Abstract
The performance of Adaptive Bitrate (ABR) algorithms for video streaming depends on accurately predicting the download time of video chunks. Existing prediction approaches (i) assume chunk download times are dominated by network throughput; and (ii) apriori cluster sessions (e.g., based on ISP and CDN) and only learn from sessions in the same cluster. We make three contributions. First, through analysis of data from real-world video streaming sessions, we show (i) apriori clustering prevents learning from related clusters; and (ii) factors such as the Time to First Byte (TTFB) are key components of chunk download times but not easily incorporated into existing prediction approaches. Second, we propose Xatu, a new prediction approach that jointly learns a neural network sequence model with an interpretable automatic session clustering method. Xatu learns clustering rules across all sessions it deems relevant, and models sequences with multiple chunk-dependent features (e.g., TTFB) rather than just throughput. Third, evaluations using the above datasets and emulation experiments show that Xatu significantly improves prediction accuracies by 23.8% relative to CS2P (a state-of-the-art predictor). We show Xatu provides substantial performance benefits when integrated with multiple ABR algorithms including MPC (a well studied ABR algorithm), and FuguABR (a recent algorithm using stochastic control) relative to their default predictors (CS2P and a fully connected neural network respectively). Further, Xatu combined with MPC outperforms Pensieve, an ABR based on deep reinforcement learning.
- Can I stream Netflix in ultra hd? https://help.netflix.com/en/node/13444.Google Scholar
- Chrome Remote Interface. https://github.com/cyrus-and/chrome-remoteinterface.Google Scholar
- Cisco Visual Networking Index: Forecast and Trends, 2017--2022 White Paper. https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11--741490.html.Google Scholar
- Cisco Visual Networking Index: Forecast and Trends, 2017--2022 White Paper. https://apps.fcc.gov/edocs_public/attachmatch/FCC-18--10A1.pdf.Google Scholar
- DASH IF Test Assets Database. http://testassets.dashif.org/#testvector/list.Google Scholar
- DASH Industry Forum: Dash.js. http://dashif.org/reference/players/javascript/1.4.0/samples/dash-if-reference-player/.Google Scholar
- Fugu Github. https://github.com/StanfordSNR/puffer.Google Scholar
- Google-Chrome: Chrome DevTools Protocol. https://chromedevtools.github.io/ devtools-protocol/tot/Network/.Google Scholar
- hmmlearn. https://hmmlearn.readthedocs.io/en/latest/#.Google Scholar
- New research reveals buffer rage as tech's newest epidemic. https://www.prnewswire.com/news-releases/new-research-reveals-buffer-rage-as-techs-newest-epidemic-300237001.html.Google Scholar
- Pensieve Github. https://github.com/hongzimao/pensieve.Google Scholar
- Principal component analysis. https://en.wikipedia.org/wiki/Principal_component_analysis.Google Scholar
- PyTorch. https://pytorch.org/.Google Scholar
- Reduce CloudFront Latency "X-Cache: Miss from cloudfront". https://aws.amazon.com/premiumsupport/knowledge-center/cloudfront-latency-xcache/.Google Scholar
- Understanding cache HIT and MISS headers with shielded services. https://docs.fastly.com/guides/performance-tuning/understanding-cache-hit-and-miss-headers-with-shielded-services.Google Scholar
- US Alexa Rank. https://www.alexa.com/topsites/countries/US.Google Scholar
- Using akamai pragma headers to investigate or troubleshoot akamai content delivery. https://community.akamai.com/customers/s/article/Using-Akamai-Pragma-headers-to-investigate-or-troubleshoot-Akamai-content-delivery?language=en_US.Google Scholar
- Z. Akhtar, Y. S. Nam, R. Govindan, S. Rao, J. Chen, E. Katz-Bassett, B. Ribeiro, J. Zhan, and H. Zhang. Oboe: Auto-tuning video abr algorithms to network conditions. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, SIGCOMM '18, pages 44--58, New York, NY, USA, 2018. ACM.Google Scholar
Digital Library
- B. Alt, T. Ballard, R. Steinmetz, H. Koeppl, and A. Rizk. Cba: Contextual quality adaptation for adaptive bitrate video streaming (extended version). arXiv preprint arXiv:1901.05712, 2019.Google Scholar
- A. Azzouni and G. Pujolle. Neutm: A neural network-based framework for traffic matrix prediction in sdn. In NOMS 2018--2018 IEEE/IFIP Network Operations and Management Symposium, pages 1--5. IEEE, 2018.Google Scholar
