A novel workload scheduling framework for intrusion detection system in NFV scenario

Abstract

Compared with traditional Intrusion Detection System (IDS) solutions, deploying IDS in Network Function Virtualization (NFV) environment can have better scalability and flexibility. Existing research works in this area do not consider many IDS features to design IDS-specific workload scheduling approaches. Thus, there is space further to promote the performance of IDS deployment in the NFV scenario. In this paper, we find some critical IDS features by analyzing packet processing procedures, software implementation, and rulesets of typical IDS. Combining these features with the flexibility of NFV, we propose a novel workload scheduling framework for IDS deployment in the NFV scenario. Our framework contains two parts: 1) a novel protocol & destination port based traffic migration strategy which can promote the detection performance and reduce the memory usage compared with the traditional 5-tuple hash based strategy; 2) an auto-configuration algorithm to find a better-than-default configuration for each Virtual Network Function (VNF) instance. We evaluate our framework with real network traffic and benchmark traffic datasets for IDS. Experimental results show that our framework can always have better detection performance and lower memory usage than the 5-tuple hash based migration strategy and the default configuration.