Skip to main content
Oral defences & examinations, Thesis defences

Masters Thesis Defense: Shivam Patel


Date & time
Thursday, June 17, 2021
1 p.m. – 3 p.m.
Speaker(s)

Shivam Patel

Cost

This event is free

Where

Online

Candidate:

Shivam Patel

   
             

Thesis Title:


Augmenting Network Performance Datasets with Weather, Sports and Social Media Data for Improved Predictions

             

Date & Time: 

Thursday, June 17th, 2021 at 1:00 PM

   
             

Location:

Zoom

   
             

Examining Committee:

         
             
 

Dr. Peter Chen

(Chair)

   
             
 

Drs. Brigitte Jaumard & Tristan Glatard

(Supervisors)

   
             
 

Dr. Peter Chen

(Examiner)

 
             
 

Dr. Yann-Gael Gueheneuc

(Examiner)

 
             
             



Abstract: 

           

 

Understanding the network performance enables the network providers to manage their network better. Network performance degradation can lead to network service issues causing monetary loss and customer churn for the network providers. Accurate network performance prediction potentially enables the proactive resource allocation to attenuate the anticipated network performance degradation and associated service issues.

 

Previous literature attempts to predict the network performance using historical network data. However, real-world network performance is impacted by various external factors. Existing literature fails to consider such external factors that can improve the understanding and predictions of the network performance.

 

This thesis aims to examine if external factors can improve the network performance understanding and predictions. To this end, we inspect the correlation of network performance data with various external data sources like Weather, NFL, NBA, and Twitter. Then, we perform network performance data augmentation using the contextual information in such external data. Then we investigate the network performance prediction improvements after data augmentation using Machine Learning. Predictive experiments with data augmentation using the NFL events highlight a 23% improvement in the network performance predictions. The augmentation using other external sources fails to improve the network performance predictions.

Back to top

© Concordia University