A Learning Approach to Wi-Fi Access

TL;DR

This paper introduces a predictive model for Wi-Fi access point-station associations that enhances system throughput in dense networks by leveraging workload data, achieving near-optimal performance based on real traffic traces.

Contribution

It presents a novel workload-based association method and a predictive model that guides resource allocation in dense Wi-Fi networks, demonstrating significant throughput improvements.

Findings

Achieves 72-77% of optimal throughput with real traffic data

Workload-based associations outperform traditional methods

Model adapts well with varying training data sizes

Abstract

We show experimentally that workload-based AP-STA associations can improve system throughput significantly. We present a predictive model that guides optimal resource allocations in dense Wi-Fi networks and achieves 72-77% of the optimal throughput with varying training data set sizes using a 3-day trace of real cable modem traffic.