|
On this page are downloads of data-sets, traces, source code,
utilities and multimedia files that have been used in our research.
If you download and use any of the below in any research, please let
us (claypool@cs.wpi.edu)
know. Most can be extracted via "gzip -dc filename.tgz | tar xf
-
" or via "unzip filename.zip
". Have fun!
We did some experiments measuring the effects of latency on user performance in Age of Mythology. You can download the maps we used as well as some network traces.
Used in:
Mark Claypool. The Effect of Latency on User Performance in Real-Time Strategy Games, Elsevier Computer Networks, special issue on Networking Issues in Entertainment Computing, Volume 49, Issue 1, Pages 52-70, September 2005. Online at: http://www.cs.wpi.edu/~claypool/papers/rts/
We wrote some software that can measure the battery drain rate on a laptop PC. You can download the Visual C++ source code (with executable already made) here:
We did some experiments measuring the effects of latency on user performance in Command and Conquer: Generals. You can download some network traces here.
Used in:
Mark Claypool. The Effect of Latency on User Performance in Real-Time Strategy Games, Elsevier Computer Networks, special issue on Networking Issues in Entertainment Computing, Volume 49, Issue 1, Pages 52-70, September 2005. Online at: http://www.cs.wpi.edu/~claypool/papers/rts/
CStream (Collaborative Streaming) is a system that aggregates bandwidth from multiple cooperating users in a neighborhood. When a user streams a video, CStream aggregates bandwidth by connecting to nearby cooperating users and use their Internet connection in addition to the user's own connection.
Used in:
Thangam Vedagiri Seenivasan. CStream: Neighborhood Bandwidth Aggregation For Better Video Streaming, M.S. Thesis, Computer Science Department, Worcester Polytechnic Institute, Spring 2010. (Advisor Mark Claypool) Online at: http://www.cs.wpi.edu/~claypool/ms/cstream/
An implementation of CUBIC in ns-3, designed based on the current literature describing the CUBIC algorithm and an examination of source code in the Linux kernel. TCP CUBIC, the default TCP congestion control algorithm in the Linux kernel and, given the popularity of Linux servers, one of the most widely used variants of TCP in use.
(Earlier versions can be found here.)
Used in:
Brett Levasseur, Mark Claypool, and Robert Kinicki. A TCP CUBIC Implementation in ns-3, In Proceedings of the Workshop on ns-3 (WNS3), Atlanta, GA, USA, May 7, 2014. Online at: http://www.cs.wpi.edu/~claypool/papers/tcp-cubic/
D-CBT is an router queue management mechanism that extends RED by having three classes of traffic: TCP, UDP and tagged UDP (multimedia). It provides fairness among the classes of flows using dynamic thresholds for each class.
NS version:
Used in:
Jae Chung and Mark Claypool. Dynamic-CBT - Better Performing Active Queue Management for Multimedia Networking, In Proceedings of the Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), Chapel Hill, NC, USA, June 25-28, 2000.
Jae Chung and Mark Claypool. Dynamic-CBT and ChIPS - Router Support for Improved Multimedia Performance on the Internet, In Proceedings of ACM Multimedia, Los Angeles, CA, USA, November 2000.
Linux version:
Used in:
Brian Conway, Charles McAuley, and Jonathan Yurek. Evaluation of DCBT. MQP-MLC-LR01, Spring 2002. (Advisor Mark Claypool) http://www.cs.wpi.edu/~claypool/mqp/dcbt-eval/
We have design and implemente a streaming system (client and server) called Goddard for use in the NS simulator. Goddard is designed based on the behaviors of Real Networks streaming media and Windows Stream media, as observed in measurements studies from work at the Video Tracer project page.
Used in:
Jae Chung, Mark Claypool, and Robert Kinicki. MTP: A Streaming-Friendly Transport Protocol, Technical Report WPI-CS-TR-05-10, Computer Science Department, Worcester Polytechnic Institute, May 2005. Online at: ftp://ftp.cs.wpi.edu/pub/techreports/pdf/05-10.pdf
(Note, the system is named after Robert Goddard, the "Father of Modern Rocketry", and a WPI alumnus.)
