Use of Machine Learning for Rate Adaptation in MPEG-DASH for Quality of Experience Improvement

  • Ibrahim Rizqallah Alzahrani
  • Naeem Ramzan
  • Stamos Katsigiannis
  • Abbes Amira
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 753)

Abstract

Dynamic adaptive video streaming over HTTP (DASH) has been developed as one of the most suitable technologies for the transmission of live and on-demand audio and video content over any IP network. In this work, we propose a machine learning-based method for selecting the optimal target quality, in terms of bitrate, for video streaming through an MPEG-DASH server. The proposed method takes into consideration both the bandwidth availability and the client’s buffer state, as well as the bitrate of each video segment, in order to choose the best available quality/bitrate. The primary purpose of using machine learning for the adaptation is to let clients know/learn about the environment in a supervised manner. By doing this, the efficiency of the rate adaptation can be improved, thus leading to better requests for video representations. Run-time complexity would be minimized, thus improving QoE. The experimental evaluation of the proposed approach showed that the optimal target quality could be predicted with an accuracy of 79%, demonstrating its potential.

Keywords

MPEG-DASH Machine learning Rate adaptation QoE Video streaming 

References

  1. 1.
    Cisco: Cisco visual networking index: Global mobile data traffic forecast update (2017). https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/mobile-white-paper-c11-520862.html. White Paper. Accessed 23 Jan 2018
  2. 2.
    Microsoft Corporation: [MS-SSTR]: Smooth Streaming Protocol. V8.0-2017/09/15 (2015). https://winprotocoldoc.blob.core.windows.net/productionwindowsarchives/MS-SSTR/[MS-SSTR].pdf. White Paper. Accessed 2 Oct 2017
  3. 3.
    Adobe Systems Inc.: High-quality, network-efficient HTTP streaming. https://www.adobe.com/products/hds-dynamic-streaming.html. Accessed 21 Jun 2017
  4. 4.
    Pantos, R., May, W.: HTTP Live Streaming. RFC 8216, RFC Editor (2017)Google Scholar
  5. 5.
    ISO/IEC: Dynamic adaptive streaming over HTTP (DASH) - Part 1: Media presentation description and segment formats. Standard, International Organization for Standardization (2014)Google Scholar
  6. 6.
    Oyman, O., Singh, S.: Quality of experience for http adaptive streaming services. IEEE Commun. Mag. 50(4), 20–27 (2012).  https://doi.org/10.1109/MCOM.2012.6178830CrossRefGoogle Scholar
  7. 7.
    Petrangeli, S., Wu, T., Wauters, T., Huysegems, R., Bostoen, T., Turck, F.D.: A machine learning-based framework for preventing video freezes in HTTP adaptive streaming. J. Netw. Comput. Appl. 94, 78–92 (2017).  https://doi.org/10.1016/j.jnca.2017.07.009CrossRefGoogle Scholar
  8. 8.
    Chan, K.M., Lee, J.Y.B.: Improving adaptive HTTP streaming performance with predictive transmission and cross-layer client buffer estimation. Multimedia Tools Appl. 75(10), 5917–5937 (2016).  https://doi.org/10.1007/s11042-015-2556-yCrossRefGoogle Scholar
  9. 9.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995).  https://doi.org/10.1007/BF00994018MATHGoogle Scholar
  10. 10.
    Mirza, M., Sommers, J., Barford, P., Zhu, X.: A machine learning approach to TCP throughput prediction. IEEE/ACM Trans. Netw. 18(4), 1026–1039 (2010).  https://doi.org/10.1109/TNET.2009.2037812CrossRefGoogle Scholar
  11. 11.
    Tian, G., Liu, Y.: Towards agile and smooth video adaptation in HTTP adaptive streaming. IEEE/ACM Trans. Netw. 24(4), 2386–2399 (2016).  https://doi.org/10.1109/TNET.2015.2464700CrossRefGoogle Scholar
  12. 12.
    Xiong, P., Shen, J., Wang, Q., Jayasinghe, D., Li, J., Pu, C.: NBS: a network-bandwidth-aware streaming version switcher for mobile streaming applications under fuzzy logic control. In: 2012 IEEE First International Conference on Mobile Services, pp. 48–55 (2012). https://doi.org/10.1109/MobServ.2012.10
