A Study of Effect of Architectural Design on Quality of Service of a Live Streaming Application with Multiple Endpoints over LTE Network

Abstract

The number of streaming service providers has been increasing dramatically every year. Hence, users may prefer to publish their stream to multiple service endpoints simultaneously to increase visibility. However, most service providers prefer to monopolize their services. Hence, a study of a suitable architectural design of a streaming service that supports multiple streaming endpoints has not gained lots of attention. In this study, the effect of adopting different architectural design on developing a live streaming service over LTE network which can supports multiple streaming endpoints are investigated. Two major designs are selected which are a selective forwarding unit based architecture, and a non-selective forwarding unit based architecture. The results suggest that a selective forwarding unit architecture has an advantage over a non-selective forwarding unit based architecture on keeping overall average streaming end-to-end delay to be minimum., while a fluctuation in an end-to-end delay occurs in a non-selective forwarding unit based architecture in our experiment testbed. The results, discussions, and suggestions on future studies are given at the end of this study.