Serverless edge computing framework to support delivery of data intensive and latency-sensitive applications in a sustainable manner

边缘计算提供灵活的按需资源和服务，放置在最终用户和设备附近，以满足各种现代应用程序（包括延迟敏感和数据密集型应用程序）的性能要求。随着这些应用程序（例如，支持无服务器的应用程序）的增长，这些资源和服务的广泛使用预计将呈指数级增长，并导致高能耗。为了支持这种增长并以可持续的方式满足这些应用程序的性能需求，仍然需要解决几个挑战，包括在集成运行的应用程序的动态（例如，工作流和工作负载的波动性）的同时，有效地管理能源消耗和资源在可用性和消耗方面的可变性。因此，本项目将能够在满足应用部署和管理约束（如资源配置、工作流结构）的同时，开发无服务器边缘计算平台在时变工作流、工作负载和资源消耗下动态联合优化性能和能耗的新技术。此外，这些技术将允许调整资源及其配置运行时，以优化资源和能源成本，同时满足运行应用程序的性能要求。开发的技术将刺激快速的功能即服务（FaaS）边缘基础设施的发展和采用，并加快新的无服务器应用程序的上市时间。他们将帮助FaaS边缘计算提供商降低运营成本，因为他们将能够最大限度地减少FaaS边缘计算基础设施的部署和运营成本（最大限度地减少资源和能源消耗，自动资源部署和适应）。此外，他们将提供绿色可靠的FaaS边缘计算基础设施，并以可持续的方式向客户提供新的无服务器应用程序。这些新技术将增强FaaS边缘计算基础设施，并将以更强的定位对加拿大ICT市场产生重大影响。

Edge computing offers flexible on-demand resources and services placed in the proximity of end users and devices to meet performance requirements of a wide range of modern applications (including latency-sensitive and data-intensive applications). With the growth of these applications (e.g., serverless enabled applications), the extensive use of these resources and services is anticipated to grow exponentially and result in high energy consumption. To support this growth and to meet the performance requirements of these applications in a sustainable manner, several challenges still need to be tackled, including the efficient management of the energy consumption and the variability of resources in terms of availability and consumption while integrating the dynamics of the running applications (e.g., volatility of workflows and workloads). Therefore, this project will enable to develop new technologies for dynamic and joint optimization of performances and energy consumption in serverless edge computing platform under time-varying workflows, workloads and resource consumption while meeting the application deployment and management constraints (e.g., resources' configurations, workflows' structures). Moreover, these technologies will allow to adapt resources and their configuration runtime to optimize the resource and energy costs while meeting the performance requirements of running applications. The developed technologies will stimulate rapid Function as a Service (FaaS) edge infrastructure evolution and adoption as well as speed up the time to market for new serverless applications. They will help, the FaaS edge computing providers reducing their OPEX, since they will be able to minimize the FaaS edge computing infrastructure deployment and operational costs (minimize resource and energy consumption, automatic resource deployment and adaptation). Moreover, they will provide green and reliable FaaS edge computing infrastructure and deliver new serverless applications in sustainable manner to customers. These new technologies will enhance FaaS edge computing infrastructure and will have a great impact on the Canadian ICT market with a stronger positioning.