Real-Time FaaS: serverless computing for Industry 4.0
Real-Time FaaS: serverless computing for Industry 4.0
复制标题
实时 FaaS：工业 4.0 的无服务器计算
DOI：
--
复制
发表时间：
2023
影响因子：
1.3
通讯作者：
M. Cinque
中科院分区：
文献类型：
--
作者：
M. Cinque
近年来，我们见证了服务计算和云技术在工业应用中的出现，带来了有趣的创新和新的引人注目的挑战。例如，在汽车领域，有将电子控制单元（ecu）整合为同一电路板上的虚拟机的计划。或者，在工业4.0 （I4.0）中，研究人员和从业者正在处理通过将硬件元素与边缘云原生组件软件化来使工厂车间可编程的挑战[2,3]。因此，典型的云设置虚拟化技术开始在这样的工业场景中被采用，以整合同一硬件上的多个应用程序，主要是为了减小尺寸、重量、功耗和成本（SWAP-C）。虚拟化还满足在同一设备上运行具有不同临界级别的应用程序的需求，以实现所谓的混合临界系统（MCS）[4]。这可以使，例如，在同一板上运行一个驱动线控ECU与信息娱乐并排。为了在应用程序开发、部署和操作（即所谓的devops）方面全面接受行业中的云范式，在工业环境中采用云原生解决方案（如容器化和无服务器计算）的想法也正在兴起。由于大量采用容器和微服务来开发企业应用[6]，无服务器计算成为部署云应用程序的最新范例。它是软件行业创造的一个术语，用来描述一种编程模型，其中代码片段可以在云中运行，而无需对代码运行的资源进行任何控制或了解。这并不意味着服务器被移除，而是它们从用户的角度“消失”了，用户不再需要支付租用服务器的费用，而是将自己的代码作为服务来运行。当函数用作部署(和
In recent years, we are witnessing the advent of service computing and cloud technologies in industrial applications, with intriguing innovations and novel compelling challenges. For instance, in the automotive, there are initiatives for consolidating electronic control units (ECUs) as virtual machines on the same board [1]. Or, in the Industry 4.0 (I4.0), researchers and practitioners are dealing with the challenge of making the factory floor programmable by softwarizing hardware elements with edge cloud-native components [2,3]. Virtualization technologies typical of cloud settings are hence starting to be adopted in such industrial scenarios, to consolidate multiple applications on the same hardware, mainly to reduce Size, Weight, Power and Cost (SWAP-C). Virtualization also serves the need of running, on the same device, applications with differentiated criticality levels, to realize so-called Mixed-Criticality Systems (MCS) [4]. This can enable, for instance, to run on the same board a Driveby-wire ECU side by side with the infotainment. To fully embrace the cloud paradigm in the industry, in terms of also application development, deployment and operations (the so-called devops), it is also emerging the idea of adopting cloud-native solutions, such as containerization and serverless computing, in industrial settings [5]. Serverless computing is a recent paradigm for the deployment of cloud applications, due to the large adoption of containers and microservices for the development of enterprise applications [6]. It is a term coined by software industry to describe a programming model where code snippets can run in the cloud without any control or knowledge on the resources onwhich the code run. It does notmean that servers are removed, rather they “disappear” from the user perspective,who is no longer billed to rent a server, but to run his code as a service. When functions are used as deployment (and