Stuart Clayman

As cloud computing becomes more predominant, the problem of scalability has become critical for cloud computing providers. The cloud paradigm is attractive because it offers a dramatic reduction in capital and operation expenses for consumers.

This paper addresses the problem of managing highly dynamic network and service environments, where virtual nodes and virtual links are created and destroyed depending on traffic volumes, service requests, or high-level goals such as reduction in energy consumption. This problem will be one of the main technical challenges to be faced in the evolution towards Future Networks (FN). Emerging paradigms such as Software Defined Networks (SDN) and Network Function Virtualization (NfV) are concrete steps towards infrastructures where network functions and services will be executed as applications in ensembles of virtual machines (VMs) hosted in pervasive standard hardware resources located across a network. The paper argues that in order to manage these virtual infrastructures there is a need to introduce high-level systems orchestration. The paper describes an architecture based on an orchestrater that ensures the automatic placement of the virtual nodes and the allocation of network services on them, supported by a monitoring system that collects and reports on the behaviour of the resources. The orchestrater manages the creation and removal of the virtual nodes, as well as configuring, monitoring, running and stopping software on them. As a proof of these concepts, a distributed orchestrater prototype has been designed, implemented and tested with the results of different placement algorithms presented.

Service Clouds are a key emerging feature of the Future Internet which will provide a platform to execute virtualized services. To effectively operate a service cloud there needs to be a monitoring system which provides data on the actual usage and changes in resources of the cloud and of the services running in the cloud. We present the main aspects of Lattice, a new monitoring framework, which has been specially designed for monitoring resources and services in virtualized environments. Finally, we discuss the issues related to federation of service clouds, and how this affects monitoring in particular.

The heterogeneous nature of the applications, technologies and equipment that today's networks have to support has made the management of such infrastructures a complex task. The Software-Defined Networking (SDN) paradigm has emerged as a promising solution to reduce this complexity through the creation of a unified control plane independent of specific vendor equipment. However, designing a SDN-based solution for network resource management raises several challenges as it should exhibit flexibility, scalability and adaptability. In this paper, we present a new SDN-based management and control framework for fixed backbone networks, which provides support for both static and dynamic resource management applications. The framework consists of three layers which interact with each other through a set of interfaces. We develop a placement algorithm to determine the allocation of managers and controllers in the proposed distributed management and control layer. We then show how this layer can satisfy the requirements of two specific applications for adaptive load-balancing and energy management purposes.

The use of the Lattice monitoring framework as a fundamental part of a overlay management system for virtual networks is presented. Lattice has been specially designed for monitoring resources and services in virtualized environments, including virtual networks. Monitoring of virtualized resources and services has many criteria which are not relevant for monitoring systems that are used for traditional fixed resources. We present the main aspects of the framework together with details of measurement transmission and meta-data encoding. Finally, the use of the Lattice framework for monitoring virtual machines executing under hypervisor control is presented.