Digital Library
- M. Bartulovic, J. Jiang, S. Balakrishnan, V. Sekar, and B. Si nopoli. Biases in Data-Driven Networking, and What to Do About Them. In Proceedings of the 16th ACM Workshop on Hot Topics in Networks - HotNets- XVI, pages 192--198, Palo Alto, CA, USA, 2017. ACM Press.Google Scholar
Digital Library
- N. Cardwell, Y. Cheng, C. S. Gunn, S. H. Yeganeh, and V. Jacobson. Bbr: Congestion-based congestion control. ACM Queue, 14, pages 20----53, 2016.Google Scholar
- F. Chiariotti, S. D'Aronco, L. Toni, and P. Frossard. Online learning adaptation strategy for dash clients. In Proceedings of the 7th International Conference on Multimedia Systems, MMSys '16, pages 8:1--8:12, New York, NY, USA, 2016. ACM.Google Scholar
Digital Library
- K. Cho, B. Van Merriënboer, D. Bahdanau, and Y. Bengio. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259, 2014.Google Scholar
- M. Claeys, S. Latré, J. Famaey, T. Wu, W. Van Leekwijck, and F. De Turck. Design of a q-learning-based client quality selection algorithm for http adaptive video streaming. In Proceedings of the 2013 Workshop on Adaptive and Learning Agents (ALA), Saint Paul (Minn.), USA, pages 30--37, 2013.Google Scholar
- M. Claeys, S. Latré, J. Famaey, T. Wu, W. Van Leekwijck, and F. De Turck. Design and optimisation of a (fa) q-learning-based http adaptive streaming client. Connection Science, 26(1):25--43, 2014.Google Scholar
Digital Library
- J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.Google Scholar
- A. Elgabli, V. Aggarwal, S. Hao, F. Qian, and S. Sen. Lbp: Robust rate adaptation algorithm for svc video streaming. IEEE/ACM Transactions on Networking, 26(4):1633--1645, 2018.Google Scholar
Digital Library
- C. Esteban, O. Staeck, S. Baier, Y. Yang, and V. Tresp. Predicting clinical events by combining static and dynamic information using recurrent neural networks. In 2016 IEEE International Conference on Healthcare Informatics (ICHI), pages 93--101. IEEE, 2016.Google Scholar
Cross Ref
- A. Ganjam, F. Siddiqui, J. Zhan, X. Liu, I. Stoica, J. Jiang, V. Sekar, and H. Zhang. C3: Internet-scale control plane for video quality optimization. In 12th Symposium on Networked Systems Design and Implementation NSDI '15), pages 131--144, 2015.Google Scholar
- E. Ghabashneh and S. Rao. Exploring the interplay between cdn caching and video streaming performance. In 2020 IEEE Conference on Computer Communications (INFOCOM). IEEE, 2020.Google Scholar
Digital Library
- M. Ghasemi, P. Kanuparthy, A. Mansy, T. Benson, and J. Rexford. Performance characterization of a commercial video streaming service. IMC '16, New York, NY, USA, 2016. Association for Computing Machinery.Google Scholar
Digital Library
- Q. He, C. Dovrolis, and M. Ammar. On the predictability of large transfer tcp throughput. In ACM SIGCOMM Computer Communication Review, volume 35, pages 145--156. ACM, 2005.Google Scholar
Digital Library
- S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735--1780, 1997.Google Scholar
Digital Library
- T.-C. Hsu, S.-T. Liou, Y.-P. Wang, Y.-S. Huang, et al. Enhanced recurrent neural network for combining static and dynamic features for credit card default prediction. In ICASSP 2019--2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1572--1576. IEEE, 2019.Google Scholar
Cross Ref
- T.-Y. Huang, R. Johari, N. McKeown, M. Trunnell, and M. Watson. A buffer-based approach to rate adaptation: Evidence from a large video streaming service. In Proceedings of the 2014 ACM Conference on SIGCOMM, SIGCOMM '14, pages 187--198, New York, NY, USA, 2014. ACM.Google Scholar
Digital Library
- A. Jabri, A. Joulin, and L. Van Der Maaten. Revisiting visual question answering baselines. In European conference on computer vision, pages 727--739. Springer, 2016.Google Scholar
Cross Ref
- J. Jiang, V. Sekar, and H. Zhang. Improving fairness, efficiency, and stability in http-based adaptive video streaming with festive. In Proceedings of the 8th International Conference on Emerging Networking Experiments and Technologies, CoNEXT '12, pages 97--108, New York, NY, USA, 2012. ACM.Google Scholar
Digital Library
- D. H. Lee, C. Dovrolis, and A. C. Begen. Caching in http adaptive streaming: Friend or foe? In Proceedings of Network and Operating System Support on Digital Audio and Video Workshop, page 31. ACM, 2014.Google Scholar
