Proactive Traffic Sampling with Dynamic Flow Rates in Software-Defined Networks
Date
2024-12-12
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
As modern networks continue to grow in scale and speed, traffic sampling has become an indispensable tool in network management. While there exists a plethora of sampling systems, they generally assume flow rates are stable and predictable over a sampling period. Consequently, when deployed in networks with dynamic flow rates, some flows may be missed or under-sampled, while others are over-sampled. This thesis presents the design and evaluation of dSamp, a network-wide sampling system capable of handling dynamic flow rates in Software-Defined Networks (SDNs). The key idea in dSamp is to consider flow rate fluctuations when deciding on which network switches and at what rate to sample each flow. We formulate the network-wide sampling with dynamic flow rates as a robust optimization problem. Our proactive approach leverages statistical information about flow rates to cope with fluctuations in flow rates. Since our initial formulation is an Integer Second Order Cone Program (ISOCP), which is infeasible for both small-scale and large-scale network instances, we shift our focus to developing an efficient approximate Integer Linear Program (ILP) called APX, which can compute sampling allocations even for large-scale networks. To show the efficacy of dSamp for network monitoring, we have implemented APX and several existing solutions in ns-3 and conducted extensive experiments using both model-driven and trace-driven simulations. Our model-driven results indicate that APX outperforms the approaches in [50] and [21] by up to 10%. Similarly, our trace-driven results show that APX surpasses these works by up to 6.37%. Unlike [50] and [21], which require fine-tuning in model-driven simulations for use in trace-driven simulations, APX works across all simulations without such a requirement.
Description
Keywords
Traffic Sampling, Software-Defined Networking, Dynamic Flow Rates
Citation
Esmaeilian, S. (2024). Proactive traffic sampling with dynamic flow rates in software-defined networks (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.