Carey Williamson Department of Computer Science University of Calgary Winter 2018 Course Project Overview A typical course project might involve choosing a topic and perf eval methodology ID: 799943
Download The PPT/PDF document "CPSC 641: Project Brainstorming" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
CPSC 641:Project Brainstorming
Carey Williamson
Department of Computer Science
University of Calgary
Winter 2018
Slide2Course Project Overview
A “typical” course project might involve:
choosing a topic and perf
eval
methodology
designing/building appropriate testbed, environment, or platform for your project
extend/customize system as needed
obtain relevant data/measurements needed
design suitable experiment: clear goal, identify factors, levels, performance metrics
obtain and describe (new/interesting) results
Slide3Project Timeline
By Tuesday, February 27:
One-page project proposal (not marked)
Issues: uniqueness, relevance, fit, scale, data
By Monday, April 16:
Submit 12-15 page research paper (hardcopy)
Worth 50% of your grade in CPSC 641
Eval
: problem statement, lit review, method, results, writing style, originality, difficulty, etc.
Slide4Examples of Past Projects
Benchmarking dynamic Web content generation
Web browsing over wireless/mobile networks
Traffic classification using machine learning
Temporal locality in multimedia workloads
WWW2007 Web workload characterization
Benchmarking modern Web browsers
Probabilistic key distribution in WSNs
Measurements and analysis of IP-TV
Characterizing performance of multi-core Web servers
Peer-assisted video streaming
Slide5Possible Project Ideas
Wavelet-based traffic modeling/forecasting
DASH-based video streaming
Multi-path TCP (MPTCP) performance
Wavelength assignment in WDM optical networks
Energy efficient routing in WSNs
Office 365 email traffic characterization
DNS-based attacks on U of C network
HTTP/2.0 deployment and performance
D2L caching and/or content acceleration
Design and performance of Netflix CDN
PyeongChang
2018 video streaming traffic
Social network analysis and visualization
Slide6Experimental Equipment
Rack-mounted clients and servers
Several routers and switches
WiMAX modem
Web proxy caching appliance
Wireless laptops, PDAs, and APs
Wireless network analyzers
Gigabit Ethernet LAN analyzer
Wireless video cameras
Wireless sensor motes
Access to SAVI national testbed for SDN
Slide7Some Available Simulators
ns-2 network simulator (TCP packet level)
ns-3 network simulator
OMNET++ simulator
Web proxy caching simulator
ATM-TN simulator (ATM cell-level)
IP-TN simulator (U of C)
IP-TNE network emulator (U of C)
Mininet
network emulator
Speed scaling simulator
Slide8Some Useful Software Tools
Synthetic Web proxy workload generation
Web client traffic model (mosaic, 1995)
LRD traffic analysis (R/S, V-T, AC,
etc
)
GUI for traffic modeling/analysis (
synTraff
)
Wavelet-based traffic model (MWM)
Synthetic MPEG video trace generation
GISMO (Generator for Internet Streaming Media Objects)
BRITE Internet Topology Emulator
netalyzr
tool for benchmarking network paths
tcpanaly
tool for TCP trace analysis
Slide9Public Traces and Data Sets
CRAWDAD: Community Resource for Archiving Wireless Data at Dartmouth (
crawdad.cs.dartmouth.edu
)
CAIDA: Cooperative Association for Internet Data Analysis (
www.caida.org
)
Internet Traffic Archive (
ita.ee.lbl.gov
)
Bellcore
Ethernet LAN trace (1989)
LBL TCP/IP packet traces (1990)
Web server access logs (1996)
Slide10Local U of C Datasets
Connection-level summary logs for U of C inbound/outbound Internet traffic (hourly/daily/monthly for 10+ years)
UcalgaryBlogs
Web server access log
Carey’s email archives (3 years of data)
Slide11Dataset #1: UCalgaryBlogs Web Server
What: about 16 months of Web server access log data from
UCalgaryBlogs
Web server (1 GB .
gz
file)
Objective: characterization of Web site usage
Possible analyses:
Which of the hosted Web sites get the most activity?
