Analyzing resource distribution over a real-world large-scale virtual content infrastructure

• Main Authors: Endo, Patricia Takako, Loomba, Radhika, Quinn, Ruth, Filelis-Papadopoulos, Christos K., Giannoutakis, Konstantinos M., Gravvanis, George A., Tzovaras, Dimitrios, Willis, Peter, Svorobej, Sergej, Byrne, James, Lynn, Theo
• Format: Conference Proceeding
• Language: English
• Subjects: Bandwidth; Computational modeling; Content distribution networks; Engines; IP networks; Quality of service; Servers
• ISSN: 2642-7389
• DOI: 10.1109/ISCC47284.2019.8969755

Communication service providers (CSPs) face competitive pressure to increase infrastructure utilization and reduce operational costs while at the same time maximize bandwidth and maintain quality of service for end users. Content Distribution Networks (CDNs) are widely used to achieve these goals by optimally distributing content to cache servers at the edge, access and core networks. More recently, virtualization and cloud computing are being used to deploy and utilize virtual Content Delivery Networks (vCDNs) to reduce costs and increase elasticity while avoiding performance, quality, reliability and availability limitations that characterize traditional CDNs. In order to study the effectiveness of virtual cache placements and optimal distribution over a real-world large-scale vCDN infrastructure, we model and simulate BT's network using a novel parallel simulation framework. Results show that virtual cache placement impacts on the number of accepted requests, resource consumption (compute and network), and end-user network latency. We also present a trade-off analysis between infrastructure provider utility and service customer utility to quantity the number and distribution of these virtual cache placements and to determine the optimal number of virtual cache servers that should be deployed.