Scribd
Upload
18 views2 pages

Group 53 Project Proposal

Uploaded by

Grace Anyanwu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
18 views2 pages

Group 53 Project Proposal

Uploaded by

Grace Anyanwu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Title of the Study

Learning Wi-Fi Performance

Background of the Study


The study addresses the challenges in accurately predicting the performance of Wi-Fi
networks, particularly in the context of dense deployments where multiple links contend for
limited spectrum. Existing models often struggle to account for the complex interactions
between the MAC and PHY layers, especially with newer IEEE amendments like 802.11n
and 802.11ac that introduce variable channel widths and higher modulation schemes.

The Problem Statement


Obtaining precise and quantitative performance predictions in Wi-Fi networks is notoriously
difficult due to the complexity of interference interactions and the vast variety of possible
wireless configurations. Traditional models often fail to capture the actual performance of
Wi-Fi links under varying conditions.

The Aim and Objectives of the Study


The aim of the study is to develop a more effective method for predicting Wi-Fi performance
by using machine learning techniques to learn implicit performance models from real-world
measurements. The objectives include:
- To improve the accuracy of performance predictions compared to existing models.
- To create a model that can adapt to varying conditions without needing exhaustive
measurements.

Methodology - How It Was Done


The study employed a two-phase approach:
1. Measurement Phase: Conducted controlled experiments to measure throughput for various
configurations of Wi-Fi links.
2. Learning Phase**: Used supervised machine learning to find a mathematical function that
maps the input features (such as spectral configurations and channel qualities) to the observed
throughput.

The Tools Used for the Study


The study utilized machine learning techniques to analyze the collected data and develop
predictive models. Specific tools or algorithms used for the machine learning process were
not detailed in the provided text, but the approach emphasizes the use of supervised learning
methods.

The Results of the Study


The results indicated that the learned models improved prediction accuracy by at least 49%
compared to traditional measurement-seeded models based on SINR. The study also
demonstrated that the learned models could effectively predict throughput in new or unseen
environments.

Significance of the Study


This study is significant as it provides a novel approach to Wi-Fi performance prediction that
can adapt to complex and varying conditions. It highlights the potential of machine learning
to enhance resource allocation and performance optimization in Wi-Fi networks, which is
crucial for meeting the increasing demand for wireless connectivity.

Limitations of the Study


The study acknowledges that while the learned models improve accuracy, they may still be
limited by the quality and range of the initial measurements. Additionally, the complexity of
real-world environments may introduce factors that were not captured during the
measurement phase.
Future Works
Future research could focus on expanding the model to include a wider range of
environmental conditions and interference scenarios. Additionally, exploring the integration
of these models into real-time network management systems could enhance their practical
applicability in dynamic Wi-Fi environments.

References

[1] “Learning Wi-Fi performance,” IEEE Conference Publication | IEEE Xplore, Jun. 01, 2015.
https://ieeexplore.ieee.org/abstract/document/7338298

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy