Development of a QoE Model Himadeepa Karlapudi 03/07/03.

Slides:



Advertisements
Similar presentations
Measuring IP Performance Geoff Huston Telstra. What are you trying to measure? User experience –Responsiveness –Sustained Throughput –Application performance.
Advertisements

Congestion Control and Fairness Models Nick Feamster CS 4251 Computer Networking II Spring 2008.
A3: APPLICATION AWARE ACCELERATION FOR WIRELESS DATA NETWORKS Athours: Zhenyun Zhuang and Tae-Young Chang GNAN Research Group, Georgia Tech, Atlanta, GA.
TCP Vegas: New Techniques for Congestion Detection and Control.
© 2007 Pearson Education Inc., Upper Saddle River, NJ. All rights reserved.1 Computer Networks and Internets with Internet Applications, 4e By Douglas.
Transport Layer – TCP (Part2) Dr. Sanjay P. Ahuja, Ph.D. Fidelity National Financial Distinguished Professor of CIS School of Computing, UNF.
Doc.: IEEE /0604r1 Submission May 2014 Slide 1 Modeling and Evaluating Variable Bit rate Video Steaming for ax Date: Authors:
Congestion Control Created by M Bateman, A Ruddle & C Allison As part of the TCP View project.
Restricted Slow-Start for TCP William Allcock 1,2, Sanjay Hegde 3 and Rajkumar Kettimuthu 1,2 1 Argonne National Laboratory 2 The University of Chicago.
Locating Bottleneck/Congested Links Jeng Lung WebTP Meeting 11/8/99.
Modeling of Web/TCP Transfer Latency Yujian Peter Li January 22, 2004 M. Sc. Committee: Dr. Carey Williamson Dr. Wayne Eberly Dr. Elena Braverman Department.
Modeling TCP Throughput Jeng Lung WebTP Meeting 11/1/99.
Reduced TCP Window Size for Legacy LAN QoS II Niko Färber Sept. 20, 2000.
TCP Congestion Control TCP sources change the sending rate by modifying the window size: Window = min {Advertised window, Congestion Window} In other words,
Available bandwidth measurement as simple as running wget D. Antoniades, M. Athanatos, A. Papadogiannakis, P. Markatos Institute of Computer Science (ICS),
1 TCP latency modeling. 2 Q: How long does it take to receive an object from a Web server after sending a request? r TCP connection establishment r data.
The Transport Layer Chapter 6. The Transport Service Services Provided to the Upper Layers Transport Service Primitives Berkeley Sockets An Example of.
1 Emulating AQM from End Hosts Presenters: Syed Zaidi Ivor Rodrigues.
FTDCS 2003 Network Tomography based Unresponsive Flow Detection and Control Authors Ahsan Habib, Bharat Bhragava Presenter Mohamed.
1 K. Salah Module 6.1: TCP Flow and Congestion Control Connection establishment & Termination Flow Control Congestion Control QoS.
TCP. Learning objectives Reliable Transport in TCP TCP flow and Congestion Control.
Reduced TCP Window Size for Legacy LAN QoS Niko Färber July 26, 2000.
1 A State Feedback Control Approach to Stabilizing Queues for ECN- Enabled TCP Connections Yuan Gao and Jennifer Hou IEEE INFOCOM 2003, San Francisco,
Copyright © 2005 Department of Computer Science CPSC 641 Winter Tutorial: TCP 101 The Transmission Control Protocol (TCP) is the protocol that sends.
Error Checking continued. Network Layers in Action Each layer in the OSI Model will add header information that pertains to that specific protocol. On.
Bandwidth Estimation: Metrics Mesurement Techniques and Tools By Ravi Prasad, Constantinos Dovrolis, Margaret Murray and Kc Claffy IEEE Network, Nov/Dec.
All rights reserved © 2006, Alcatel Accelerating TCP Traffic on Broadband Access Networks  Ing-Jyh Tsang 
Internet Traffic Management Prafull Suryawanshi Roll No - 04IT6008.
Process-to-Process Delivery:
Lect3..ppt - 09/12/04 CIS 4100 Systems Performance and Evaluation Lecture 3 by Zornitza Genova Prodanoff.
Advanced Network Architecture Research Group 2001/11/149 th International Conference on Network Protocols Scalable Socket Buffer Tuning for High-Performance.
3: Transport Layer3b-1 Principles of Congestion Control Congestion: r informally: “too many sources sending too much data too fast for network to handle”