Some of the research in our REFER group is looking at the correlation between user Web browsing actions (implicit interest) with explicit interest. We built a Web browser (called Curious Browser) that records scrolling, access time, mouse movement and mouse clicks, conducted user tests with a bunch of volunteers, and analyzed the gathered data. The Curious Browser and the dataset collected is available below.
Used in:
Mark Claypool, David Brown, Phong Le, and Makoto Waseda. Inferring User Interest, IEEE Internet Computing, November/December 2001. Online at: http://www.cs.wpi.edu/~claypool/papers/iui/
Mark Claypool, Phong Le, Makoto Waseda, and David Brown, Implicit Interest Indicators, In Proceedings of ACM Intelligent User Interfaces Conference (IUI), Santa Fe, New Mexico, January 14-17, 2001. Winner! Best paper award.
We studied the effects of latency on Madden Football. We also captured some network traces, which you can look at here.
Used in:
James Nichols and Mark Claypool. The Effects of Latency on Online Madden NFL Football, In Proceedings of the 14th ACM International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), Kinsale, County Cork, Ireland, June 16-18, 2004. Online at: http://www.cs.wpi.edu/~claypool/papers/madden/
MM-Flow is a set of rate-based applications for NS that use AIMD congestion control built on top of UDP. They are designed for better-performing yet responsive multimedia applications. We've implemented them in NS. Note, these are included with the ns-2 tree if you download D-CBT above.
Used in:
Jae Chung and Mark Claypool, Better-Behaved, Better-Performing Multimedia Networking, SCS Euromedia Conference, Antwerp, Belgium, May 8-10, 2000.
Each movie clip was recorded from a VCR using a Video ATI All-in-one capture card into AVI format then converted into MPEG-1. Each clip is about 60 seconds long and 10 MBytes in size.
Used in:
Mark Claypool and Jonathan Tanner, The Effects of Jitter on the Perceptual Quality of Video, ACM Multimedia Conference, Volume 2, Orlando, FL, October 30 - November 5, 1999.
Yanlin Liu and Mark Claypool, Video Redundancy - A Best-Effort Solution to Network Data Loss, Technical Demonstration at the ACM Multimedia Conference, Volume 2, Orlando, FL, October 30 - November 5, 1999.
Yanlin Liu and Mark Claypool, Using Redundancy to Repair Video Damaged by Network Data Loss, ACM Multimedia Computing and Networking, San Jose, CA, January 25-27, 2000.
Brandon Ngo and Lisa Zhang, Tuning Video
Redundancy, Major Qualifying Project MQP-MLC-MQ99, Spring
2000.
The benchmark source code here can be used to evaluate the performance of MPFS file systems.
Used in:
Yubing Wang and Mark Claypool. An Adaptable Benchmark for MPFS Performance Testing, Technical Report WPI-CS-TR-02-14, Computer Science Department, Worcester Polytechnic Institute, May 2002. Online at: ftp://ftp.cs.wpi.edu/p ub/techreports/pdf/02-14.pdf
kernel/knistnet.c
source
code file. You can download the source code below and read about
compilation and installation on the NIST Net page, as they remain the
same.
We measured the turbulence (size and distribution of network packets) for the OnLive thin client game system for 3 games. We compared them to 2-person Skype video and Youtube. Traces can be found here.
Used in:
Mark Claypool, David Finkel, Alexander Grant and Michael Solano. Thin to Win? Network Performance Analysis of the OnLive Thin Client Game System, In Proceedings of the 11th ACM Network and System Support for Games (NetGames), Venice, Italy, November 2012. Online at: http://www.cs.wpi.edu/~claypool/papers/onlive/
The results data we obtained (minus the ping distributions) from our QFind measurements are available here.
Used in:
Mark Claypool, Robert Kinicki, Mingzhe Li, James Nichols, and Huahui Wu. Inferring Queue Sizes in Access Networks by Active Measurement, In Proceedings of the 5th Passive and Active Measurement Workshop (PAM), Antibes Juan-les-Pins, France, April 2004. Online at: http://www.cs.wpi.edu/~claypool/papers/qfind/
Receiver Based Auto Rate (RBAR), proposed by Holland et al. in "A Rate-adaptive MAC Protocol for Multi-hop Wireless Networks" (Proceedings of Mobile Computing and Networking, 2001), uses analysis of RTS frames to measure channel quality. RBAR receivers determine the highest feasible frame transmission rate that channel conditions can tolerate and notify the sender of the chosen rate via the CTS frame. Since RTS/CTS messages are sent to the AP, all wireless nodes become aware of the new transmission rate and set their backoff timers accordingly.