- A. Leontjeva and I. Kuzovkin. Combining static and dynamic features for multivariate sequence classification. In 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pages 21--30. IEEE, 2016.Google Scholar
Cross Ref
- X. Liu, F. Dobrian, H. Milner, J. Jiang, V. Sekar, I. Stoica, and H. Zhang. A case for a coordinated internet video control plane. ACM SIGCOMM Computer Communication Review, 42(4):359--370, 2012.Google Scholar
Digital Library
- M. Malinowski, M. Rohrbach, and M. Fritz. Ask your neurons: A neural-based approach to answering questions about images. In Proceedings of the IEEE international conference on computer vision, pages 1--9, 2015.Google Scholar
Digital Library
- H. Mao, R. Netravali, and M. Alizadeh. Neural adaptive video streaming with pensieve. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication, pages 197--210. ACM, 2017.Google Scholar
Digital Library
- H. Mao, S. B. Venkatakrishnan, M. Schwarzkopf, and M. Alizadeh. Variance reduction for reinforcement learning in input-driven environments. In 7th International Conference on Learning Representations ICLR '19, 2019.Google Scholar
- L. Mei, R. Hu, H. Cao, Y. Liu, Z. Han, F. Li, and J. Li. Realtime mobile bandwidth prediction using lstm neural network. In International Conference on Passive and Active Network Measurement, pages 34--47. Springer, 2019.Google Scholar
Cross Ref
- S. Merity, N. S. Keskar, and R. Socher. Regularizing and optimizing lstm language models. arXiv preprint arXiv:1708.02182, 2017.Google Scholar
- M. Mirza, J. Sommers, P. Barford, and X. Zhu. A machine learning approach to tcp throughput prediction. In ACM SIGMETRICS Performance Evaluation Review, volume 35, pages 97--108. ACM, 2007.Google Scholar
Digital Library
- A. Narayanan, S. Verma, E. Ramadan, P. Babaie, and Z.-L. Zhang. Making content caching policies' smart'using the deepcache framework. ACM SIGCOMM Computer Communication Review, 48(5):64--69, 2019.Google Scholar
Digital Library
- R. Netravali, A. Sivaraman, K. Winstein, S. Das, A. Goyal, and H. Balakrishnan. Mahimahi: A lightweight toolkit for reproducible web measurement. In Proceedings of the 2014 ACM Conference on SIGCOMM, SIGCOMM '14, page 129--130, New York, NY, USA, 2014. Association for Computing Machinery.Google Scholar
Digital Library
- J. Padhye, V. Firoiu, D. Towsley, and J. Kurose. Modeling tcp throughput: A simple model and its empirical validation. ACM SIGCOMM Computer Communication Review, 28(4):303--314, 1998.Google Scholar
Digital Library
- S. Puzhavakath Narayanan, Y. S. Nam, A. Sivakumar, B. Chandrasekaran, B. Maggs, and S. Rao. Reducing latency through page-aware management of web objects by content delivery networks. In ACM SIGMETRICS Performance Evaluation Review, volume 44, pages 89--100. ACM, 2016.Google Scholar
- Y. Qin, R. Jin, S. Hao, K. R. Pattipati, F. Qian, S. Sen, C. Yue, and B. Wang. A control theoretic approach to abr video streaming: A fresh look at pid-based rate adaptation. IEEE Transactions on Mobile Computing, 2019.Google Scholar
- M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi. Bidirectional attention flow for machine comprehension. ICLR, 2017.Google Scholar
- K. Spiteri, R. Sitaraman, and D. Sparacio. From theory to practice: Improving bitrate adaptation in the dash reference player. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 15(2s):67, 2019.Google Scholar
- K. Spiteri, R. Urgaonkar, and R. K. Sitaraman. Bola: Near-optimal bitrate adaptation for online videos. In IEEE INFOCOM 2016-The 35th Annual IEEE International Conference on Computer Communications, pages 1--9. IEEE, 2016.Google Scholar
Digital Library
- P. C. Sruthi, S. G. Rao, and B. Ribeiro. Pitfalls of data-driven networking: A case study of latent causal confounders in video streaming. In ACM Sigcomm workshop on Network Meets AI and ML (NetAI), 2020.Google Scholar
Digital Library
- Y. Sun, X. Yin, J. Jiang, V. Sekar, F. Lin, N. Wang, T. Liu, and B. Sinopoli. Cs2p: Improving video bitrate selection and adaptation with data-driven throughput prediction. In Proceedings of the 2016 ACM SIGCOMM Conference, pages 272--285, 2016.Google Scholar
Digital Library
- M. Tadayon and Y. Iwashita. Comprehensive analysis of time series forecasting using neural networks. arXiv e-prints, pages arXiv--2001, 2020.Google Scholar