Transport Layer3-1 Chapter 3 outline r 3.1 Transport-layer services r 3.2 Multiplexing and demultiplexing r 3.3 Connectionless transport: UDP r 3.4 Principles.
Internet Traffic Management. Basic Concept of Traffic Need of Traffic Management Measuring Traffic Traffic Control and Management Quality and Pricing.
Modeling TCP Throughput: A Simple Model and its Empirical Validation Ross Rosemark Penn State University.
POSTECH DP&NM Lab. Internet Traffic Monitoring and Analysis: Methods and Applications (1) 2. Network Monitoring Metrics.
An Efficient Approach for Content Delivery in Overlay Networks Mohammad Malli Chadi Barakat, Walid Dabbous Planete Project To appear in proceedings of.
3: Transport Layer3b-1 TCP: Overview RFCs: 793, 1122, 1323, 2018, 2581 r full duplex data: m bi-directional data flow in same connection m MSS: maximum.
UDT: UDP based Data Transfer Protocol, Results, and Implementation Experiences Yunhong Gu & Robert Grossman Laboratory for Advanced Computing / Univ. of.
Presented by Rajan Includes slides presented by Andrew Sprouse, Northeastern University CISC 856 TCP/IP and Upper Layer Protocols Date:May 03, 2011.
Transport Layer Moving Segments. Transport Layer Protocols Provide a logical communication link between processes running on different hosts as if directly.
3: Transport Layer3-1 Where we are in chapter 3 Last time: r TCP m Reliable transfer m Flow control m Connection management r principles of congestion.
Advanced Network Architecture Research Group 2001/11/74 th Asia-Pacific Symposium on Information and Telecommunication Technologies Design and Implementation.
HighSpeed TCP for High Bandwidth-Delay Product Networks Raj Kettimuthu.
Transport Layer3-1 TCP throughput r What’s the average throughout of TCP as a function of window size and RTT? m Ignore slow start r Let W be the window.
1 Capacity Dimensioning Based on Traffic Measurement in the Internet Kazumine Osaka University Shingo Ata (Osaka City Univ.)
1 Transport Layer Lecture 10 Imran Ahmed University of Management & Technology.
1. Introduction REU 2006-Packet Loss Distributions of TCP using Web100 Zoriel M. Salado, Mentors: Dr. Miguel A. Labrador and Cesar D. Guerrero 2. Methodology.
TCP: Transmission Control Protocol Part II : Protocol Mechanisms Computer Network System Sirak Kaewjamnong Semester 1st, 2004.
Measuring the Capacity of a Web Server USENIX Sympo. on Internet Tech. and Sys. ‘ Koo-Min Ahn.
The Macroscopic behavior of the TCP Congestion Avoidance Algorithm.
Data Transfer Case Study: TCP  Go-back N ARQ  32-bit sequence # indicates byte number in stream  transfers a byte stream, not fixed size user blocks.
4343 X2 – The Transport Layer Tanenbaum Ch.6.
IP1 The Underlying Technologies. What is inside the Internet? Or What are the key underlying technologies that make it work so successfully? –Packet Switching.
Fall 2004FSU CIS 5930 Internet Protocols1 Second phase of the project Please check some networking textbooks for details on TCP and OSPF.
CS640: Introduction to Computer Networks Aditya Akella Lecture 15 TCP Congestion Control.
TCP/IP1 Address Resolution Protocol Internet uses IP address to recognize a computer. But IP address needs to be translated to physical address (NIC).
Transmission Control Protocol (TCP) TCP Flow Control and Congestion Control CS 60008: Internet Architecture and Protocols Department of CSE, IIT Kharagpur.
Chapter 10 Congestion Control in Data Networks and Internets 1 Chapter 10 Congestion Control in Data Networks and Internets.
Bandwidth estimation: metrics, measurement techniques, and tools Presenter: Yuhang Wang.
CSEN 404 Introduction to Networks Amr El Mougy Lamia AlBadrawy.
TCP - Part II.
Approaches towards congestion control
The Transport Layer (TCP)
Reddy Mainampati Udit Parikh Alex Kardomateas
Mohammad Malli Chadi Barakat, Walid Dabbous Alcatel meeting
Transport Layer Unit 5.
Monkey See, Monkey Do A Tool for TCP Tracing and Replaying
Internet Research Group at Clemson University
Modeling and Evaluating Variable Bit rate Video Steaming for ax
Presentation transcript:

