An NFV and microservice based architecture for on-the-fly component provisioning in content delivery networks

Content Delivery Networks (CDNs) deliver content (e.g. Web pages, videos) to geographically distributed end-users over the Internet. Some contents do sometimes attract the attention of a large group of end-users. This often leads to flash crowds which can cause major issues such as outage in the CDN. Microservice architectural style aims at decomposing monolithic systems into smaller components which can be independently deployed, upgraded and disposed. Network Function Virtualization (NFV) is an emerging technology that aims to reduce costs and bring agility by decoupling network functions from the underlying hardware. This paper leverages the NFV and microservice architectural style to propose an architecture for on-the-fly CDN component provisioning to tackle issues such as flash crowds. In the proposed architecture, CDN components are designed as sets of microservices which interact via RESTFul Web services and are provisioned as Virtual Network Functions (VNFs), which are deployed and orchestrated on-the-fly. We have built a prototype in which a CDN surrogate server, designed as a set of microservices, is deployed on-the-fly. The prototype is deployed on SAVI, a Canadian distributed test bed for future Internet applications. The performance is also evaluated.

[1]  Fabrizio Montesi,et al.  Microservices: Yesterday, Today, and Tomorrow , 2017, Present and Ulterior Software Engineering.

[2]  G.J. Minden,et al.  A survey of active network research , 1997, IEEE Communications Magazine.

[3]  Henning Schulzrinne,et al.  NetServ: dynamically deploying in-network services , 2009, ReArch '09.

[4]  Roch H. Glitho,et al.  RESTful web services for service provisioning in next-generation networks: a survey , 2011, IEEE Communications Magazine.

[5]  David Wetherall,et al.  Towards an active network architecture , 1996, CCRV.

[6]  Pantelis A. Frangoudis,et al.  CDN-As-a-Service Provision Over a Telecom Operator’s Cloud , 2017, IEEE Transactions on Network and Service Management.

[7]  Henning Schulzrinne,et al.  ActiveCDN: Cloud Computing Meets Content Delivery Networks , 2011 .

[8]  Halima Elbiaze,et al.  NFV and SDN-based cost-efficient and agile value-added video services provisioning in content delivery networks , 2017, 2017 14th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[9]  Eddie Li,et al.  An Overview of Cloud Based Content Delivery Networks: Research Dimensions and State-of-the-Art , 2015, Trans. Large Scale Data Knowl. Centered Syst..

[10]  Lea Skorin-Kapov,et al.  Can context monitoring improve QoE? A case study of video flash crowds in the internet of services , 2015, 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM).

[11]  Iraj Sodagar,et al.  The MPEG-DASH Standard for Multimedia Streaming Over the Internet , 2011, IEEE MultiMedia.

[12]  William LeFebvre,et al.  CNN.com: Facing a World Crisis , 2001, LiSA.

[13]  Seungjoon Lee,et al.  Network function virtualization: Challenges and opportunities for innovations , 2015, IEEE Communications Magazine.