CS2P: Improving Video Bitrate Selection and Adaptation with Data-Driven Throughput Prediction
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Bitrate adaptation is critical in ensuring good users’ quality-of-experience (QoE) in Internet video delivery system. Several efforts have argued that accurate throughput prediction can dramatically improve (1) initial bitrate selection for low startup delay and high initial resolution; (2) midstream bitrate adaptation for high QoE. However, prior ef- forts did not systematically quantify real-world throughput predictability or develop good prediction algorithms. To bridge this gap, this paper makes three key technical contributions: First, we analyze the throughput characteristics in a dataset with 20M+ sessions. We find: (a) Sessions sharing similar key features (e.g., ISP, region) present similar initial values and dynamical patterns; (b) There is a natural “stateful” dynamical behavior within a given session. Second, building on these insights, we develop CS2P, a better throughput prediction system. CS2P leverages data-driven approach to learn (a) clusters of similar sessions, (b) an initial throughput predictor, and (c) a Hidden-Markov-Model based midstream predictor modeling the stateful evolution of throughput. Third, we develop a prototype system and show by trace-driven simulation and real-world experiments that CS2P outperforms state-of-art by 40% and 50% median pre- diction error respectively for initial and midstream through- put and improves QoE by 14% over buffer-based adaptation algorithm.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“And deep learning further empowers more effective local analysis and prediction [130] at the edge node of industry instead of the cloud.”
From Deep learning for edge computing applications: A State-of-the-Art survey (2020) · cites this paper as [130]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“It has been shown in recent work [432] that accurate throughput prediction can significantly improve the QoE for adaptive video streaming.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [432]
The cited source says what the claim attributes to it.
In the citing paper
“It is also shown that CS2P achieves 3.2% improvement on overall QoE and 10.9% higher average bitrate over state-of-art Model Predictive Control (MPC) approach, which uses harmonic mean for throughput prediction.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [432]
In the citing paper
“Data-driven approaches, in particular ML, have been employed mainly in two different ways: (1) to predict changes in network QoS, namely throughput, and trigger adaptation mechanism to reduce rebuffering time [432], and (2) to select appropriate adaptation action [102].”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [432]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Scikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
(2006) · Springer eBooks · Cited by 8,123
Modeling TCP throughput: a simple model and its empirical validation
Padhye, J., Firoiu, V., Towsley, D., & Kurose, J. (1998) · Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication · doi:10.1145/285237.285291 · Cited by 2,106 · cited 1×
“Throughput prediction: Prior work either developed approximate analytical models of TCP throughput as a function of packet loss and delay [24, 38] or leveraged Time-series models (e.”
MethodVivaldi: a decentralized network coordinate system
Dabek, F., Cox, R., Kaashoek, F., & Morris, R. (2004) · Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1015467.1015471 · Cited by 1,154 · cited 1×
“Seen in a broader context, CS2P can be regarded as a middle ground between centralized video control platforms (e.g., C3 [23], CFA [29]) and decentralized player-based bi-trate adaptation (e.g., BB [27], FESTIVE [30], MPC [47]).”
BackgroundA Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP
Yin, X., Jindal, A., Sekar, V., & Sinopoli, B. (2015) · Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication · doi:10.1145/2785956.2787486 · Cited by 1,016 · cited 6×
“…adaptation: While it is possible to develop adaptation approaches without using through-put estimation (e.g., using only the playback buffer occupancy [27]), recent work [47] argues that throughput-aware bitrate adaptation can deliver a better QoE than pure buffer-occupancy based approaches.”
BackgroundMethodInfluentialSelf-citationA buffer-based approach to rate adaptation: evidence from a large video streaming service
Huang, T.-Y., Johari, R., McKeown, N., Trunnell, M., & Watson, M. (2014) · Proceedings of the 2014 ACM conference on SIGCOMM · doi:10.1145/2619239.2626296 · Cited by 1,004
Generalized Boosted Models: A guide to the gbm package
Ridgeway, G. K. (2006) · Cited by 814
Understanding the impact of video quality on user engagement
Dobrian, F., Sekar, V., Awan, A., Stoica, I., Joseph, D., Ganjam, A., Zhan, J., & Zhang, H. (2011) · Proceedings of the ACM SIGCOMM 2011 conference · doi:10.1145/2018436.2018478 · Cited by 673 · cited 2×
“Delivering good application-level video quality-of-experience (QoE) entails new metrics such as low buffering or smooth bitrate delivery [5, 22].”
