Abstract
In this article, we take advantage of the user behavior of requesting videos from the top of the related list provided by YouTube to improve the performance of YouTube caches. We recommend that local caches reorder the related lists associated with YouTube videos, presenting the cached content above noncached content. We argue that the likelihood that viewers select content from the top of the related list is higher than selection from the bottom, and pushing contents already in the cache to the top of the related list would increase the likelihood of choosing cached content. To verify that the position on the list really is the selection criterion more dominant than the content itself, we conduct a user study with 40 YouTube-using volunteers who were presented with random related lists in their everyday YouTube use. After confirming our assumption, we analyze the benefits of our approach by an investigation that is based on two traces collected from a university campus. Our analysis shows that the proposed reordering approach for related lists would lead to a 2 to 5 times increase in cache hit rate compared to an approach without reordering the related list. This increase in hit rate would lead to reduction in server load and backend bandwidth usage, which in turn reduces the latency in streaming the video requested by the viewer and has the potential to improve the overall performance of YouTube's content distribution system. An analysis of YouTube's recommendation system reveals that related lists are created from a small pool of videos, which increases the potential for caching content from related lists and reordering based on the content in the cache.
- V. K. Adhikari, S. Jain, Yingying Chen, and Zhi-Li Zhang. 2012. Vivisecting YouTube: An active measurement study. In Proceedings of the 31st IEEE INFOCOM. IEEE, 2521--2525. DOI:http://dx.doi.org/10.1109/INFCOM.2012.6195644Google Scholar
Cross Ref
- V. K. Adhikari, S. Jain, and Zhi-Li Zhang. 2011. Where do you “Tube”? Uncovering YouTube server selection strategy. In Proceedings of the 20th IEEE ICCCN. IEEE, 1--6. DOI:http://dx.doi.org/10.1109/ICCCN.2011.6006028Google Scholar
- Amos Azaria, Avinatan Hassidim, Sarit Kraus, Adi Eshkol, Ofer Weintraub, and Irit Netanely. 2013. Movie recommender system for profit maximization. In Proceedings of the 7th ACM Conference on Recommender Systems. ACM, 121--128. Google Scholar
Digital Library
- Meeyoung Cha, Haewon Kwak, Pablo Rodriguez, Yongyeol Ahn, and Sue Moon. 2007. I tube, you tube, everybody tubes: Analyzing the world's largest user generated content video system. In Proceedings of the Internet Measurement Conference (IMC'07). ACM, 1--14. Google Scholar
Digital Library
- J. Chakareski. 2011. Browsing catalogue graphs: Content caching supercharged!!. In Proceedings of the 8th International Conference on Image Processing. IEEE, 2429--2432. DOI:http://dx.doi.org/10.1109/ICIP.2011.6116134Google Scholar
- Xu Cheng and Jiangchuan Liu. 2009. NetTube: Exploring social networks for peer-to-peer short video sharing. In Proceedings of the 28th IEEE INFOCOM. IEEE, 1152--1160.Google Scholar
Cross Ref
- Xu Cheng, Jiangchuan Liu, and Haiyang Wang. 2009. Accelerating YouTube with Video Correlation. In Proceedings of the 1st SIGMM Workshop on Social Media. IEEE, 49--56. DOI:http://dx.doi.org/10.1145/1631144.1631156 Google Scholar
Digital Library
- W. J. Conover. 1999. Practical Nonparametric Statistics (3rd. Ed.). Wiley. 388--395.Google Scholar
- James Davidson, Benjamin Liebald, Junning Liu, et al. 2010. The YouTube video recommendation system. In Proceedings of the 4th ACM Conference on Recommender Systems (RecSys'10). ACM, 293--296. Google Scholar
Digital Library
- FilterProxy. 2001. HTTP Proxy. http://filterproxy.sourceforge.net/.Google Scholar
- Google. 2012. Googletransparencyreport. http://www.google.com/transparencyreport/traffic/explorer/?r=US&l==YOUTUBE&csd==1389835560000&ced==1391045160000 (Last accessed Aug. 2014).Google Scholar
- KendallCoefficient. 2014. Kendall Tau Rank Correlation Coefficient. http://en.wikipedia.org/wiki/Kendall_tau_rank_correlation_coefficient (Last accessed Aug. 2014).Google Scholar
- Samamon Khemmarat, Renjie Zhou, Lixin Gao, and Michael Zink. 2011. Watching user generated videos with prefetching. In Proceedings of the 2nd Annual ACM Conference on Multimedia Systems. IEEE, 187--198. Google Scholar
Digital Library
- Donald E. Knuth. 1998. The Art of Computer Programming, volume 3: Sorting and Searching (2nd Ed.). Addison Wesley Longman Publishing Co., Inc., Redwood City, CA. Google Scholar
Digital Library
