Ines Houidi

A Distributed Virtual Network Mapping Algorithm

Network visualization is a promising concept to diversify the future Internet architecture into separate virtual networks (VN) that can support simultaneously multiple network experiments, services and architectures over a shared substrate network. To take full advantage of this paradigm this paper addresses the challenge of assigning VNs to the underlying physical network in a distributed and efficient manner. A distributed algorithm responsible for load balancing and mapping virtual nodes and links to substrate nodes and links has been designed, implemented and evaluated. A VN mapping protocol is proposed to communicate and exchange messages between agent-based substrate nodes to achieve the mapping. Results of the implementation and a performance evaluation of the distributed VN mapping algorithm using a multi-agent approach are reported.

Virtual network provisioning across multiple substrate networks

This paper addresses the provisioning of virtual resources in future networks relying on the Infrastructure as a service principle. Exact and heuristics optimization algorithms for the provisioning of virtual networks involving multiple infrastructure providers are presented. The study assumes the emergence of new actors such as virtual network providers acting as brokers requesting virtual resources on behalf of users. Resource matching, splitting, embedding and binding steps required for virtual network provisioning are proposed and evaluated. Splitting of the virtual network provisioning request across multiple infrastructure providers is solved using both max-flow min-cut algorithms and linear programming techniques. Virtual network embedding is formulated and solved as a mixed integer program with the aim of decreasing embedding cost for infrastructure providers while increasing the acceptance ratio of requests. Performance of the splitting and embedding algorithms is reported.

Adaptive virtual network provisioning

In the future, virtual networks will be allocated, maintained and managed much like clouds offering flexibility, extensibility and elasticity with resources acquired for a limited time and even on a lease basis. Adaptive provisioning is required to maintain virtual network topologies, comply with established contracts, expand initial allocations on demand, release resources no longer useful, optimize resource utilization and respond to anomalies, faults and evolving demands. In this paper, we elaborate on adaptive virtual resource provisioning to maintain virtual networks, allocated initially on demand, in response to a virtual network creation request. We propose a distributed fault-tolerant embedding algorithm, which relies on substrate node agents to cope with failures and severe performance degradation. This algorithm coupled with dynamic resource binding is integrated and evaluated within a medium-scale experimental infrastructure.

Cloud Service Delivery across Multiple Cloud Platforms

The paper presents work-in-progress on the cloud service provisioning across multiple cloud providers. The work assumes the emergence of Cloud Brokers between customers and cloud providers. The brokers split user requests and ensure provisioning from multiple providers. An exact splitting algorithm is developed to efficiently split the cloud requests among the multiple cloud platforms with the aim of decreasing the cost for customers. This splitting is formulated as a Mixed Integer Program and this is combined with Open Flow and NOX technologies that achieve flow based inter-cloud networking. A new controller module is developed and integrated in NOX to configure the Open Flow switches for inter-cloud path establishments.

Virtual Resource Description and Clustering for Virtual Network Discovery

This paper explores description and clustering techniques for virtual networks provisioning from shared physical resources. The contribution consists of a virtual resource description schema to specify properties and relations between virtual resources and a conceptual clustering technique to facilitate matching and discovery. Conceptual clustering provides a hierarchical classification of virtual resources and concept descriptions for clusters. Performance results benefits of conceptual clustering for resource matching are reported.

A Distributed and Autonomic Virtual Network Mapping Framework

This paper addresses the challenge of assigning virtual networks, through network virtualisation, to the underlying physical network in a distributed and efficient manner. The paper reports on an implementation and evaluation of a distributed and autonomic framework with algorithms responsible for mapping virtual nodes and links to the physical resources. A virtual network (VN) mapping protocol is proposed for exchange of messages between autonomic substrate nodes. Results of the implementation and a performance evaluation of the distributed and autonomic VN mapping using a multi-agent approach are provided.

SDN for Inter Cloud Networking

This paper presents a Software Defined Network (SDN) controller, called Cloud Networking Gateway (CNG) Manager, that enhances networking of distributed cloud resources and provides authorized customers with the ability to control and configure networks. The CNG Manager interconnects virtual machines acquired from distributed heterogeneous resources and services from multiple providers using a generic gateway. The cloud networking gateways are managed by the CNG Manager that handles allocation and configuration of the gateways according to connectivity requirements. Our implementation of the CNG Manager and the gateway is combined with an exact splitting algorithm and integrated in a cloud services provisioning system. The CNG Manager and the associated gateway extend the current state of the art by applying the SDN principle to connectivity control of distributed and networked cloud resources.

Design, Implementation and Evaluation of Virtual Resource Description and Clustering Framework

This paper presents an approach to speed up and enhance matching of virtual network requests to available resources in virtual network provisioning frameworks. The method consists of introducing a weight or score expressing the importance of the resources, their attributes and the values taken by these attributes. The scores are obtained through statistical analysis of the requests for virtual network resources. Previous methods treat resources equally and experience longer delays and lower efficiency during the matching process. They were originally not designed for virtual network provisioning and the proposed method in this work aims at addressing their weaknesses in scalability, in resource representation and incremental updates. To highlight this new method, a functional comparison with these previous techniques is proposed. Evaluation results of the score based clustering and matching algorithm show improved scalability and performance in clustering efficiency and matching delays for virtual network provisioning.

Building virtual networks across multiple domains

This paper presents a platform for virtual network (VN) provisioning across multiple domains. The platform decomposes VN provisioning into multiple steps to address the implications of limited information disclosure on resource discovery and allocation. A new VN embedding algorithm with simultaneous node and link mapping allows to assign resources within each domain. For inter-domain virtual link setup, we design and realize a signaling protocol that also integrates resource reservations for providing virtual links with Quality-of-Service guarantees. Experimental results show that small VNs can be provisioned within a few seconds.

RSforEVN: Node reallocation algorithm for virtual networks adaptation

This paper addresses the dynamic adaptation of already embedded virtual network (VN) resources to respond to increasing network services demands and load on network nodes. The proposed algorithm focuses on the virtual nodes, of the embedded VN, requiring more resources. The adaptation scheme goes beyond the reallocation of the virtual nodes by considering their topological neighborhood. The proposed algorithm outperforms existing approaches in reallocation cost and in execution time (or convergence time) for larger graphs.