Abstract
Adaptive Bitrate (ABR) algorithms have become increasingly important for delivering high-quality video content over fluctuating networks. Considering the complexity of video scenes, video chunks can be separated into two categories: those with intricate scenes and those with simple scenes. In practice, improving the quality of intricate chunks can lead to more significant improvements in Quality of Experience (QoE) than improving simple chunks. However, current schemes either assign equal priority to all chunks or optimize using a fixed linear-based reward function, making them inadequate for meeting real-world requirements. To tackle these limitations, this paper introduces a novel ABR approach that explicitly considers bitrate adaptation as the primary objective. The proposed approach, CAST (Complex-scene Aware bitrate algorithm via Self-play reinforcemenT learning), leverages the power of parallel computing with multiple agents to train a neural network, aiming to achieve superior video playback quality for intricate scenes while minimizing frequent freezing events. The extensive trace-driven evaluation and subjective test results demonstrate that CAST outperforms existing off-the-shelf schemes.
This work was conducted during the pursuit of a Master’s degree by Weihe Li at Central South University. This work was supported in part by the National Natural Science Foundation of China (62302524, 62132022); in part by the Key Research and Development Program of Hunan under Grant 2022WK2005; in part by the Natural Science Foundation of Hunan Province, China, under Grant 2021JJ30867; and in part by using computing resources at the High Performance Computing Center of Central South University.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Here, we employ the average chunk rebuffering time as an indicator of the rebuffering experience. This measure is computed by dividing the total rebuffering time by the total number of chunks [19].
References
Hu, J., Huang, J., Li, Z., Wang, J., He, T.: A receiver-driven transport protocol with high link utilization using anti-ECN marking in data center networks. IEEE Trans. Netw. Serv. Manage. 20(2), 1898–1912 (2023)
Sodagar, I.: The MPEG-DASH standard for multimedia streaming over the internet. IEEE Multimed. 18(4), 62–67 (2011)
Qin, Y., et al.: ABR streaming of VBR-encoded videos: characterization, challenges, and solutions. In: Proceedings of ACM CoNEXT, pp. 366–378 (2018)
Qin, Y., Hao, S., Pattipati, K.R., Qian, F.: Quality-aware strategies for optimizing ABR video streaming QoE and reducing data usage. In: Proceedings of ACM MMSys, pp. 189–200 (2019)
Li, W., Huang, J., Wang, S., Wu, C., Liu, S., Wang, J.: An apprenticeship learning approach for adaptive video streaming based on chunk quality and user preference. IEEE Trans. Multimed. 25, 2488–2502 (2023)
Yin, X., Jindal, A., Sekar, V., Sinopoli, B.: A control-theoretic approach for dynamic adaptive video streaming over HTTP. In: Proceedings of ACM SIGCOMM, pp. 325–338 (2015)
Yadav, P.K., Shafiei, A., Ooi, W.T.: QUETRA: a queuing theory approach to DASH rate adaptation. In: Proceedings of ACM MM (2017)
Qin, Y., Jin, R., Hao, S., Pattipati, K.R., Qian, F.: A control theoretic approach to ABR video streaming: a fresh look at PID-based rate adaptation. In: Proceedings of IEEE INFOCOM (2017)
Wang, B., Ren, F.: Towards forward-looking online bitrate adaptation for DASH. In: Proceedings of ACM MM (2017)
Mao, H., Netravail, R., Alizadeh, M.: Neural adaptive video streaming with pensieve. In: Proceedings of ACM SIGCOMM, pp. 197–210 (2017)
Huang, T., et al.: Quality-aware neural adaptive video streaming with lifelong imitation learning. IEEE J. Sel. Areas Commun. 38(10), 2324–2342 (2020)
Kan, N., Li, C., Yang, C., Dai, W., Zou, J., Xiong, H.: Uncertainty-aware robust adaptive video streaming with bayesian neural network and model predictive control. In: Proceedings of ACM NOSSDAV, pp. 17–24 (2021)
Yan, F.Y., et al.: Learning in situ: a randomized experiment in video streaming. In: Proceedings of USENIX NSDI, pp. 495–511 (2020)
Yuan, D., Zhang, Y., Zhang, W., Liu, X., Du, H., Zheng, Q.: PRIOR: deep reinforced adaptive video streaming with attention-based throughput prediction. In: Proceedings of ACM NOSSDAV (2022)
Zuo, X., Yang, J., Wang, M., Cui, Y.: Adaptive bitrate with user-level QoE preference for video streaming. In: Proceedings of IEEE INFOCOM, pp. 1279–1288 (2022)
Huang, T., Zhang, R., Sun, L.: Zwei: a self-play reinforcement learning framework for video transmission services. IEEE Trans. Multimed. 24(1), 1350–1365 (2022)
Huang, T., Yao, X., Wu, C., Zhang, R.X., Pang, Z., Sun, L.: Tiyuntsong: a self-play reinforcement learning approach for ABR video streaming. In: Proceedings of IEEE ICME, pp. 1678–1683 (2019)
Huang, T., Zhou, C., Zhang, R.X., Wu, C., Yao, X., Sun, L.: Stick: a harmonious fusion of buffer-based and learning-based approach for adaptive streaming. In: Proceedings of IEEE INFOCOM, pp. 1967–1976 (2020)
