Wpływ typu treści wideo na przydatności algorytmów uczenia ze wzmocnieniem w systemach DASH

• Autorzy: Markiewicz Przemyslaw , Przyłucki Sławomir

Identyfikatory

DOI

10.35784/jcsi.3579

Warianty tytułu

EN

Influence of video content type on the usefulness of reinforcement learning algorithms in DASH systems

• Języki publikacji: PL

Abstrakty

PL

Artykuł przedstawia wynik badań nad systemami adaptacyjnego strumieniowania DASH (ang. Dynamic Adaptive Streaming over HTTP). W zaproponowanym rozwiązaniu algorytm adaptacyjny oparty jest na paradygmacie uczenia ze wzmocnieniem RL (ang. Reinforcement Learning). Jako podstawę do przeprowadzonych testów wybrany został algorytm Pensieve. Algorytm ten jest szeroko omawiany w literaturze naukowej i dlatego badanie i analiza jego własności jest przydatna w szerokiej gamie rozwiązań wykorzystujących DASH. Główny wkład zaprezentowanych wyników testów w rozwój wiedzy nad usługami strumieniowej transmisji wideo polega na analizie wpływu cech charaktery-stycznych materiałów wideo na efektywność procesu adaptacji realizowanego przez opracowany model RL. Przedstawione wyniki świadczą o tym, że wpływzmienności treści wideonie powinien być pomijany w jakichkolwiek pogłę-bionych analizach cech systemów DASH.

EN

The article presents the result of research on DASH (Dynamic Adaptive Streaming over HTTP) systems. In the proposed solution, the adaptive algorithm is based on the RL (Reinforcement Learning) paradigm. The Pensieve algorithm was chosen as the basis for the tests. This algorithm is widely discussed in the scientific literature and therefore the study and analysis of its properties is useful in a wide range of solutions using DASH. The main contribution of the presented test results to the development of knowledge on video streaming services consists in the analysis of the impact of the characteristics of video materials on the effectiveness of the adaptation process implemented by the developed RL model. The presented results show that this influence should not be omitted in any in-depth analyses of the characteristics of DASH systems.

Słowa kluczowe

PL

DASH; uczenie ze wzmocnieniem; transmisja wideo; QoE

EN

DASH; reinforcement learning; video streaming; QoE

• Wydawca: Wydawnictwo Politechniki Lubelskiej
• Czasopismo: Journal of Computer Sciences Institute
• Rocznik: 2023
• Tom: Vol. 27
• Strony: 162--170
• Opis fizyczny: Bibliogr. 23 poz., rys.

Twórcy

autor

Markiewicz Przemyslaw

• Politechnika Lubelska (Poland)

