Device-driven On-demand Deployment of Serverless Computing Functions
Trang Quang, Yang Lin Peng · 2020
Due to its merit of elasticity and scalability, server-less computing has been accepted as a fundamental technology block when building the edge-cloud back end of IoT systems. Though existing edge computing frameworks such as AWS Greengrass and Azure IoT Edge have enabled the deployment of serverless computing functions to edge, users must manually start the deployment process in cloud. Such a user-driven push-model approach demands heavy user involvement, which makes it less efficient and sometimes slow to react to dynamic changes in IoT environments. Considering these limitations, we propose a novel scheme that enables device-driven on-demand deployment of serverless computing functions to edge. This solution can allow a large number of IoT devices to utilize edge computing resources in a more responsive and scalable manner. Extensive evaluations have been conducted in AWS, and the obtained performance results on both end-to-end and step-wise operation latency demonstrated that the proposed scheme could successfully and efficiently achieve the desired on-demand deployment with minimal overhead in various scenarios.