BackgroundMethodSelf-citation
Research works printed but not linked: 3
- J. Jiang, V. Sekar, H. Milner, D. Shepherd, I. Stoica, and H. Zhang. CFA: A Practical Prediction System for Video QoE Optimization. In Proc. USENIX NSDI, 2016.
- H. V. Madhyastha, T. Isdal, M. Piatek, C. Dixon, T. Anderson, A. Krishnamurthy, and A. Venkataramani. iPlane: An Information Plane for Distributed Services. In Proc. USENIX OSDI, 2006.
- K. Murphy and M. Dunham. PMTK: Probabilistic Modeling Toolkit. In Proc. NIPS, 2008.
Cited by
Items 301–400 of 428
Hao, P., Hu, L., Zhao, K., Jiang, J., Li, T., & Che, X. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6111-5 · Cited by 3
Self-citationA Frame-Aggregation-Based Approach for Link Congestion Prediction in WiFi Video Streaming
Zhu, S., Mohammed, A., & Striegel, A. (2020) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn49398.2020.9209675 · Cited by 3
“From monitoring throughput directly, the adaptation algorithms could effectively choose the bit-rate levels for future chunks to deliver the highest possible QoE [14].”
MethodQOE-Based Neural Live Streaming Method with Continuous Dynamic Adaptive Video Quality Control
Wei, X., Zhou, M., Kwong, S., Yuan, H., & Xiang, T. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428162 · Cited by 3
“Rate-Based (RB) : RB uses a throughput prediction model to select the highest available bitrate under the band-width constraint [8].”
BackgroundMethodBulk Transfer Scheduling with Deadline in Best-Effort SD-WANs
Hosseini, A., Dolati, M., & Ghaderi, M. (2021) · IFIP/IEEE International Symposium on Integrated Network Management (IM) · Cited by 3
Nam, Y. S., Gao, J., Bothra, C., Ghabashneh, E., Rao, S., Ribeiro, B., Zhan, J., & Zhang, H. (2022) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3547353.3522641 · Cited by 3
Waheed, T., Qazi, I. A., Akhtar, Z., & Qazi, I. A. (2022) · ACM International Conference on emerging Networking EXperiments and Technologies (CoNEXT) · doi:10.1145/3555050.3569120 · Cited by 3
A Multilayer Perceptron Model for Station Grouping in IEEE 802.11ah Networks
Wang, G.-S., Lin, C., Tseng, Y., & Van, L.-D. (2023) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms56928.2023.10154425 · Cited by 3
“Reference [18] presents an Hidden-Markov Model that is capable of predicting throughput.”
BackgroundA Visual Sensitivity Aware ABR Algorithm for DASH via Deep Reinforcement Learning
Jin, Y., Meng, D., & Jiang, W. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3591108 · Cited by 3
Real-Time MPC for Adaptive Video Streaming
Racanelli, V. A., Manfredi, G., Cicco, L. D., & Mascolo, S. (2025) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc54725.2025.10976087 · Cited by 3
“Most ABR algorithms use static bitrate selection methods based on either estimated network bandwidth ( rate-based algorithms) [4] or playback buffer size ( buffer-based algorithms) [5].”
BBGDASH: A Max-Min Bounded Bitrate Guidance for SDN Enabled Adaptive Video Streaming
Al-Issa, A. E., Bentaleb, A., Zinner, T., Mkwawa, I.-H. M., & Ghita, B. (2019) · Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN) · doi:10.1109/icin.2019.8685894 · Cited by 3
“The Cross-Session Stateful Predictor (CS2P) [10] algorithm also falls within the throughput-based category, employing hidden Markov chains to predict the throughput; even though this approach is easy to deploy, it may perform poorly under unstable network conditions.”
