Modeling for a QoS-efficient real-time video conferencing system in the cloud

Recently on-premises deployed real-time video conferencing (VC) systems have been facing the growing resource demand from using desktop and mobile devices. To address the cost of upgrading the existing on-promises VC infrastructure, businesses are moving towards cloud-based VC services. However, operating cloud-based VC and maintaining real-time interactive conferencing of audio and video sessions also has a number of challenges including availability, quality of video calls and performance issues. Video conferencing require significant hardware resources and stringent Quality of Service (QoS) requirements in terms of bandwidth, delay, and jitter. This research proposes a viable model for the design and implementation of a cloud-based VC system that meets time-critical requirements. We provide a numerical simulation evaluation, which shows that a relevant methodology can be used to best manage and control a cloud-based VC system to realize benefits while maintaining required level of QoS and performance.