Advanced

Monitoring Network Congestion in Wi-Fi, based on QoE in HTTP Video Steaming Services

Nasir, Muhammad Umar LU (2016) EITM02 20151
Department of Electrical and Information Technology
Abstract
Improvements in Internet technology, development of multimedia applications, protocols and improvement in user devices have led to the popularity of multimedia applications, among which video streaming applications are most popular. Streaming video services are sensitive to network conditions, thus making Quality of Experience (QoE) of end users sensitive to network conditions. QoE is affected by small disturbances in network conditions and end users observe this as blurred video or lost scenes. This may lead to end users giving up the service or switching to another network operator. To avoid this, network operators and service providers need to maintain QoE at a satisfactory level. The purpose of this study is to develop a monitoring... (More)
Improvements in Internet technology, development of multimedia applications, protocols and improvement in user devices have led to the popularity of multimedia applications, among which video streaming applications are most popular. Streaming video services are sensitive to network conditions, thus making Quality of Experience (QoE) of end users sensitive to network conditions. QoE is affected by small disturbances in network conditions and end users observe this as blurred video or lost scenes. This may lead to end users giving up the service or switching to another network operator. To avoid this, network operators and service providers need to maintain QoE at a satisfactory level. The purpose of this study is to develop a monitoring method, which can monitor network congestion in Wi-Fi, based on QoE in HTTP video streaming services. This study proposes a QoE assessment method based on Machine Learning (ML), which allows network operators and service providers to predict QoE from network level measurements.
This study was conducted in four steps. Initially, network monitoring probes were designed to measure key metrics that affect QoE, which involved development of QoE assessment model based on relationship between Quality of Service (QoS) and QoE, and implementation of an active measurement protocol called Two-Way Active Measurement Protocol (TWAMP) for network level measurements. Subsequently, a direct link was established between subjective QoE and objective network measurements by designing various test cases. Data was collected by performing network measurements on a Wi-Fi testbed to study the impact of wireless rate adaptation and link utilization on QoE by loading WLAN with cross traffic on downlink or bi-directional paths along with YouTube video. A ML approach was then used to classify network level measurements into QoE levels. A set of ML algorithms: SVM, KNN and Logistic Regression were tested and evaluated to build a classification model to be used in network monitoring system module within network management system. Ultimately, the performance of the proposed QoE assessment method was evaluated using five test cases.
The results show that this method performed well and give high classification accuracy in all cases. Outputs from this work may be used by network operators and service providers to modify their network management system by developing effective congestion management solutions to bring back QoE to satisfactory level. (Less)
Popular Abstract
Loading ... Loading ... Loading ... is what we observe while watching streaming videos in areas like downtown, shopping malls, university, airports, etc., while connected to Wi-Fi. This causes irritation to users if the video loads a lot or takes too much time to load. This study proposes a method, which predicts user experience. Network operators and service providers can use this prediction to manage their networks more efficiently.
Video streaming applications are very popular among multimedia applications. Video traffic on the Internet is predicted to grow further and the share of video is expected to be 82% as compared to other applications by 2020. Video requires high bit rates. Video consumes high bandwidths of about more than 10... (More)
Loading ... Loading ... Loading ... is what we observe while watching streaming videos in areas like downtown, shopping malls, university, airports, etc., while connected to Wi-Fi. This causes irritation to users if the video loads a lot or takes too much time to load. This study proposes a method, which predicts user experience. Network operators and service providers can use this prediction to manage their networks more efficiently.
Video streaming applications are very popular among multimedia applications. Video traffic on the Internet is predicted to grow further and the share of video is expected to be 82% as compared to other applications by 2020. Video requires high bit rates. Video consumes high bandwidths of about more than 10 times as compared to other popular applications, for example, Facebook and music streaming applications. If there is not enough bandwidth, users observe video re-buffering, while watching videos. This is more common in low capacity networks like Wi-Fi. Consequently, leading
to bad user experience and as a result, users can either switch network operator or quit watching video. Thus, there is an increasing interest from network operators and service providers to monitor user satisfaction.
This study is aimed to design a method to predict user experience of YouTube video users, using Wi-Fi as access network. The results show that this method performed well and give high accuracy for all test cases. Prediction of user experience is a first step in user satisfaction. It is very important for the network operators and service providers to predict user experience. Consequently, they can tune their services accordingly to bring back the user satisfaction to acceptable level. This study provides means for network operators and service providers to predict user experience. (Less)
Please use this url to cite or link to this publication:
author
Nasir, Muhammad Umar LU
supervisor
organization
course
EITM02 20151
year
type
H2 - Master's Degree (Two Years)
subject
keywords
QoE, Video Streaming, QoE-QoS Relationship, Packet Loss Pattern, RTT, Active Measurements, TWAMP, Machine Learning Approach.
report number
LU/LTH-EIT 2016-533
language
English
id
8887180
date added to LUP
2016-08-17 15:47:05
date last changed
2016-08-17 15:47:05
@misc{8887180,
  abstract     = {Improvements in Internet technology, development of multimedia applications, protocols and improvement in user devices have led to the popularity of multimedia applications, among which video streaming applications are most popular. Streaming video services are sensitive to network conditions, thus making Quality of Experience (QoE) of end users sensitive to network conditions. QoE is affected by small disturbances in network conditions and end users observe this as blurred video or lost scenes. This may lead to end users giving up the service or switching to another network operator. To avoid this, network operators and service providers need to maintain QoE at a satisfactory level. The purpose of this study is to develop a monitoring method, which can monitor network congestion in Wi-Fi, based on QoE in HTTP video streaming services. This study proposes a QoE assessment method based on Machine Learning (ML), which allows network operators and service providers to predict QoE from network level measurements.
This study was conducted in four steps. Initially, network monitoring probes were designed to measure key metrics that affect QoE, which involved development of QoE assessment model based on relationship between Quality of Service (QoS) and QoE, and implementation of an active measurement protocol called Two-Way Active Measurement Protocol (TWAMP) for network level measurements. Subsequently, a direct link was established between subjective QoE and objective network measurements by designing various test cases. Data was collected by performing network measurements on a Wi-Fi testbed to study the impact of wireless rate adaptation and link utilization on QoE by loading WLAN with cross traffic on downlink or bi-directional paths along with YouTube video. A ML approach was then used to classify network level measurements into QoE levels. A set of ML algorithms: SVM, KNN and Logistic Regression were tested and evaluated to build a classification model to be used in network monitoring system module within network management system. Ultimately, the performance of the proposed QoE assessment method was evaluated using five test cases.
The results show that this method performed well and give high classification accuracy in all cases. Outputs from this work may be used by network operators and service providers to modify their network management system by developing effective congestion management solutions to bring back QoE to satisfactory level.},
  author       = {Nasir, Muhammad Umar},
  keyword      = {QoE,Video Streaming,QoE-QoS Relationship,Packet Loss Pattern,RTT,Active Measurements,TWAMP,Machine Learning Approach.},
  language     = {eng},
  note         = {Student Paper},
  title        = {Monitoring Network Congestion in Wi-Fi, based on QoE in HTTP Video Steaming Services},
  year         = {2016},
}