Unfortunately, this algorithm is not integrated into ns-2 releases. However, an RBAR simulation module for ns-2 2.1b7 is downloadable from the Rice Networks Group. We re-implemented RBAR in NS 2.27 and extended the physical layer parameters using the specifications of the Lucent OriNOCO wireless PC card. Our implementation can be found here with documentation.
By default, ns-2 provides a two-way ground propagation module. To more accurately simulate physical condition effects on RCAs, an additional ns-2 extension module was implemented that models Ricean (or Rayleigh) fading (Punnoose et al. in Proceedings Vehicular Technology Conference, 2000).
Selective Flooding is a QoS routing algorithm checks the state of the links on a set of pre-computed routes from the source to the destination in parallel and based on this information computes the best route and then reserves resources. We implemented Selective Flooding by extending a QoS routing simulator. That simulator is available here:
Used in:
Mark Claypool and Gangadharan Kannan. Selective Flooding for Improved Quality-of-Service Routing, In Proceedings of SPIE Quality of Service over Next-Generation Data Networks (part of ITCom), Denver, Colorado, USA, August 2001. http://www.cs.wpi.edu/~claypool/papers/hsf/
Gangadharan Kannan. Selective Flooding for Improved Quality-of-Service Routing, M.S. Thesis, Computer Science Department, Worcester Polytechnic Institute, Spring 2000. (Advisor Mark Claypool)
Selective Retransmission Protocol (SRP) balances the potentially high loss found in UDP with the potentially high latency found in TCP. SRP uses an application-specific decision algorithm (based on an audioconference in this implementation) to determine whether or not to ask for a retransmission for a lost packet, adjusting the loss and latency to the optimum level for the application.
Linux version:
Used in:
Mike Piecuch, Ken French, George Oprica and Mark Claypool, A Selective Retransmission Protocol for Multimedia on the Internet, In Proceedings of SPIE Multimedia Systems and Applications, Boston, MA, USA, November 5-8, 2000.
The increasing use of end-to-end encryption (e.g., TSL/SSL) makes it difficult to identify video flows even with deep packet inspection (DPI). Silhouette is a real-time, lightweight video classification mechanism that uses only flow statistics (i.e., "shape") for video identification making it payload-agnostic, effective for identifying video flow even when encrypted.
Used in:
Feng Li, Jae Chung and Mark Claypool. Silhouette - Identifying YouTube Video Flows from Encrypted Traffic, In Proceedings of the 28th ACM International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), Amsterdam, The Netherlands, June 2018. Online at: http://www.cs.wpi.edu/~claypool/papers/yt-crawler/
Network games are becoming increasingly popular, but their traffic patterns have received little attention from the academic research community. We have examined network traffic from Counter-Strike and Starcraft thus far. The Commview traces and a parsing tool are available here.
Used in:
Mark Claypool, David LaPoint, and Josh Winslow. Network Analysis of Counter-strike and Starcraft, In Proceedings of the 22nd IEEE International Performance, Computing, and Communications Conference (IPCCC), Phoenix, Arizona, USA, April 2003. Online at: http://www.cs.wpi.edu/~claypool/papers/net-game/
Mark Claypool, David LaPoint and Josh Winslow. Network Analysis of Counter-strike and Starcraft, Technical Report WPI-CS-TR-02-04, Computer Science Department, Worcester Polytechnic Institute, January 2002. ftp://ftp.cs.wpi.edu/pub/techreports/pdf/02-04.pdf
Dave LaPoint and Josh Winslow. Analyzing and Simulating Network Game Traffic, Major Qualifying Project MQP-MLC-NG01, Computer Science Department, Fall 2001. (Advisor Mark Claypool)
Stats is designed to be a quick, simple to use program as a Unix filter to generate the summary statistics.
