Data Centre Optimisation Enhanced by Software Defined Networking

Abstract

Contemporary Cloud Computing infrastructures are being challenged by an increasing demand for evolved cloud services characterised by heterogeneous performance requirements including real-time, data-intensive and highly dynamic workloads. The classical way to deal with dynamicity is to scale computing and network resources horizontally. However, these techniques must be coupled effectively with advanced routing and switching in a multi-path environment, mixed with a high degree of flexibility to support dynamic adaptation and live-migration of virtual machines (VMs). We propose a management strategy to jointly optimise computing and networking resources in cloud infrastructures, where Software Defined Networking (SDN) plays a key enabling role.

Reducing Temporal Interference in Private Clouds through Real-Time Containers

“…Various works exist on controlling performance of distributed cloud services via elasticity and auto-scaling mechanisms [8], [9], intelligent placement strategies [10], [11], possibly including network-awareness [12] and SDN-based approaches [13]. To reduce interferences of co-located services, solutions based on real-time scheduling applied to hypervisors have been proposed, e.g., for the KVM [14] and Xen [15] hypervisors.…”

Software-defined networks for resource allocation in cloud computing: A survey

“…Table 6 compares the techniques according to allocate resources in cloud computing based on the application's user's request. Another work focusing on integrated computing and networking resources to optimize performance in the multi-tenant data centers was proposed in [150]. The optimization process studies the application that requires heavy data transfers and tight time constraints and then monitors the state of the underlying physical resources to match the application's requirements.…”

Virtual Network Functions as Real-Time Containers in Private Clouds

“…Several works exist on controlling performance of distributed cloud services via elasticity and auto-scaling mechanisms [7], [8], intelligent placement strategies [9], [10], possibly including network-awareness [11] and SDN-based approaches [12]. To mitigate interferences of co-located services, real-time scheduling applied to hypervisors has been proposed, e.g., for the KVM [13] and Xen [14] hypervisors.…”