SDN/NFV System

We have explored thoroughly packet processing algorithms and implementation mechanism including I/O, memory management, virtualization, multi-core, and heterogeneous hardware, to enable efficient and flexible data path. The operation system with innovative orchestration, resource management, flow migration framework has been proposed to enable dynamical scale-in and scale-out for service function chains both for functions and performance. With these research results, the NFV (Network Functions Virtualization) platform is developed on heterogeneous processors to flexibly provide the high performance security service (IDS, Firewall, etc.) for Multi-Tenants.

SOFIA: Service-Oriented Future Internet Architecture

The initial aim of todayfs Internet, which was created in the 1960s and 1970s, is computing resource sharing in a trust environment through host-to-host communication model. Internet has become a critical worldwide infrastructure with the unprecedented size with 50 years explosive growth due to the development of information and communication technologies. All kinds of social activities have been moved to Internet. These changes bring new challenges to Internet in various aspects, such as traffic growth, mobility support, security, scalability, etc.
We propose a service-oriented future Internet architecture. The Internet is viewed not only as a collection of transport channels but also as a service pool. This fundamental change naturally benefits the Internet in the following aspects.


The State-of-the-art flow recognition techniques suffer from limitations of coarse-grained parallelims, large memory requirements, and limited throughput. The multi-core processor emerges as a promising approach for high-performance and scalalbe flow recognition. However, it imposes great challenges on parallelism and memory consumption. This project will study multi-core processor-based parallel flow recognition (pFlow), with particular focurses on parallel flow recognition architecture on the Multi-core platform, parallel signature matching algorithms and data structures, behavioral modeling and datamining, expeirmentation and evaluation. This project will improve the time/space efficiency of flow recogntion for network applications such as NIDS/NIPS, application-layer flow identifcation, and flow anomlay detection.