A QoS-based Resource Selection Approach for Virtual Networks

The Internet has gained an outstanding success in a short amount of time and it became a critical infrastructure for accessing information and global commerce. With the help of the Internet and its new channels for connecting people a new way of communication has been established. Meanwhile, its great success leads to new limitations. The Internet consists of various network infrastructure providers with different objectives which makes emerging of new technologies or major architectural changes that require cooperative agreements, relatively impractical. While the current Internet architecture is not suitable for supporting many types of applications, network virtualization is considered as promising, yet challenging solution of these limitations. Network virtualization separates the role of traditional internet service providers (ISPs) into physical infrastructure providers (PIPs) responsible for deploying the physical infrastructure and service providers (SPs) offering end-to-end services to end users. Another motivation for network virtualization is the possibility to add value in the virtualization layer aiming to make use of new technologies (e.g. QoS schemes) and customizing existing technologies to adapt specific services (i.e. customizable networks). This provides the means to run multiple virtual networks on a shared substrate network simultaneously while each virtual network is customized for a specific use. The key challenge in virtual networks is the problem of assigning virtual nodes and links to physical resources. Virtual network mapping/embedding consists in finding the most suitable physical nodes and links in the physical network in order to map virtual network requests with certain constraints on virtual nodes and links. The goal of this thesis is to design and implement substrate network resource selection scheme to increase the overall efficiency of the virtual network embedding process and satisfy the set of predefined resource constraints. This work assumes the existence of a virtual infrastructure provider requesting virtual networks from physical infrastructure providers and proposes a selection algorithm based on service-oriented architecture. Our proposed virtual network embedding algorithm is a heuristic algorithm that considers static attributes along with dynamic attributes of nodes and links as well as end-to-end QoS constraints.

[1]  Scott Shenker,et al.  Overcoming the Internet impasse through virtualization , 2005, Computer.

[2]  Rachida Dssouli,et al.  Open virtual playground: Initial architecture and results , 2012, 2012 IEEE Consumer Communications and Networking Conference (CCNC).

[3]  Raouf Boutaba,et al.  Multi-provider service negotiation and contracting in network virtualization , 2010, 2010 IEEE Network Operations and Management Symposium - NOMS 2010.

[4]  Qiang Duan Automatic Network Service Discovery and Selection in Virtualization-Based Future Internet , 2012, Netw. Protoc. Algorithms.

[5]  Ellen W. Zegura,et al.  How to model an internetwork , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[6]  Xiang Cheng,et al.  Virtual network embedding through topology-aware node ranking , 2011, CCRV.

[7]  Raouf Boutaba,et al.  A survey of network virtualization , 2010, Comput. Networks.

[8]  D. Zeghlache,et al.  Virtual Resource Description and Clustering for Virtual Network Discovery , 2009, 2009 IEEE International Conference on Communications Workshops.

[9]  Djamal Zeghlache,et al.  A Distributed Virtual Network Mapping Algorithm , 2008, 2008 IEEE International Conference on Communications.

[10]  Minlan Yu,et al.  Rethinking virtual network embedding: substrate support for path splitting and migration , 2008, CCRV.

[11]  Raouf Boutaba,et al.  Virtual Network Embedding with Coordinated Node and Link Mapping , 2009, IEEE INFOCOM 2009.

[12]  Hongyan Cui,et al.  A virtual network embedding algorithm based on virtual topology connection feature , 2013, 2013 16th International Symposium on Wireless Personal Multimedia Communications (WPMC).

[13]  Anja Feldmann,et al.  Network virtualization architecture: proposal and initial prototype , 2009, VISA '09.

[14]  Jonathan S. Turner,et al.  Efficient Mapping of Virtual Networks onto a Shared Substrate , 2006 .

[15]  Rachida Dssouli,et al.  A multi-service multi-role integrated information model for dynamic resource discovery in virtual networks , 2013, 2013 IEEE Wireless Communications and Networking Conference (WCNC).

[16]  Yunjie Liu,et al.  A new algorithm based on the proximity principle for the virtual network embedding problem , 2011, Journal of Zhejiang University SCIENCE C.