autor

Przyłucki Sławomir

Bibliografia

• 1. Cisco Visual Networking Index: Forecast and Methodology 2016-2021, High Efficiency Video Coding (HEVC) Algorithms and Architectures (2017).
• 2. K. u. R. Laghari, O. Issa, F. Speranza, T. H. Falk, Quality-of-Experience perception for video streaming services: Preliminary subjective and objective results, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Hollywood, CA, USA, (2012) 1-9.
• 3. Reuban, MPEG-DASH Enhanced Multimedia Streaming, International Journal of Advanced Research in Computer Science and Software Engineering, 4 (2014) 848-851.
• 4. D. You, S. -H. Kim, D. H. Kim, ATSC 3.0 ROUTE/DASH Signaling for Immersive Media: New Perspectives and Examples, in IEEE Access, 9 (2021) 164503-164509, https://dx.doi.org/10.1109/ACCESS.2021.3133626.DOI: https://doi.org/10.1109/ACCESS.2021.3133626
• 5. Sodagar, The MPEG-DASH Standard for Multimedia Streaming Over the Internet, IEEE MultiMedia, 18 (2011) 62-67, https://doi.org/10.1109/MMUL.2011.71.DOI: https://doi.org/10.1109/MMUL.2011.71
• 6. O. Izima, R. de Fréin, A. Malik, A Survey of Machine Learning Techniques for Video Quality Prediction from Quality of Delivery Metrics, Electronics, 10 (2021) 2851, https://dx.doi.org/10.3390/electronics10222851.DOI: https://doi.org/10.3390/electronics10222851
• 7. T-Y. Huang, R. Johari, N. McKeown, M. Trunnell, W. Mark, A buffer-based approach to rate adaptation: Evidence from a Large Video Streaming Service, SIGCOMM Computer Communication Review, New York, NY, USA, 44 (2014) 187-198, https://dx.doi.org/10.1145/2619239.2626296.DOI: https://doi.org/10.1145/2740070.2626296
• 8. X. Yin, A. Jindal, V. Sekar, B. Sinopoli, A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP, SIGCOMM Computer Communication Review, New York, NY, USA, 45 (2015) 325-338, https://doi.org/10.1145/2829988.2787486.DOI: https://doi.org/10.1145/2829988.2787486
• 9. K. Spiteri, R. Sitaraman, D. Sparacio, From Theory to Practice: Improving Bitrate Adaptation in the DASH Reference Player, ACM Transactions on Multimedia Computing, Communications, and Applications, New York, NY, USA, 15 (2019) 1-29, https://doi.org/10.1145/3336497.DOI: https://doi.org/10.1145/3336497
• 10. M. Otterlo, M. Wiering, Reinforcement Learning and Markov Decision Processes, Reinforcement Learning: State of the Art, (2012) 3-42, https://doi.org/10.1145/2829988.2787486.DOI: https://doi.org/10.1007/978-3-642-27645-3_1
• 11. S. Bhatt, Reinforcement Learning 101, Learn the essentials of Reinforcement Learning!, https://towardsdatascience.com/reinforcement-learning-101-e24b50e1d292, [03.11.2022].
• 12. H. Mao, R. Netravali, M. Alizadeh, Neural Adaptive Video Streaming with Pensieve, Association for Computing Machinery, Los Angeles, CA, USA, (2017) 197–210, https://doi.org/10.1145/3098822.3098843.DOI: https://doi.org/10.1145/3098822.3098843
• 13. Grondman, L. Busoniu, G. Lopes, R. Babuska, A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients, IEEE Transactions on Systems, Man and Cybernetics Part B-Cybernetics, 42 (2012) 1291-1307, https://doi.org/10.1109/TSMCC.2012.2218595DOI: https://doi.org/10.1109/TSMCC.2012.2218595
• 14. H. -C. Jang, Y. -C. Huang, H. -A. Chiu, A Study on the Effectiveness of A2C and A3C Reinforcement Learning in Parking Space Search in Urban Areas Problem, International Conference on Information and Communication Technology Convergence, Jeju, South Korea, (2020) 567-571, https://doi.org/10.1109/ICTC49870.2020.9289269.DOI: https://doi.org/10.1109/ICTC49870.2020.9289269
• 15. J. Schmidhuber, Deep learning in neural networks: An overview, Neural Networks, 61 (2015) 85-117, https://doi.org/10.1016/j.neunet.2014.09.003.DOI: https://doi.org/10.1016/j.neunet.2014.09.003
• 16. Z. Tian, L. Zhao, L. Nie, P. Chen, S. Chen, Deeplive: QoE Optimization for Live Video Streaming through Deep Reinforcement Learning, IEEE 25th International Conference on Parallel and Distributed Systems, Tianjin, China, (2019) 827-831, https://doi.org/10.1109/ICPADS47876.2019.00122.DOI: https://doi.org/10.1109/ICPADS47876.2019.00122
• 17. Y. Liu, D. Wei, C. Zhang, W. Li, Distributed Bandwidth Allocation Strategy for QoE Fairness of Multiple Video Streams in Bottleneck Links, Future Internet, 14 (2022) 152, https://doi.org/10.3390/fi14050152.DOI: https://doi.org/10.3390/fi14050152
• 18. Dethise, M. Canini, S. Kandula, Cracking Open the Black Box: What Observations Can Tell Us About Reinforcement Learning Agents, Association for Computing Machinery, New York, NY, USA, (2019) 29-36, https://doi.org/10.1145/3341216.3342210.DOI: https://doi.org/10.1145/3341216.3342210
• 19. H. Riiser, P. Vigmostad, C. Griwodz, P. Halvorsen, Commute Path Bandwidth Traces from 3G Networks: Analysis and Applications, Association for Computing Machinery, New York, NY, USA, (2013) 114-118, https://doi.org/10.1145/2483977.2483991.DOI: https://doi.org/10.1145/2483977.2483991
• 20. M. Ribeiro, S. Singh, C. Guestrin, “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, Association for Computational Linguistics: Demonstrations, San Diego, California, (2016) 97-101, http://dx.doi.org/10.18653/v1/N16-3020.DOI: https://doi.org/10.18653/v1/N16-3020
• 21. Raw Data - Measuring Broadband America 2016, Federal Communications Commission, https://www.fcc.gov/reports-research/reports/measuring-broadband-america/, [03.11.2022].
• 22. ITEC - Dynamic Adaptive Streaming over HTTP, https://dash.itec.aau.at/contact/, [03.11.2022].
• 23. C. Müller, S. Lederer, C. Timmerer, H. Hellwagner, Dynamic Adaptive Streaming over HTTP/2.0, IEEE International Conference on Multimedia and Expo, (2013) 1-6, http://dx.doi.org/10.1109/ICME.2013.6607498.DOI: https://doi.org/10.1109/ICME.2013.6607498

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).