NeTS: Small: Intelligent Optical Networks using Virtualization and Software-Defined Control

点击翻译按钮获取中文摘要

Software-defined networking (SDN) is a promising paradigm that has the potential to enable Internet Service Providers (ISPs) to achieve a high level of network automation and therefore significant cost savings. Indeed software-defined wide area networks (SD-WANs) are emerging in industry and are projected to account for 25 percent of WAN traffic by 2021. However, many challenges remain. The networks of large ISPs such as AT&T are complex, and most Internet traffic traverses multiple network domains. It is highly desirable, then, to extend the software control paradigm to enable fast, efficient, cost effective end-to-end provisioning of services and resources over heterogeneous, multi-domain networks in an integrated and unified way. The goal of this project is to address research challenges in this area, leveraging SDN and investigating novel strategies for expediting efficient data transfer across the fiber optic backbone networks underlying the Internet. A unified network architecture for a software defined optical network (SDON) will be developed that features: (1) End-to-end provisioning of services, and (2) Expediting data transfers over multiple domains that use heterogeneous transport layer technologies using inter-domain tunnels. SDONs will usher in virtualization and intelligence as the new features of future networks. The project will explore different strategies for dynamic resource allocation including the creation and use of virtual transport links (VTL) and associated bandwidth-on-demand (BoD) techniques. The project will also explore a Resource Delayed Release (RDR) strategy to reduce the dynamic service provisioning time and multi-domain tunnels to expedite data transfers in multi-layer networks involving Optical Transport Network (OTN), Wavelength Division Multiplexing (WDM) and Elastic Optical Networking (EON) layers.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.