely integrated with the public cloud, serverless computing use is nascent for edge-based, Internet of Things (IoT) deployments. In this work, we present STOIC (serverless teleoperable hybrid cloud), an IoT application deployment and offloading system that extends the serverless model in three ways. First, STOIC adopts a dynamic feedback control mechanism to precisely predict latency and dispatch workloads uniformly across edge and cloud systems using a distributed serverless framework. Second, STOIC leverages hardware acceleration (e.g., GPU resources) for serverless function execution when available from the underlying cloud system. Third, STOIC can be configured in multiple ways to overcome deployment variability associated with public cloud use. We overview the design and implementation of STOIC and empirically evaluate it using real-world machine learning applications and multitier IoT deployments (edge and cloud). Specifically, we show that STOIC can be used for training image processing workloads (for object recognition)—once thought too resource-intensive for edge deployments. We find that STOIC reduces overall execution time (response latency) and achieves placement accuracy that ranges from 92% to 97%.

中文翻译:

用于机器学习物联网应用程序的边缘自适应无服务器加速

无服务器计算是一种新兴的事件驱动编程模型,可加速云计算系统上可扩展 Web 服务的开发和部署。尽管与公共云广泛集成,但无服务器计算的使用对于基于边缘的物联网 (IoT) 部署来说还处于起步阶段。在这项工作中,我们提出了 STOIC(无服务器远程操作混合云),这是一种物联网应用程序部署和卸载系统,以三种方式扩展了无服务器模型。首先,STOIC 采用动态反馈控制机制,使用分布式无服务器框架在边缘和云系统之间精确预测延迟和统一调度工作负载。其次,当底层云系统可用时,STOIC 利用硬件加速(例如,GPU 资源)进行无服务器功能执行。第三,STOIC 可以通过多种方式进行配置,以克服与公共云使用相关的部署可变性。我们概述了 STOIC 的设计和实现,并使用真实世界的机器学习应用程序和多层物联网部署(边缘和云)对其进行经验评估。具体来说,我们表明 STOIC 可用于训练图像处理工作负载(用于对象识别)——曾经被认为对于边缘部署来说资源密集型。我们发现 STOIC 减少了整体执行时间(响应延迟)并实现了 92% 到 97% 的放置精度。
更新日期:2020-12-17
down
wechat
bug