Scribd
Upload
6 views1 page

Enhancing WiFi Rate Adaptation with ML

The document summarizes the goal of a master's thesis on improving rate adaptation in vehicular networks using machine learning. The thesis aims to add functionality to an existing machine learning algorithm to more accurately predict rates and increase throughput. The student will evaluate the approach through network simulations and compare it to existing schemes. Basic wireless knowledge is required, while machine learning and simulation experience are bonuses but not necessary.

Uploaded by

Nazar Aziz
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views1 page

Enhancing WiFi Rate Adaptation with ML

The document summarizes the goal of a master's thesis on improving rate adaptation in vehicular networks using machine learning. The thesis aims to add functionality to an existing machine learning algorithm to more accurately predict rates and increase throughput. The student will evaluate the approach through network simulations and compare it to existing schemes. Basic wireless knowledge is required, while machine learning and simulation experience are bonuses but not necessary.

Uploaded by

Nazar Aziz
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Master

Thesis
Boosting Rate Adaptation in
WiFi-Based Vehicular Networks with
Machine Learning
Motivation
Vehicular networks will soon provide support for multimedia and other throughput-
hungy applications. Rate adaptation techniques have been typically applied to meet
the throughput requirements. However, in highly mobile environments an accurate
selection of the data rate is a challenging task. Recently, there have been works
proposing rate adaptation based on machine learning techniques, which can discover
certain (signal propagation and movement) patterns buried in the training data. The
latter which can be suitably exploited to predict future states and improve decisions.

Goal of the Thesis


The goal of this thesis is to add functionalities to an existing machine learning algorithm
(using the Random Forests method) to improve the prediction accuracy and increase the
achievable throughput in vehicular communications. By means of network simulations
(ns3) you will evaluate the performance of your approach and benchmark it to state-of-
the-art schemes.

Requirements
Basic knowledge on wireless communications will surely help.
Knowledge on machine learning and experience with (ns3) simulations are a plus but not required.

Contact Information
Oscar Puñal
[Link]@[Link]
UMIC Building Room 106
0241 8020744
follow us on
 [Link]

You might also like