Performance Analysis of Real-Time Video Surveillance Application Leveraging Edge and Cloud

With the advent of the Edge and Cloud server in the 5G system, an application needs to be designed to have multiple components, where a part of it (Data Intensive Component (DIC)) is executed on the Edge server while the other part (Computation Intensive Component (CIC)) is executed on the Cloud server. Such deployment of the applications’ components into the Edge and Cloud server opens up opportunities for managing the Edge, Cloud, and network resources. In this work, performance aspects of the simultaneous deployment of a video surveillance application on the Edge and Cloud server are explored. Furthermore, application placement approach at the Edge and Cloud server based on the service time requirement of an application is demonstrated. In addition, an adaptive data transmission mechanism at the Edge server is presented, where the components that run at the Edge server use a scaled-down version of the video based on Initial Analysis, reducing the bandwidth consumption between the Edge server and UE. As a use-case, a surveillance application to identify traffic violations (jumping signal) is deployed. The performance of the simultaneous deployment of video surveillance application (Edge-cloud approach) is evaluated by demonstrating bandwidth preserved and end-to-end bandwidth requirement in comparison with the different Cloud only approaches. To simulate actual deployments, the surveillance application is deployed on an ETSI-compliant 5G MEC testbed with the Edge and Cloud server.