NeTS: Small: Collaborative Research: Revisiting Network QoS in the Cloud-based Era

Trustees Of Boston University, Boston

Investigators

Abstract

Today's Internet is increasingly expected to support resource-intensive interactive applications, exemplified by the emerging wave of virtual, augmented, and mixed reality applications. Unfortunately, today's public Internet offers a best-effort service, which often falls short of meeting the unprecedented resource requirements and desired goals of these applications. This project aims to achieve high Quality of Service (QoS) for these and other applications by judiciously combining existing Internet resources with additional resources drawn from the cloud, while also being cost-effective for end users. The principal investigators will revisit the QoS problem in the context of the emerging cloud infrastructure: the global footprint of data centers (DC) hosted by major cloud providers. These DCs have good network connectivity (both between data centers as well as to the end-users) but are costly to use. Using extensive network measurements, this project will first quantify the potential benefits of using the cloud as an overlay for wide area communication. Further, it will investigate how best-effort Internet paths can be judiciously combined with cloud overlays to provide bandwidth and latency guarantees to applications, using appropriate and economically efficient pricing mechanisms. The project, if successful, will empower the delivery of high QoS to typical, cost-sensitive end-users, potentially enabling transformative networked applications in areas like healthcare and education. Measurement and protocol insights from this project have the potential to benefit network service providers and network researchers, while students will benefit from new course material and hands-on programming projects. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.