ICE-T:RC: Accelerating NFV Service Function Chain Processing at Scale

网络功能虚拟化（NFV）与软件定义网络（SDN）相结合，有望彻底改变网络。运营商可以根据需要创建、更新或扩展虚拟网络功能（vNFs），构建一系列虚拟网络功能链，形成业务功能链（SFC），引导流量通过SFC，以满足各种策略和业务需求。在新兴的第5代（5G）蜂窝网络技术中，NFV将成为支持动态网络切片和各种服务（从增强型移动宽带到大规模机器类型通信和超可靠低延迟通信）的关键使能技术。该项目提出了一种名为HydraNF的新型分布式并行框架，用于大规模加速NFV业务功能链的处理。HydraNF将通过充分利用多核服务器集群进行动态和弹性扩展，同时解决NFV大规模部署中的性能和自动扩展挑战。提议的项目考虑了扩展和加速NFV服务链的问题，利用服务器上多核以及集群中多服务器的并行性。该项目是在5G蜂窝服务和预期的云无线接入网络、移动边缘云和分组核心的背景下构建的，这些都是对未来5G网络的设想。项目团队将设计一个名为HydraNF的框架，并研究1)VNF行为和SFC规范的模型，2)SFC分解、图构建和映射、放置和规则生成的控制器，3)数据平面引擎，以及4)在欧洲合作伙伴的5G测试平台内实施、评估和集成。这是一项与明尼苏达大学、马德里卡洛斯三世大学（UC3M）和西班牙马德里IMDEA网络研究所的合作研究项目。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Network Function Virtualization (NFV), coupled with Software Defined Networking (SDN), promises to revolutionize networking. Operators can create, update or scale out/in (virtualized) network functions (vNFs) on demand, construct a sequence of vNFs to form a service function chain (SFC) and steer traffic through it to meet various policy and service requirements. In emerging 5th Generation (5G) cellular networking technologies, NFV will be a key enabling technology for support of dynamic network slicing and diverse services ranging from enhanced mobile broadband to massive machine type communications and ultra-reliable low latency communications.This project advances a novel distributed parallelization framework, dubbed HydraNF, for accelerating NFV service function chain processing at scale. HydraNF will be designed to simultaneously tackle the performance and auto-scaling challenges in large scale deployment of NFV by taking full advantage of a cluster of multi-core servers for dynamic and elastic scale-out. The proposed project considers the problem of scaling and accelerating NFV service chains leveraging parallelism across multi-cores on a server as well as across multiple servers in a cluster. The project is framed within the context of 5G cellular service and the intended cloud radio access network, mobile edge clouds, and packet cores that are envisioned for future 5G networks. The project team will design a framework, called HydraNF, and study 1) models for VNF behaviors and SFC specification, 2) a controller for SFC decomposition, graph construction and mapping, placement and rule generation, 3) a data plane engine, and 4) the implementation, evaluation and integration within the European collaborator's 5G testbed. This is a collaborative research project with the University of Minnesota and the Universidad Carlos III de Madrid (UC3M) and IMDEA Networks Institute in Madrid, Spain.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.