UDP Ping, UDP Heartbeat and UDP Load are customized ping tools using application-layer UDP packets to provide delay, loss and throughput information. UDP Ping reports round-trip time information while UDP Heartbeat reports one-way link information. UDP Load provides throughput information. Both require applications to be run on the end-hosts.
Download source, README and executables (windows):
See also:
In studying FPS games under network degrdataions, we've looked at UT2003. We ran multiple full-length games with one player matched against two bots on a small standard map (DM-GAEL) with four different conditions of packet loss and latency. For each game, we captured all network packets for 120 seconds during the middle of the 5 minute match. You can get the tcpdump traces here:
Used in:
Tom Beigbeder, Rory Coughlan, Corey Lusher, John Plunkett, Emmanuel Agu, and Mark Claypool. The Effects of Loss and Latency on User Performance in Unreal Tournament 2003, In Proceedings of ACM Network and System Support for Games Workshop (NetGames), Portand, OG, USA, September 2004. Online at: http://www.cs.wpi.edu/~claypool/papers/ut2003/
We crawled the Internet from many carefully selected starting points in an effort to characterize vidoes stored on the Web. You can download the URLs we crawled and the video URLs we found.
Used in:
Mingzhe Li, Mark Claypool, Robert Kinicki and James Nichols. Characteristics of Streaming Media Stored on the Web, ACM Transactions on Internet Technology (TOIT), Volume 5, Number 4, pages 601-626, November 2005. Online at: http://www.cs.wpi.edu/~claypool/papers/video-crawler/
We did some experiments measuring the effects of latency on user performance in Warcraft III. You can download the maps we used as well as some network traces.
Used in:
Nathan Sheldon, Eric Girard, Seth Borg, Mark Claypool, and Emmanuel Agu. The Effect of Latency on User Performance in Warcraft III, In Proceedings of ACM NetGames, Redwood City, CA, USA, May 2003. Online at: http://www.cs.wpi.edu/~claypool/papers/war3/
Mark Claypool. The Effect of Latency on User Performance in Real-Time Strategy Games, Elsevier Computer Networks, special issue on Networking Issues in Entertainment Computing, Volume 49, Issue 1, Pages 52-70, September 2005. Online at: http://www.cs.wpi.edu/~claypool/papers/rts/
WBest is a wireless bandwidth estimation tool designed for applications that requires fast convergence time and low intrusiveness, such as multimedia streaming applications. WBest employs packet dispersion techniques to provide capacity and available bandwidth information for the underlying wireless networks.
Used in:
Mingzhe Li, Mark Claypool and Robert Kinicki. WBest: a Bandwidth Estimation Tool for IEEE 802.11 Wireless Networks, In Proceedings of the 33rd IEEE Conference on Local Computer Networks (LCN), Montreal, Quebec, Canada, October 2008. Online at: http://www.cs.wpi.edu/~claypool/papers/wbest/
WRAPI+ is a tool to monitor wireless statistics, including received signal strength, transmitted frame count, and failed frame transmissions and acknowledgments on a Windows XP end hosts' IEEE 802.11b/g network device. WRAPI+ was built upon the freely available WRAPI C++ library.
Download (for Windows XP):
Used in:
Feng Li, Mingzhe Li, Rui Lu, Huahui Wu, Mark Claypool, and Robert Kinicki. Tools and Techniques for Measurement of IEEE 802.11 Wireless Networks, In Proceedings of the Second International Workshop On Wireless Network Measurement (WiNMee), Boston, MA, USA, April 2006. Online at: http://www.cs.wpi.edu/~claypool/papers/tools/
See also:
We built a YouTube crawler that samples Internet videos by selecting and crawling through several video channels each day. We ran our crawler from 2018-2020 (so far) and provide the dataset here.
Used in:
Feng Li, Jae Chung and Mark Claypool. Three-year Trends in YouTube Video Content and Encoding, In Proceedings the 18th International Conference on Signal Processing and Multimedia Applications (SIGMAP), Virtual Conference, July 6-8, 2021. Online at: http://www.cs.wpi.edu/~claypool/papers/youtube-crawler-21/