Popularity analysis (URL based,
Zipf
-like distributions)
Traffic analysis (volume, time of day, day of week, sizes)
Longitudinal analysis (growth trends, seasonal effects)
Geographical analysis (IP geolocation of Web clients)
Security analysis (denial of service attacks)
D2L analysis (logout activity)
Slide12Example: Data Format
188.143.232.27 - - [24/Jan/2016:03:15:26 -0700] "GET /2013/03/04/
krazy
-
kats
-remarkably-changing-dynamics/ HTTP/1.1" 200
8054 "-" "Mozilla/5.0 (Windows NT 6.1; WOW64)
AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36"
188.143.234.155 - - [24/Jan/2016:03:15:26 -0700] "GET /2013/04/24/manga-vs-comics-another-perspective/ HTTP/1.1" 200 11835
"-" "Mozilla/5.0 (Windows NT 6.1; WOW64)
AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36"
195.154.199.128 - - [24/Jan/2016:03:15:26 -0700] "POST /
wp-login.php
HTTP/1.1" 200 4216 "http://richardzach.org/
wp
-login.
php
" "Mozilla/4.0 (compatible; MSIE 9.0; Windows NT 6.1; 125LA; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.
21022)"
70.180.122.48 - - [24/Jan/2016:03:15:26 -0700] "POST /
wp-signup.php
HTTP/1.0" 200 31441 "http://ucalgaryblogs.ca/
wp-signu
p.php?action
=register" "Opera/9.80 (Windows NT 6.2; Win64; x64) Presto/2.12.388 Version/12.17"
195.154.199.128 - - [24/Jan/2016:03:15:28 -0700] "POST /
wp-login.php
HTTP/1.1" 200 4216 "http://richardzach.org/
wp
-login.
php
" "Mozilla/4.0 (compatible; MSIE 9.0; Windows NT 6.1; 125LA; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.
21022)"
188.143.232.32 - - [24/Jan/2016:03:15:30 -0700] "GET /2013/02/27/why-the-web-slinger/ HTTP/1.1" 200 11605 "-" "Mozilla/5.
0 (Windows NT 6.1; WOW64)
AppleWebKit
/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36"
195.154.199.128 - - [24/Jan/2016:03:15:29 -0700] "POST /
wp-login.php
HTTP/1.1" 200 4216 "http://richardzach.org/
wp
-login.
php
" "Mozilla/4.0 (compatible; MSIE 9.0; Windows NT 6.1; 125LA; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.
21022)"
Slide13Dataset #2: Email Archive
What: about 3 years of “sent-mail” archive (1 GB) recorded by the pine mail reading client on Linux
Objective: characterization of email usage
Possible analyses:
“The Email Chronicles: A Year in the Life of a CPSC Head”
Workload characterization (volume, size, attachments)
Temporal analysis of email usage (date timestamps)
Topical analysis (subject header for theme river analysis)
Social network analysis (CPSC,
FoS
,
UofC
, research,
etc
)
Seasonal analysis (spiral model a la Charles Perrin)
Note: Confidentiality agreement would be required before working with this data
Slide14Example: Metadata
Date: Thu, 1 Jan 2015 11:50:14 -0700 (MST)
From: Carey Williamson <carey@cpsc.ucalgary.ca>
To: Ken Barker <kbarker@ucalgary.ca>
Subject: Re: What to include in the Executive Summary?
Date: Thu, 1 Jan 2015 12:54:55 -0700 (MST)
From: Carey Williamson <carey@cpsc.ucalgary.ca>
To: Ken Barker <kbarker@ucalgary.ca>
Subject: Re: Unit Reviewers
Date: Fri, 2 Jan 2015 08:57:13 -0700 (MST)
From: Carey Williamson <carey@cpsc.ucalgary.ca>
To:
Niklas
Carlsson <nikca@ida.liu.se>
Subject: Re: Happy New Year 2015
Date: Fri, 2 Jan 2015 10:28:12 -0700 (MST)
From: Carey Williamson <carey@cpsc.ucalgary.ca>
To: Carey Williamson <carey@ucalgary.ca>
Subject: [Hiring-
cpsc
-l] CRC Advertisements for Revision (
fwd
)
Date: Tue, 1 Oct 2013 09:50:05
From: Erin
Moloney
<moloney@ucalgary.ca>
To: "hiring@cpsc.ucalgary.ca" <hiring@cpsc.ucalgary.ca>
Subject: [Hiring-
cpsc
-l] CRC Advertisements for Revision