Jing Guo
ABSTRACT
In recent years, fueled by the rapid advances in high-speed mobile networks, streaming short-form videos over mobile devices (e.g., TikTok) is ubiquitous among mobile users. Despite its widespread application, our investigation revealed that the video quality experienced by the viewers exhibits substantial fluctuations over different short video sessions, so the Quality-of-Experience (QoE) is in fact far from optimal. To tackle this problem, this work develops a novel strategy called Quality Aware Short Video Streaming (QASVS), which employs deep reinforcement learning to automatically generate a quality-driven bitrate decision model to dynamically determine the bitrate for each session. Extensive evaluations show that QASVS can maintain much more consistent video quality across the video sessions. Moreover, compared to the state-of-the-art algorithms, it can improve the video quality by 11.1%~27.9% and significantly reduce the rebuffering events. Therefore, QASVS offers an effective solution for high-performance short video services.
- Cisco Visual Networking Index: Global Mobile Data Traffic Forecase Update, 2017--2022, Mar 2020, Cisco Inc.Google Scholar
- https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11--741490.htmlGoogle Scholar
- TikTok [Online] https://www.tiktok.comGoogle Scholar
- Douyin [Online] https://www.douyin.comGoogle Scholar
- Kwai [Online] http://www.kwai.com/Google Scholar
- Z. Chen, Q. He, Z. Mao, "A Study on The Characteristics of Douyin Short Videos and Implications for Edge Caching," Proc. ACM Turing Celebration Conf. - China, Chengdu, China, May 2019, pp. 1--6. Google ScholarDigital Library
- J. He, M. Hu, Y. Zhou, "LiveClip: Towards Intelligent Mobile Short-form Video Streaming with Deep Reinforcement Learning," Proc. ACM NOSSDAV, Istanbul, Turkey, June 2020, pp. 54--59. Google ScholarDigital Library
- T. Stockhammer, "Dynamic Adaptive Streaming over HTTP: Standards and Design Principles," Proc. ACM Conf. Multimedia Syst., San Jose, USA, Feb 2011, pp.133--144. Google ScholarDigital Library
- G. Zhang and J. Lee, "Ensemble Adaptive Streaming-A New Paradigm to Generate Streaming Algorithms via Specializations," IEEE Transactions on Mobile Computing, vol. 19(6), June 2020, pp.1346--1358.Google ScholarCross Ref
- Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image Quality Assessment: From Error Visibility to Structural Similarity," IEEE Transactions Image Processing, vol. 13(4), Apr. 2004, pp. 600--612. Google ScholarDigital Library
- Z. Li, A. Aaron, L. Katsavounidis, A. Moorthy, and M. Manohara. (Jun. 2016). Toward a Practical Perceptual Video Quality Metric. [Online] https://netflixtechblog.com/toward-a-practical-perceptual-video-quality-metric-653f208b9652Google Scholar
- Y. Qin, S. Hao, R. Pattipati, F. Qian, S. Sen, B. Wang, and C. Yue, "ABR Streaming of VBR-encoded Videos: Characterization, Challenges, and Solutions," Proc. 14th International Conference on Emerging Networking EXperiments and Technologies (CoNEXT'18), Dec. 2018, pp. 366--378. Google ScholarDigital Library
- ITU-T P. 910. 2008. Subjective Video Quality Assessment Methods for Multimedia Applications. (2008).Google Scholar
- V. Mnih, A. P. Badia, M. Mirza, A. Graves, "Asynchronous Methods for Deep Reinforcement Learning," International Conference on Machine Learning, New York City, NY, USA, Jun 2016, pp. 1928--1937. Google ScholarDigital Library
- H. Mao, R. Netravali, M. Alizadeh, "Neural Adaptive Video Streaming with Pensieve," Proc. ACM SIGCOMM, Los Angeles, CA, USA, Aug 2017, pp. 197--210. Google ScholarDigital Library