- G. Tian and Y. Liu. Towards agile and smooth video adaptation in dynamic http streaming. In Proceedings of the 8th International Conference on Emerging Networking Experiments and Technologies, CoNEXT '12, 2012.Google Scholar
Digital Library
- H. D. Trinh, L. Giupponi, and P. Dini. Mobile traffic prediction from raw data using lstm networks. In 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), pages 1827--1832. IEEE, 2018.Google Scholar
Digital Library
- J. van der Hooft, S. Petrangeli, M. Claeys, J. Famaey, and F. De Turck. A learning-based algorithm for improved bandwidth-awareness of adaptive streaming clients. In 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM), pages 131--138. IEEE, 2015.Google Scholar
Cross Ref
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is All you Need. In NIPS, 2017.Google Scholar
Digital Library
- D. Wang and E. Nyberg. A long short-term memory model for answer sentence selection in question answering. In ACL, volume 2, pages 707--712, 2015.Google Scholar
Cross Ref
- Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600--612, 2004.Google Scholar
Digital Library
- W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, and A. Stolcke. The microsoft 2017 conversational speech recognition system. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5934--5938. IEEE, 2018.Google Scholar
Digital Library
- F. Y. Yan, H. Ayers, C. Zhu, S. Fouladi, J. m. Hong, K. Zhang, P. Levis, and K. Winstein. Learning in situ: a randomized experiment in video streaming. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), pages 495--511, 2020.Google Scholar
- H. Yeo, Y. Jung, J. Kim, J. Shin, and D. Han. Neural adaptive content-aware internet video delivery. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI) 18), pages 645--661, 2018.Google Scholar
- X. Yin, A. Jindal, V. Sekar, and B. Sinopoli. A control-theoretic approach for dynamic adaptive video streaming over http. In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, SIGCOMM '15, London, United Kingdom, 2015.Google Scholar
Digital Library
- C. Zhang and P. Patras. Long-term mobile traffic forecasting using deep spatio-temporal neural networks. In Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing, pages 231--240. ACM, 2018.Google Scholar
Digital Library
- Y. Zhang, V. Zhong, D. Chen, G. Angeli, and C. D. Manning. Position-aware attention and supervised data improve slot filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 35--45, 2017.Google Scholar
Cross Ref
- F. Zhu, X. Song, C. Zhong, S. Fang, R. Bouchard, V. N. Fontama, P. Singh, J. Gao, and L. Deng. Churn prediction using static and dynamic features, Sept. 6 2018. US Patent App. 15/446,870.Google Scholar
- X. K. Zou, J. Erman, V. Gopalakrishnan, E. Halepovic, R. Jana, X. Jin, J. Rexford, and R. K. Sinha. Can accurate predictions improve video streaming in cellular networks? In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications, pages 57--62. ACM, 2015.Google Scholar
Digital Library
Index Terms
Xatu: Richer Neural Network Based Prediction for Video Streaming
Recommendations
Xatu: Richer Neural Network Based Prediction for Video Streaming
SIGMETRICS '22The performance of Adaptive Bitrate (ABR) algorithms for video streaming depends on accurately predicting the download time of video chunks. Existing prediction approaches (i) assume chunk download times are dominated by network throughput; and (ii) ...
Xatu: Richer Neural Network Based Prediction for Video Streaming
SIGMETRICS/PERFORMANCE '22: Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer SystemsThe performance of Adaptive Bitrate (ABR) algorithms for video streaming depends on accurately predicting the download time of video chunks. Existing prediction approaches (i) assume chunk download times are dominated by network throughput; and (ii) ...
Bimodal leaky prediction for error resilient video streaming
Asilomar'09: Proceedings of the 43rd Asilomar conference on Signals, systems and computersA novel video coding scheme based on leaky prediction is proposed and its superiority against conventional predictive video coding is demonstrated in environments with moderate to heavy packet loss. The strength of the scheme stems from the fact that it ...






Comments