Douglas M. Freimuth

Policy-based NFV management and orchestration

Softwarization of network functions running on commodity servers, switches, and storage by leveraging standard IT virtualization and cloud technologies has become a goal of communications service providers (CSPs). Management and orchestration (MANO) is crucial for achieving this network functions virtualization (NFV) vision. We propose an open platform for NFV that exposes APIs that can be consumed by other components of a MANO framework. This Enhanced Network Cloud Platform (ENCP) is based on a common policy-based framework. It employs a network appliance container (NAC) as an abstraction of a network function, and it uses predictive and proactive analytics for elasticity and virtual resource management. The architecture of ENCP is presented, and its prototype implementation is discussed.

Using SDN technology to enable cost-effective bandwidth-on-demand for cloud services

We describe bandwidth-on-demand in an evolved multi-layer, SDN-based Cloud Services model. We also show an initial proof-of-concept demonstration of this capability.

Evaluating the Jaccard-Tanimoto Index on Multi-core Architectures

The Jaccard/Tanimoto coefficient is an important workload, used in a large variety of problems including drug design fingerprinting, clustering analysis, similarity web searching and image segmentation. This paper evaluates the Jaccard coefficient on three platforms: the Cell Broadband EngineTMprocessor Intel ®Xeon ®dual-core platform and Nvidia ®8800 GTX GPU. In our work, we have developed a novel parallel algorithm specially suited for the Cell/B.E. architecture for all-to-all Jaccard comparisons, that minimizes DMA transfers and reuses data in the local store. We show that our implementation on Cell/B.E. outperforms the implementations on comparable Intel platforms by 6-20X with full accuracy, and from 10-50X in reduced accuracy mode, depending on the size of the data, and by more than 60X compared to Nvidia 8800 GTX. In addition to performance, we also discuss in detail our efforts to optimize our workload on these architectures and explain how avenues for optimization on each architecture are very different and vary from one architecture to another for our workload. Our work shows that the algorithms or kernels employed for the Jaccard coefficient calculation are heavily dependent on the traits of the target hardware.

Using sdn technology to enable cost-effective bandwidth-on-demand for cloud services [Invited]

We describe bandwidth-on-demand in an evolved multilayer, software-defined networking (SDN) based cloud services model. We present motivation for using a multilayer architecture for the wide-area network (WAN). Our laboratory testbed is described, and both the hardware and management architecture are presented. We also show an initial proof-of-concept demonstration of this capability.

Automated virtual network functions onboarding

Network functions virtualization (NFV) opens up a new ability of network enablement through agile network DevOps to design, develop, and test new services and to provide ongoing updates of existing services. This paper proposes a tool and methodology to aid the NFV designer to rapidly design and onboard new services and applications. Although the main focus is on the service design and onboarding, we provide the relation with other aspects such as management and orchestration, and service assurance of a complete lifecycle for network service. The proposed tool and methodology is called VNF Onboarding Automation Tool (VOAT). The prototype implementation is discussed as well as various use cases where VOAT has been used. With VOAT, an automated service design and onboarding can be efficiently achieved, hence reducing significantly the timeframe for deploying new services in telco cloud-based environment.

Optical Network Requirements for Cloud

The cloud computing model’s acceptance is accelerating and the network is an essential enabler. This tutorial will describe the cloud computing model and relate the requirements of dynamic cloud networks for carrier NFV and large enterprise cloud networks.