SuVMF: software-defined unified virtual monitoring function for SDN-based large-scale networks

Abstract

Traffic and resource monitoring is the essential function for large-scale enterprises, service providers, and network operators to ensure reliability, availability, and security of their resources. For this reason, many large-scale enterprises and providers have been investing in various standalone dedicated monitoring solutions. However, they find the cost of a dedicated standalone appliance per-feature prohibitive, inflexible, slow to install and difficult to maintain. Network Function Virtualization (NFV)-based virtualization trends represent an attractive opportunity for such stakeholders trying to meet the above requirements while controlling OPEX and CAPEX. Although there are many advantages that virtualization of monitoring function brings, some challenges remained to be solved are ensuring scalability and performance of single or distributed multiple virtual monitoring functions and flexibility and easiness of virtual functions lifecycle management. In this paper, to address such problems, we propose a novel architecture of software-defined unified virtual monitoring function for SDN-based large-scale networks (SuVMF). SuVMF is an essential component to build a scalable, reliable, secure and high-performance SDN architecture by providing intelligent control and monitoring management abstraction and filtering layer. In this paper, we present design, implementation, and evaluation results of SuVMF.