International study of the prevalence and outcomes of infection in intensive care units

A Comprehensive Survey of Network Function Virtualization

Annales françaises d'anesthésie et de réanimation

Cloud computing and network slicing are essential concepts of forthcoming 5G mobile systems. Network slices are essentially chunks of virtual computing and connectivity resources, configured and provisioned for particular services according to their characteristics and requirements. The success of cloud computing and network slicing hinges on the efficient allocation of virtual resources (e.g., VCPU and VMDISK) and the optimal placement of virtualized network functions (VNFs) composing the network slices. In this context, this paper elaborates issues that may disrupt the placement of VNFs and virtual machines (VMs). This paper classifies the existing solutions for VM placement based on their nature, whether the placement is dynamic or static, their objectives, and their metrics. This paper then proposes a classification of VNF placement approaches, first, regarding the general placement and management issues of VNFs, and second, based on the target VNF type.

/pdf/a-survey-on-the-placement-of-virtual-resources-and-virtual-1ax0uij3t0.pdf

A Survey on the Placement of Virtual Resources and Virtual Network Functions

Resource scheduling for infrastructure as a service (IaaS) in cloud computing

This paper presents two exact algorithms for energy efficient scheduling of virtual machines (VMs) in cloud data centers. Modeling of energy aware allocation and consolidation to minimize overall energy consumption leads us to the combination of an optimal allocation algorithm with a consolidation algorithm relying on migration of VMs at service departures. The optimal allocation algorithm is solved as a bin packing problem with a minimum power consumption objective. It is compared with an energy aware best fit algorithm. The exact migration algorithm results from a linear and integer formulation of VM migration to adapt placement when resources are released. The proposed migration is general and goes beyond the current state of the art by minimizing both the number of migrations needed for consolidation and energy consumption in a single algorithm with a set of valid inequalities and conditions. Experimental results show the benefits of combining the allocation and migration algorithms and demonstrate their ability to achieve significant energy savings while maintaining feasible convergence times when compared with the best fit heuristic.

Energy efficient VM scheduling for cloud data centers: exact allocation and migration algorithms

Network function virtualization (NFV) decouples software implementations of network functions from their hosts (or hardware). NFV exposes a new set of entities, the virtualized network functions (VNFs). The VNFs can be chained with other VNFs and physical network functions to realize network services. This flexibility introduced by NFV allows service providers to respond in an agile manner to variable service demands and changing business goals. In this context, the efficient establishment of service chains and their placement becomes essential to reduce capital and operational expenses and gain in service agility. This paper addresses the placement aspect of these service chains by finding the best locations and hosts for the VNFs and to steer traffic across these functions while respecting user requirements and maximizing provider revenue. We propose a novel eigendecomposition-based approach for the placement of virtual and physical network function chains in networks and cloud environments. A heuristic based on a custom greedy algorithm is also presented to compare performance and assess the capability of the eigendecomposition approach. The performance of both algorithms is compared to a multi-stage-based method from the state of the art that also addresses the chaining of network services. Performance evaluation results show that our matrix-based method, eigendecomposition of adjacency matrices, has reduced complexity and convergence times that essentially depend only on the physical graph sizes. Our proposal also outperforms the related work in provider’s revenue and acceptance rate.

/pdf/a-scalable-algorithm-for-the-placement-of-service-function-2dt8q1petx.pdf

A Scalable Algorithm for the Placement of Service Function Chains

In the context of NFV and agile service production, virtualization of resources and SFC play a key role in automating network services deployment. Designing NFV management and orchestration to provide dynamic SFC as a service is addressed by the proposed NFV orchestration framework.1 The framework is designed to facilitate the development of NFV architecture components with a focus on SFC orchestration, placement algorithms, required monitoring, and network services stitching. The proposed framework can be used to compare placement algorithms as well as develop and evaluate other service function chaining solutions using a variety of SDN controllers to interact with heterogeneous underlying networking technologies. This article presents the SFC orchestration framework, an implementation, and a qualitative and quantitative evaluation of its components in an experimental environment.

NFV Orchestration Framework Addressing SFC Challenges

This paper addresses energy efficient VNF placement and chaining over NFV enabled infrastructures. VNF placement and chaining are formulated as a decision tree search to overcome this NP-Hard problem complexity. The proposed approach is an extension of the Monte Carlo Tree Search (MCTS) method to achieve energy savings using physical resource consolidation and sharing VNFs between multiple tenants. A real cloud testbed and extensive simulations are used to assess performance and ability to scale with problem size. Evaluation results show significant reduction in energy consumption of the proposed placement solution compared to related work. The polynomial complexity of our proposal is highlighted by the simulation results.

Energy Efficient Algorithm for VNF Placement and Chaining

This paper presents a model for Virtual Network Function (VNF) placement and chaining across Cloud environments. We propose a new analytical approach for joint VNFs placement and traffic steering for complex service chains and different VNF types. A custom greedy algorithm is also proposed to compare with our solution. Performance evaluation results show that our approach is fast and stable and has a execution time that essentially depends only on the NFV infrastructure size.

Chaima Ghribi

Papers

Energy efficient VM scheduling for cloud data centers: exact allocation and migration algorithms

A Scalable Algorithm for the Placement of Service Function Chains

NFV Orchestration Framework Addressing SFC Challenges

Energy Efficient Algorithm for VNF Placement and Chaining

VNF Placement and Chaining in Distributed Cloud