  13. 13.
    Vergados, D.J., Michalas, A., Sgora, A., Vergados, D.D.: A control-based algorithm for rate adaption in MPEG-DASH. In: IISA 2014, The 5th International Conference on Information, Intelligence, Systems and Applications, pp. 438–442 (2014). https://doi.org/10.1109/IISA.2014.6878834
  14. 14.
    Sobhani, A., Yassine, A., Shirmohammadi, S.: A fuzzy-based rate adaptation controller for DASH. In: Proceedings of the 25th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV 2015, pp. 31–36. ACM, New York (2015). https://doi.org/10.1145/2736084.2736090
  15. 15.
    Chien, Y.L., Lin, K.C.J., Chen, M.S.: Machine learning based rate adaptation with elastic feature selection for HTTP-based streaming. In: 2015 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2015). https://doi.org/10.1109/ICME.2015.7177418
  16. 16.
    Basso, S., Servetti, A., Masala, E., De Martin, J.C.: Measuring DASH streaming performance from the end users perspective using Neubot. In: Proceedings of the 5th ACM Multimedia Systems Conference, MMSys 2014, pp. 1–6. ACM, New York (2014). https://doi.org/10.1145/2557642.2563671
  17. 17.
    Bhat, A.R., Bhadu, S.K.: Machine learning based rate adaptation in DASH to improve quality of experience. In: 2017 IEEE International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), pp. 82–89 (2017). https://doi.org/10.1109/ICSTM.2017.8089131
  18. 18.
    van der Hooft, J., Petrangeli, S., Claeys, M., Famaey, J., Turck, F.D.: A learning-based algorithm for improved bandwidth-awareness of adaptive streaming clients. In: 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM), pp. 131–138 (2015). https://doi.org/10.1109/INM.2015.7140285
  19. 19.
    Claeys, M., Latré, S., Famaey, J., Wu, T., Van Leekwijck, W., De Turck, F.: Design of a Q-learning-based client quality selection algorithm for HTTP adaptive video streaming. In: Adaptive and Learning Agents Workshop, part of AAMAS2013, Proceedings, pp. 30–37 (2013)Google Scholar
  20. 20.
    Claeys, M., Latre, S., Famaey, J., Turck, F.D.: Design and evaluation of a self-learning HTTP adaptive video streaming client. IEEE Commun. Lett. 18(4), 716–719 (2014).  https://doi.org/10.1109/LCOMM.2014.020414.132649CrossRefGoogle Scholar
  21. 21.
    Martín, V., Cabrera, J., Garca, N.: Evaluation of Q-learning approach for HTTP adaptive streaming. In: 2016 IEEE International Conference on Consumer Electronics (ICCE), pp. 293–294 (2016). https://doi.org/10.1109/ICCE.2016.7430618
  22. 22.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  23. 23.
    Bezerra, D., Ito, M., Melo, W., Sadok, D., Kelner, J.: DBuffer: A state machine oriented control system for DASH. In: 2016 IEEE Symposium on Computers and Communication (ISCC), pp. 861–867 (2016). https://doi.org/10.1109/ISCC.2016.7543844
  24. 24.
    GPAC: Osmo4 / MP4Client, a powerful multimedia player. https://www.gpac-licensing.com/gpac/. Accessed 3 Feb 2017
  25. 25.
    The Linux Foundation: netem wiki. https://wiki.linuxfoundation.org/networking/netem. Accessed 24 Apr 2017
  26. 26.
    ITU-T: H.265: High efficiency video coding. ITU-T Rec. H.265 (2016)Google Scholar
  27. 27.
    GPAC: MP4Box General Documentation. https://gpac.wp.imt.fr/mp4box/mp4box-documentation/. Accessed 3 Feb 2017
  28. 28.
    Xiph Foundation: Xiph.org video test media [derf’s collection]. https://media.xiph.org/video/derf/. Accessed 21 Jan 2017
  29. 29.
    Mathworks: Matlab 2016b (2016). https://uk.mathworks.com/products/matlab.html

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Ibrahim Rizqallah Alzahrani
    • 1
  • Naeem Ramzan
    • 1
  • Stamos Katsigiannis
    • 1
  • Abbes Amira
    • 1
  1. 1.School of Engineering and ComputingUniversity of the West of ScotlandPaisleyUK

Personalised recommendations