Adaptive virtualization for AI-enabled Cloud-edge Continuum (CloudSkin)

截至目前，80%的数据处理和分析发生在云数据中心，只有20%的处理发生在边缘。这种对边缘资源的初期利用增加了实现价值的时间，并阻止了业务流程、决策和智能在数据中心之外进行，从而阻止了欧洲在未来几年释放一整套新的机会来服务于欧洲不同的行业和使用案例。为了在未来几年实现欧洲对真正连续体的竞标，CloudSkin致力于构建认知云连续体平台，主要创新有三：1.CloudSkin平台将利用AI/ML来优化工作负载、资源、能量和网络流量，以快速适应应用行为和数据可变性的变化，在快速变化的条件下重新配置云和边缘之间的“甜蜜点”；2.CloudSkin平台还将帮助用户实现跨云边缘连续体的“堆栈同一性”，从而使在数据中心运行的相同(传统)软件堆栈(例如，MPI程序)可以在远程边缘无缝运行。在开发新的轻量级、可移植的虚拟化抽象的同时，还将开发新的机密抽象来保护正在使用的数据；以及3.CloudSkin还将帮助准备必要的基础设施，以将新的虚拟化执行抽象集成到虚拟资源连续体中，特别是对于那些由具有快速数据访问和共享要求的小任务组成的云边缘应用程序。基础设施将公开相关的控制旋钮，以在CloudSkin平台中基于AI/ML的编排平面的帮助下实现资源的动态重新配置。总而言之，上述创新是我们设想的新的“云和边缘认知连续体”的战略要素。

As of today, 80% of the data processing and analysis occurs in cloud data centers, and only 20% of processing occurs at the edge. This incipient exploitation of edge resources increases time to value and prevents business processes, decisions, and intelligence to be taken outside of the data center, which prevents Europe to unlock an entire set of new opportunities to serve different industries and use cases in Europe in the next years. To help to materialize the European bid on a true continuum in the next few years, CloudSkin pursues to build a cognitive cloud continuum platform with three main innovations: 1. The CloudSkin platform will leverage AI/ML to optimize workloads, resources, energy, and network traffic for a rapid adaptation to changes in application behavior and data variability, re-configuraing the "sweet spot" between the cloud and the edge in the face of the rapid varying conditions; 2. The CloudSkin platform will also help users to achieve “stack identicality” across the Cloud-edge continuum, whereby the same (legacy) software stacks (e.g., MPI programs) running in data centers can seamlessly run at remote edges. The development of a new lightweight, portable virtualizaion abstraction will be paired with the development of new confidential abstractions to protect data while it is in use; and 3. CloudSkin will also contribute to prepare the needed infrastructure to integrate the new virtualized execution abstractions into the virtual resource continuum, particularly, for those Cloud-edge applications composed of small tasks with fast data access and sharing requirements. The infrastructure will expose the relevant control knobs to enable dynamic reconfiguration of resources as assisted by the AI/ML-based orchestration plane in the CloudSkin platform. Altogether, the above innovations are the strategic elements of what we envision as the new “cognitive continuum for the cloud and edge".