Development of a QoE Model Himadeepa Karlapudi 03/07/03

 What is Quality of Experience (QoE)?  Why do we need QoE ?

How is QoE measured?  Predicting TCP throughput and obtaining other network observables  Converting network observables into representative inputs for the QoE model.  The QoE model gets these inputs and conveys the predicted QoE.

Predicting TCP throughput  Development of a model that is representative of majority of TCP traffic on the internet.  Three models have been used as a basis for the development of the new model. Amherst Model Amherst Model Roch Guerin’s Model Roch Guerin’s Model Cardwell’s Model Cardwell’s Model

Parameters considered for the development of the model  Network environment and nature of flows  Startup effects  Losses during connection establishment  Acknowledgement type  Inference of packet loss  Assumptions about loss

Cont.  Receiver and Sender buffering limitation  Congestion Control Algorithm  Maximum Congestion Window  Delayed acks  Retransmission timeout  Initial congestion window  Other assumptions

Simulation Environment Router 100Mbps client server Test client Link Capacity 10 Mbps or 1.5 Mbps Ping,WRT, SNMP,MRTG

SURGE  Scalable URL Reference Generator  SURGE is used to generate a sequence of URL requests  SURGE consists of three main parts  Client set up  Server set up  Client request generator

SURGE (cont.)  The SURGE client setup spawns a number of threads each of which behaves like an individual client.  The client request generator makes the requests for files from the server.  The server setup generates the set of files which are requested by SURGE clients.

SURGE (cont.)  As it’s output SURGE gives the start time and end time of each client process.  We can also obtain the mean and variance of server throughput and the total amount of data transferred by the server in unit time.  SURGE can be modified to obtain statistics at regular intervals instead of waiting for the completion of entire simulation.

Development of QoE model  Two major issues are involved in the development of QoE model  How should the network be sampled (non invasive sampling)  Transforming these raw samples into input parameters of the chosen model (WRT metric)

Sampling Techniques  We use non invasive network sampling where in the network element itself communicates its status (statistics) to the network manager instead of examining tcpdump traces.  Sampling is mostly done at network level and not at application level.

Non invasive sampling techniques  Probing: Probes can be implemented using ping packets. We can obtain an estimate of RTT and loss rates.  Polling: This refers to periodic querying by SNMP MIBs maintained in routers to retrieve performance data.

Development of QoE model  Once this raw data is obtained this has to fed into a QoE model.  We use a simple WRT metric to obtain QoE initially. The WRT metric gives a variation in the response time.  Our QoE model should be able to predict the mean sample time and also it’s variation.

Future work  Comparison of non-invasive and invasive sampling techniques  Impact of congestion control/ avoidance algorithm on the assessment of metrics  Once this is done we assess how our predicted QoE is correlated to the QoE perceived by the user.

Future work  Develop a survey methodology to help us validate our assessment algorithm (i.e., have a set of users tell us what they think of their web browsing experience when the WRT metric is 2.5 seconds).  Use the results of this survey to further strengthen the algorithm and make the metrics as close as possible to the quality perceived by end user.  to validate the QoE assessment

Future work  Possibly extend Surge to model streaming or conferencing flows  Compare Surge traffic with other approaches to generating realistic traffic loads  Extend the QoE model to Real time applications.