- S. Sengupta, N. Ganguly, S. Chakraborty and P. De, "HotDASH: Hotspot Aware Adaptive Video Streaming Using Deep Reinforcement Learning," Proc. IEEE 26th International Conference on Network Protocols (ICNP), Cambridge, UK, Sep. 2018, pp. 165--175.Google ScholarCross Ref
- C. Wang, J. Guan, T. Feng, N. Zhang, and T. Cao, "BitLat: Bitrate-adaptivity and Latency-awareness Algorithm for Live Video Streaming," Proc. 27th ACM International Conference on Multimedia (MM '19), Nice, France, Oct 2019, pp. 2642--2646. Google ScholarDigital Library
- C. J. C. H. Watkins, P. Dayan, "Q-learning," Machine learning, vol.8(3--4), May 1992, pp. 279--292. Google ScholarDigital Library
- V. Mnih, K. Kavukcuoglu, D. Silver, et al. "Human-level Control through Deep Reinforcement Learning," Nature, Feb 2015, vol. 518(7540), pp. 529--533.Google Scholar
- T. Lillicrap, J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, "Continuous Control with Deep Reinforcement Learning," arXiv Preprint, Sep 2015.Google Scholar
- G. Zhang, R. Ngan, and J. Lee, "EmuStream - An End-to-End Platform for Streaming Video Performance Measurement," IEEE Access, vol.8, Dec 2019, pp 669--680.Google ScholarCross Ref
- C. M. Bishop, "Pattern Recognition and Machine Learning," Springer, 2006. Google ScholarDigital Library
- C. Qiao, J. Wang and Y. Liu, "Beyond QoE: Diversity Adaptation in Video Streaming at the Edge," IEEE/ACM Transactions on Networking, vol. 29(1), Feb. 2021, pp. 289--302.Google ScholarDigital Library
- Mobile Throughput Trace Data. http://sonar.mclab.info/tracedata/TCP/Google Scholar
- H. Riiser, P. Vigmostad, C. Griwodz, P. Halvorsen, "Commute Path Bandwidth Traces from 3G Networks: Analysis and Applications," Proc. ACM Multimedia Syst., Oslo, Norway, Feb 2013, pp.114--118. Google ScholarDigital Library
- Federal Communications Commission, Raw Data Measuring Broadband America. [Online] https://www.fcc.gov/reports-research/reports/measuring-broadband-america/raw-data-measuring-broadband-america-2016.Google Scholar
- G. Zhang, K. Liu, H. Hu, V. Aggarwal and J. Lee, "Post-Streaming Wastage Analysis A Data Wastage Aware Framework in Mobile Video Streaming," IEEE Transactions on Mobile Computing, Early Access, Mar. 2021.Google Scholar
- G. Zhang, J. Lee, K. Liu, H. Hu and V. Aggarwal, "A Unified Framework for Flexible Playback Latency Control in Live Video Streaming," IEEE Transactions on Parallel and Distributed Systems, vol. 32(12), Dec. 2021, pp. 3024--3037.Google ScholarCross Ref
- Subjective Experiment on Video Quality by Netflix https://github.com/Netflix/vmaf/blob/master/resource/doc/models.mdGoogle Scholar
Index Terms
- A Video-Quality Driven Strategy in Short Video Streaming
Recommendations
Can You See What I See? Quality-of-Experience Measurements of Mobile Live Video Broadcasting
Broadcasting live video directly from mobile devices is rapidly gaining popularity with applications like Periscope and Facebook Live. The quality of experience (QoE) provided by these services comprises many factors, such as quality of transmitted ...
Towards viewing quality optimized video adaptation
ICME '11: Proceedings of the 2011 IEEE International Conference on Multimedia and ExpoFor video delivery over heterogeneous networks, the band width mismatch at the receiver edge often leads to inevitable degradation of video quality during adaptation. While most studies in this field are based on maximizing PSNR (peak signal-to-noise-...
Bandwidth-Efficient Multi-video Prefetching for Short Video Streaming
MM '22: Proceedings of the 30th ACM International Conference on MultimediaApplications that allow sharing of user-created short videos exploded in popularity in recent years. A typical short video application allows a user to swipe away the current video being watched and start watching the next video in a video queue. Such ...
Comments