- Dilip Kumar Krishnappa, Michael Zink, and Carsten Griwodz. 2013a. What should you cCache?: A global analysis on YouTube related video caching. In Proceedings of the 23rd ACM Workshop on Network and Operating Systems Support for Digital Audio and Video. ACM, 31--36. Google Scholar
Digital Library
- Dilip Kumar Krishnappa, Michael Zink, Carsten Griwodz, and Påal Halvorsen. 2013b. Cache-centric video recommendation: An approach to improve the efficiency of YouTube caches. In Proceedings of the 4th ACM Multimedia Systems Conference. ACM, 261--270. Google Scholar
Digital Library
- Muffin. 2012. World Wide Web Filtering System. http://muffin.doit.org/(Last accessed Aug. 2014).Google Scholar
- NetworkMonitor. 2014. Endace DAG network monitoring interface. http://www.emulex.com/products/network-visibility-products-and-services/endacedag-data-capture-cards/features/(Last accessed Aug. 2014).Google Scholar
- Opera. 2012. Mobile Browser. http://www.opera.com/mobile/(Last accessed Aug. 2014).Google Scholar
- Andreas Papadakis, Theodore Zahariadis, and George Mamais. 2013. Advanced content caching schemes and algorithms. Adv. Electronics Telecommunications 3, 5.Google Scholar
- PlanetLab. 2007. PlanetLab Portal. http://planet-lab.org/.Google Scholar
- Stefan Podlipnig and Laszlo Böszörmenyi. 2003. A survey of web cache replacement strategies. ACM Comput. Surv. 35, 4 (2003), 374--398. Google Scholar
Digital Library
- YouTube. 2014a. YouTube Video Logger Chrome Plugin. https://chrome.google.com/webstore/detail/video-logger/nhilghfofbfdemgllaekjpkajmjemobb (Last accessed Aug. 2014).Google Scholar
- YouTube. 2014b. Vimeo Vs YouTube. http://www.business2community.com/youtube/vimeo-vs-youtube-will-winner-emerge-2014-infographic-0864787 (Last accessed Dec. 2014).Google Scholar
- TcpDump. 2010. Network packet analyzer. http://www.tcpdump.org/(Last accessed Aug. 2014).Google Scholar
- WebCleaner. 2010. A Filtering HTTP-Proxy.). http://webcleaner.sourceforge.net/(Last accessed Aug. 2014).Google Scholar
- Byungjoon Yoo and Kwansoo Kim. 2012. Does popularity decide rankings or do rankings decide popularity? An investigation of ranking mechanism design. Electron. Commerce Research Appl. 11, 2, 180--191. Google Scholar
Digital Library
- YouTube. 2007. YouTubeAPI. https://developers.google.com/youtube/.Google Scholar
- YouTube. 2012a. YouTube Keynote of MMSYS 2012. https://docs.google.com/presentation/pub?id=1bMLitOefxARBbgcu1v1xaJj89hbJGXYse17Xvgwro&start==false&loop==false&delayms==3000#slide=id.g47538e9_2_210 (Last accessed Aug. 2014).Google Scholar
- YouTube. 2012b. YouTube press Statistics. http://www.youtube.com/yt/press/statistics.html (Last accessed Aug. 2014).Google Scholar
- Renjie Zhou, Samamon Khemmarat, and Lixin Gao. 2010. The impact of YouTube recommendation system on video views. In Proceedings of the 10th ACM SIGCOMM conference on Internet measurement. ACM, 404--410. DOI:http://dx.doi.org/10.1145/1879141.1879193 Google Scholar
Digital Library
- Renjie Zhou, Samamon Khemmarat, Lixin Gao, and Huiqiang Wang. 2011. Boosting video popularity through recommendation systems. In Proceedings of Databases and Social Networks. ACM, 13--18. DOI:http://dx.doi.org/10.1145/1996413.1996416 Google Scholar
Digital Library
- Michael Zink, Kyoungwon Suh, Yu, and James Kurose. 2009. Characteristics of YouTube network traffic at a campus network: Measurements, models, and implications. Elsevier Computer Networks 53, 4, 501--514. Google Scholar
Digital Library
Index Terms
Cache-Centric Video Recommendation: An Approach to Improve the Efficiency of YouTube Caches
Recommendations
Cache-centric video recommendation: an approach to improve the efficiency of YouTube caches
MMSys '13: Proceedings of the 4th ACM Multimedia Systems ConferenceIn this paper, we take advantage of the user behavior of requesting videos from the related list provided by YouTube and the user behavior of requesting videos from the top of this related list to improve the performance of YouTube's caches. We ...
Modeling LRU cache with invalidation
Least Recently Used (LRU) is a very popular caching replacement policy. It is very easy to implement and offers good performance, especially when data requests are temporally correlated, as in the case of web traffic.When the data content can change ...
Cache "less for more" in information-centric networks
IFIP'12: Proceedings of the 11th international IFIP TC 6 conference on Networking - Volume Part IUbiquitous in-network caching is one of the key aspects of information-centric networking (ICN) which has recently received widespread research interest. In one of the key relevant proposals known as Networking Named Content (NNC), the premise is that ...






Comments