Empowering Sketches with Machine Learning for Network Measurements

Abstract

Network monitoring and management require accurate statistics of a variety of flow-level metrics, such as flow sizes, top-k flows, and number of flows. Arguably, the most commonly used data structure to record and measure these metrics is the sketch. While a significant amount of work has already been done on sketching techniques, there is still a lot of room for improvement because the accuracy of existing sketches depends a lot on the nature of network traffic and varies significantly as the network traffic characteristics change. In this paper, we propose the idea of employing machine learning to reduce this dependence of the accuracy of sketches on network traffic characteristics and present a generalized machine learning framework that increases the accuracy of sketches significantly. We further present three case studies, where we applied our framework on sketches for measuring three well-known flow-level network metrics. Experimental results show that machine learning helps decrease the error rates of existing sketches by up to 202 times.