SDN-Based Virtual Machine Management for Cloud Data Centers

Abstract

Abstract-Software-Defined Networking (SDN) is an emerging paradigm to logically centralize the network control plane and automate the configuration of individual network elements. At the same time, in Cloud Data Centers (DCs), even though network and server resources converge over the same infrastructure and typically under a single administrative entity, disjoint control mechanisms are used for their respective management.In this paper, we propose a unified server-network control mechanism for converged ICT environments. We present a SDNbased orchestration framework for live Virtual Machine (VM) management where server hypervisors exploit temporal network information to migrate VMs and minimize the network-wide communication cost of the resulting traffic dynamics. A prototype implementation is presented and Mininet is used to evaluate the impact of diverse orchestration algorithms.

An SDN orchestrator for cloud data center: System design and experimental evaluation

“…A prototype is presented for live VM management that measures temporal load information to made migration decisions aimed at minimizing the network‐wide communication cost of the resulting traffic dynamics. Similar to our work, in a previous study, authors present an SDN‐based prototype that not only controls the network, but also VMs and hypervisors. This work differentiates in the joint provision of VMs along with a data delivery paths to convey VM data with better than best‐effort quality as result of traffic load estimations.…”

“…Despite being developed with SDN, these solutions exploit topology discovery, statistic collection services given by OF to develop network applications (e.g., detection of link failures and topology changes) without interacting with Hypervisors. In another study, an SDN‐based framework is proposed for the synergistic network and cloud resource management in cloud DCs. A prototype is presented for live VM management that measures temporal load information to made migration decisions aimed at minimizing the network‐wide communication cost of the resulting traffic dynamics.…”

“…This work differentiates in the joint provision of VMs along with a data delivery paths to convey VM data with better than best‐effort quality as result of traffic load estimations. While in another study, the traffic loads given by VM data flows are basic average values, in this work we leverage on the weighted moving average scheme that considers history values of the load to have more reliable traffic estimations and thus well‐considered data delivery path decisions.…”

“…However, a novel usage of Northbound Interface is necessary to fully exploit the potential innovation offered by SDN and to enable the effective interworking between network controllers and application layer systems (i.e., hypervisors, cloud management platforms) . Indeed, ever‐changing information about the availability status of the network can be conveyed to cloud systems for steering selections of computing and storage resources, coordinating cloud service deployments (e.g., VM provisioning) with the establishment of data delivery paths and, ultimately, for dynamically addressing different VM traffic requirements in cloud applications …”

Management and Orchestration of Network Slices in 5G, Fog, Edge, and Clouds

“…Virtualization technology has been the cornerstone of the resource management and optimization in Cloud data centers for the last decade. Many research proposals have been expressed for VM placement and Virtual Machine (VM) migration to improve utilization and efficiency of both physical and virtual servers [15]. In this section, we focus on the state of the art network-aware VM/VNF management in line with the aim of the report, i.e., network slicing management for SDCs.…”