Li, W., Huang, J., Lyu, W., Guo, B., Jiang, W., Wang, J.: RAV: learning-based adaptive streaming to coordinate the audio and video bitrate selections. IEEE Trans. Multimed. (2022). https://doi.org/10.1109/TMM.2022.3198013
Li, W., Huang, J., Liang, Y., Liu, J., Gao, F.: Synthesizing audio and video bitrate selections via learning from actual requirements. In: Proceedings of IEEE ICME (2022)
Li, W., Huang, J., Liu, J., Jiang, W., Wang, J.: Learning audio and video bitrate selection strategies via explicit requirements. IEEE Trans. Mob. Comput. (2023). https://doi.org/10.1109/TMC.2023.3265380
Huang, T., Zhou, C., Zhang, R., Wu, C., Sun, L.: Learning tailored adaptive bitrate algorithms to heterogeneous network conditions: a domain-specific priors and meta-reinforcement learning approach. IEEE J. Sel. Areas Commun. 40(8), 2485–2503 (2022)
Qiao, C., Li, G., Ma, Q., Wang, J., Liu, Y.: Trace-driven optimization on bitrate adaptation for mobile video streaming. IEEE Trans. Mob. Comput. 21(6), 2243–2256 (2022)
Lipa, D.: Physical (Official Music Video) (2020). https://www.youtube.com/watch?v=9HDEHj2yzew
Xiph. Org, Xiph.org Video Test Media (2016). https://media.xiph.org/video/derf/
Liu, C., Bouazizi, I., Gabbouj, M.: Rate adaptation for adaptive HTTP streaming. In: Proceedings of ACM MMSys, 2011, pp. 169–174 (2011)
ITU-T P. 910, Subjective Video Quality Assessment Methods for Multimedia Applications (2008)
Huang, T., Zhang, R., Zhou, C., Sun, L.: QARC: video quality aware rate control for real-time video streaming based on deep reinforcement learning. In: Proceedings of ACM MM, pp. 1208–1216 (2018)
Huang, J., et al.: Opportunistic transmission for video streaming over wild internet. ACM Trans. Multimed. Comput. Commun. Appl. 18(140), 1–22 (2023)
Jiang, J., Sekar, V., Zhang, H.: Improving fairness, efficiency, and stability in HTTP-based adaptive video streaming with FESTIVE. In: Proceedings of ACM CoNEXT (2012)
Huang, T.Y., Johari, R., McKeown, N., Trunnell, M., Watson, M.: A buffer-based approach to rate adaptation: evidence from a large video streaming service. In: Proceedings of ACM SIGCOMM, pp. 187–198 (2014)
Spiteri, K., Urgaonkar, R., Sitaraman, R.K.: BOLA: near-optimal bitrate adaptation for online videos. In: Proceedings of IEEE INFOCOM, pp. 1–9 (2016)
Li, Z., Aaron, A., Katsavounidis, I., Moorthy, A., Manohara, M.: Toward a practical perceptual video quality metric. https://techblog.netflix.com/2016/06/toward-practical-perceptual-video.html
Huang, T.Y., et al.: Hindsight: evaluate video bitrate adaptation at scale. In: Proceedings of ACM MMSys, pp. 86–97 (2019)
Bai, Y., Jin, C., Yu, T.: Near-optimal reinforcement learning with self-play. In: Proceedings of NeurIPS, pp. 1–12 (2020)
Ye, D., et al.: Mastering intricate Control in MOBA Games with Deep Reinforcement Learning (2019). arXiv preprint arXiv:1912.09729
Abadi, M., Barham, P., Chen, J., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of USENIX OSDI, pp. 265–283 (2016)
Yuan, T.: TF.Learn: TensorFlow’s High-level Module for Distributed Machine Learning (2017). https://tflearn.org/
Riiser, H., Vigmostad, P., Griwodz, C., Halvorsen, P.: Commute path bandwidth traces from 3G networks: analysis and applications. In: Proceedings of ACM MMSys, pp. 114–118 (2013)
Federal Communications Commission, Raw Data - Measuring Broadband America (2016). https://www.fcc.gov/reports-research/reports/measuring-broadband-america/raw-data-measuring-broadband-america-2016
Coulom, R.: Whole-history rating: a bayesian rating system for players of time-varying strength. In: Proceedings of Springer International Conference on Computers and Games (2008)
Elo Rating System. https://en.wikipedia.org/wiki/Elo_rating_system
Li, W., Huang, J., Wang, S., Liu, S., Wang, J.: DAVS: dynamic-chunk quality aware adaptive video streaming using apprenticeship learning. In: Proceedings of IEEE GLOBECOM, pp. 1–6 (2020)
The ACM Multimedia 2018 Live Video Streaming Grand Challenge, LTE/WiFi Dataset (2018). https://www.aitrans.online/competition_detail/competition_id=2
Akhtar, Z., et al.: Oboe: auto-tuning video ABR algorithms to network conditions. In: Proceedings of ACM SIGCOMM, pp. 44–58 (2018)
Dash.js (2017). https://github.com/Dash-Industry-Forum/dash.js
Qiao, C., Wang, J., Liu, Y.: Beyond QoE: diversity adaption in video streaming at the edge. IEEE/ACM Trans. Networking 29(1), 289–302 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, W. et al. (2024). CAST: An Intricate-Scene Aware Adaptive Bitrate Approach for Video Streaming via Parallel Training. In: Tari, Z., Li, K., Wu, H. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2023. Lecture Notes in Computer Science, vol 14490. Springer, Singapore. https://doi.org/10.1007/978-981-97-0859-8_8
Download citation
DOI: https://doi.org/10.1007/978-981-97-0859-8_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0858-1
Online ISBN: 978-981-97-0859-8
eBook Packages: Computer ScienceComputer Science (R0)