The Challenges of Trace-Driven Wi-Fi Emulation

TL;DR

This paper evaluates the state-of-the-art trace driven emulation tool for Cellular networks and identifies issues for Wi-Fi: interference with concurrent traffic, interference with its own traffic if measurements are done on both uplink and downlink simultaneously, and packet loss.

Abstract

Wi-Fi link is unpredictable and it has never been easy to measure it perfectly; there is always bound to be some bias. As wireless becomes the medium of choice, it is useful to capture Wi-Fi traces in order to evaluate, tune, and adapt the different applications and protocols. Several methods have been used for the purpose of experimenting with different wireless conditions: simulation, experimentation, and trace-driven emulation. In this paper, we argue that trace-driven emulation is the most favorable approach. In the absence of a trace-driven emulation tool for Wi-Fi, we evaluate the state-of-the-art trace-driven emulation tool for Cellular networks and we identify issues for Wi-Fi: interference with concurrent traffic, interference with its own traffic if measurements are done on both uplink and downlink simultaneously, and packet loss. We provide a solid argument as to why this tool falls short of effectively capturing Wi-Fi traces. The outcome of our analysis guides us to propose a number of suggestions on how the existing tool can be tweaked to accurately capture Wi-Fi traces.

Figures (13)

• Figure 1: Experiment Set-up
• Figure 2: Distribution of the fraction of capacity consumed by Saturator
• Figure 3: Saturator with concurrent TCP traffic and variable bandwidth
• Figure 4: Saturator with concurrent UDP traffic and variable bandwidth
• Figure 5: Saturator with concurrent UDP traffic and variable bandwidth