Hongyu Hu

A west-east bridge based SDN inter-domain testbed

SDN is considered to be a promising way to re-architect the Internet. However, the Internet is managed by owners of different administrative domains, so the centralized control model of SDN must be extended to account for inter-domain traffic. Thus, this article proposes a WE-Bridge mechanism to enable different SDN administrative domains to peer and cooperate. Based on WE-Bridge, we further designed two innovative inter-domain routing applications as use cases. To verify our design, we implemented the WE-Bridge and the two use cases by building an international testbed on which WE-Bridge, together with the two use cases, are deployed. The testbed is composed of four SDN networks: CERNET, Internet 2 in USA, CSTNET, and SURFnet.

OpenRouter: OpenFlow extension and implementation based on a commercial router

By analyzing challenges of current OpenFlow in production network, we propose three extensions of OpenFlow about FlowTable, control mode and OpenFlow protocol. Based on these extensions, a commercial OpenFlow-enabled router, named OpenRouter, is designed and implemented using only available and existing hardware in a commercial router. OpenRouter brings the abilities of control openness, integration of inside/outside protocols, and flexibility of OpenFlow message structure, low-cost implementation and deployment. We expect OpenRouter may accelerate the large-scale application and deployment of OpenFlow in production network.

ASIC: an architecture for scalable intra-domain control in OpenFlow

Currently, the architecture of network device is closed which is detrimental to network innovation. Software defined networking decouples the vertically coupled architecture and reconstructs the Internet as a modular structure. The idea of software defined networking is widely accepted. OpenFlow, a typical instance of the software defined networking, has been deployed by many universities and research institutions all over the world. With the increasing scale of deployment, the poor scalability of the OpenFlow centralized control mode becomes more and more obvious. To solve this scalability problem, this paper adopts the idea of load balance and proposes an architecture for the scalable intra-domain control named ASIC in OpenFlow. ASIC balances all the data flow initialization requests to several physical controllers in an OpenFlow network, and then, those requests are processed with a shared global network view in a parallel manner. ASIC also builds a data cluster for the global network view. By this way, the scalability problem in the intra-domain control plane could be completely solved. At the end of this paper, the emulation shows the feasibility of ASIC.

Networking as a Service: a Cloud-based Network Architecture

With the rapid development and integration of the Internet, wireless communication network and the Internet of Things, the Internet faces many challenges as a bearer network: a large volume of information exchange, multi-level QoS and smoothly switching multiple access protocols. The Internet should be able to provide a variety of network capacities in a more dynamic and on-demand way, not just limited network resource provision through virtualization. The elastic network is expected to adapt to network changes by enabling network protocols selection and combination dynamically. Cloud computing illustrates a new Internet-based model of IT resources (hardware, software, data) provision, delivery and consumption as a service. Therefore, networking as a service can provide guaranteed quality of service and good quality of experience to users who do not care about any network configuration and network management. In this paper, we propose a novel idea of networking as a service by combining the service provision model of cloud computing with the openness of the network protocol. The related conception and stakeholders of networking as a service is depicted. Cloud-based network architecture is design to present the provision, delivery and consumption of networking as a service and discuss the key features of cloud-based network. Finally, a prototype of cloud-based network is implemented by extending OpenFlow architecture.

A quick survey on selected approaches for preparing programmable networks

Currently, new protocols or architectures related to core network layer or network forwarding equipment are hard to deploy. And the core network evolves slowly. To solve this problem, various programmable Internet architectures and approaches are proposed. Programmable networks allow network researchers (not only the equipment vendors like Cisco and Juniper) to program and manage their customized architectures or protocols. This paper firstly describes the ossification with the current Internet architecture. And then it analyzes several most representative approaches for programmable networks with their mechanisms, advantages, and shortcomings. By the analysis above, this paper at last discusses the future research trends and gives a detailed description of the key issues in the future research of the programmable networks.

VCP: A virtualization cloud platform for SDN intra-domain production network

Software Defined Networking (SDN) is considered as a promising method to re-construct the architecture of Internet. At present, the programs of network protocols are mixed together in SDN controller. However, in the production network, an isolated network environment with private resources is needed for each network protocol running on the same SDN controller. It is therefore necessary to design a practical virtualization cloud platform on the SDN network operating system (NOS). In this paper, we introduce a virtualization cloud platform for SDN production network. A prototype is implemented and two cases are performed to show the feasibility and the effectiveness of our proposed framework.

TUNOS: A novel SDN-oriented networking operating system

Software defined networking (SDN) has been a promising network architecture to improve the openness of network and the diversity of protocols. Network operating system (NOS) in SDN is a key component for the abstraction of infrastructure and feature-rich protocols, which provide a general control plane and a unified protocol operating view. SDN-oriented NOS design requires not only the control shift from the specific network functions and vendor-dependent implementation in a traditional control plane to a general control functions, but also the extension of abstraction from computing process in a computer operating system to forwarding operation. To address this, we present a novel network operating system-TUNOS from the view of device control capacities and network control capacities. For the purpose of scalability, robustness, flexibility and high-performance, TUNOS provides open device management, cognitive network status, global network view, virtual forwarding space, and APP context management. General network control APIs are designed for user-friendly network programming.

Internetworking with SDN using existing BGP

The research on transiting the existing networks to SDN (Software defined networking) just starts. We propose to continue using the BGP (Border Gateway Protocol) and the legacy BGP border routers for the SDN network and connect the SDN network with legacy IP networks in this paper. The experiments we carried out preliminary proved our design.

BTSDN: BGP-based transition for the existing networks to SDN

Currently, the architecture of network device is closed. This is detrimental to the network inno vation. Software defined networking (SDN) [1] decouples the vertically coupled architecture, and reconstructs the Internet as a modular structure. The idea of SDN is widely accepted by both of the academic and industry researchers, and is considered as a promising way to re-architect the Internet. OpenFlow as a typical instance of the SDN has been deployed by many universities and research institutions all over the world. However, the research and technologies on transitioning the existing networks to SDN are not mature. So this paper takes the instance OpenFlow for example and proposes a simple and practical BGP (Border Gateway Protocol) based transition solution named BTSDN. BTSDN fully explores the characteristics of OpenFlow network, proposes to continue using the current BGP protocol, and retains the legacy BGP border routers to connect the OpenFlow network with the rest of Internet. The experiment at the end of this paper preliminary verifies the feasibility of BTSDN.

UNA: a new internet architecture for user-level multi-homing and mobility

Host multi-homing and mobility in the Internet have become a trend due to the widespread wireless services and broad access methods. Meanwhile, with more and more devices join in the Internet, it will be common that one user has multiple devices online. So users will also desire to be multi-homed and mobile across not only addresses but also devices. To provide such support, we present a new network architecture called UNA (User-centric Network Architecture) to achieve user-oriented communications. UNA will make communications completely independent of data delivery, which offers the basis of both network and user level multi-homing and mobility. We first show the general design of UNA including the introduction of new namespaces. Then UNA-I is presented as an illustration to complete the architecture with mapping, resolution and indirection schemes. At last we describe the instantiation of UNA under LTE framework with some security enhancements. However our work is far from complete and in this paper we focus on expressing the new idea.