MethodBentaleb, A., Begen, A. C., Harous, S., & Zimmermann, R. (2019) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3336496 · Cited by 3
Pipeline-Based Chunk Scheduling to Improve ABR Performance in DASH System
Li, W., Huang, J., Zou, S., Liu, Z., Su, Q., Chen, X., & Wang, J. (2020) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn49398.2020.9209723 · Cited by 3
Benchmark of Bitrate Adaptation in Video Streaming
Chen, J. A., Milner, H., Stoica, I. G., & Zhan, J. (2021) · Journal of Data and Information Quality · doi:10.1145/3468063 · Cited by 3
Cross Layer Optimization and Distributed Reinforcement Learning for Wireless 360° Video Streaming
Elgabli, A., Elbamby, M. S., Perfecto, C., Krouka, M., Bennis, M., & Aggarwal, V. (2024) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass62177.2024.00013 · Cited by 3
“Researchers have investigated various approaches for streaming decisions, for example, by using the client’s buffer state [10], bandwidth prediction and buffer information [11], [12], [13], Markov decision processes [14], machine learning (ML) [15], [16], [17], and data-driven techniques [18], [19].”
BackgroundImproving Adaptive Video Streaming through Machine Learning
Le, A. (2018) · Scholarship at UWindsor (University of Windsor) · Cited by 3
Adaptive Bitrate Streaming Over Cellular Networks: Rate Adaptation and Data Savings StrategiesPreprint
Qin, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01104 · Cited by 6
LL-GABR: Energy Efficient Live Video Streaming Using Reinforcement LearningPreprint
Raman, A., Turkkan, B. O., & Kosar, T. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.09392 · Cited by 6
“CS2P [35] and Fugu [39] build supervised learning models with historical data and find optimal bitrate decisions.”
BackgroundExamining the Predictability of Starlink Downlink Throughput
Ukwen, D., Garcia, J., Brunström, A., & Rajiullah, M. (2024) · IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD) · doi:10.1109/camad62243.2024.10942703 · Cited by 2
A Cache-Aware Approach for Dynamic Adaptive Video Streaming over HTTP
Liu, Y., Lin, T., Liu, Z., & Dai, L. (2019) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc47284.2019.8969599 · Cited by 2
Rakesh, K., Kumar, L. S., Mittar, R., Chakraborty, P., Ankush, P. A., & Gairuboina, S. K. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-4018-9_13 · Cited by 2
Continuously running genetic algorithm for real-time networking device optimization
Mandelbaum, A., Haritan, D., & Shechtman, N. (2021) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3449639.3459272 · Cited by 2
“In the area of supervised learning we can find, for example, works on traffic prediction [22, 39, 51], load prediction[2, 3] and classification of network traffic[49, 50] or even specific packets[26, 35].”
BackgroundVisual Sensitivity Aware Rate Adaptation for Video Streaming via Deep Reinforcement Learning
Meng, D., Jin, Y., Jiang, W., & Shan, Y. (2021) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys53884.2021.00045 · Cited by 2
“The content-agnostic methods select the bitrate only based on the network environment and player state, such as the estimated network throughput [3], [4], the current buffer occupancy [5], [6], or considering both factors by employing model predictive control (MPC) [7] or markov decision process…”
MethodA Data-Driven Framework for TCP to Achieve Flexible QoS Control in Mobile Data Networks
Yao, J., Liu, K., Liang, T., Benson, T., Lee, J. Y. B., Aggarwal, V., Bao, Y., & Chen, M. (2023) · International Workshop on Quality of Service · doi:10.1109/iwqos57198.2023.10188765 · Cited by 2
“reuse throughput estimates from slow-start instead of using the throughput of the previous session [6], [31].”
BackgroundCOCKTAIL: Video streaming QoE optimization with chunk replacement and guided learning
Lee, A., Bae, H., & Kim, C.-K. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.01.014 · Cited by 3
TPMI:Accurate Throughput Prediction for Better Bitrate Selection in Adaptive Video Streaming
Liu, J., Li, J., Yang, X., & Sun, M. (2023) · International Conference on Sensing, Measurement, Communication and Internet of Things Technologies (SMC-IoT) · doi:10.1109/smc-iot62253.2023.00033 · Cited by 2
GRadient sharing A3C for Adaptive Bitrate (GRAAB): A DRL Based Approach for Adaptive Video Streaming
Naresh, M., Saxena, P., & Gupta, M. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572060 · Cited by 2
EASR: Enabling Neural-Enhanced Video Streaming on Mobile Devices with Edge Assistance
Xu, J., Hu, M., Zhao, Q., & Wu, D. (2024) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc61514.2024.10592463 · Cited by 2
“• Rate-based (RB) [9], which adopts the harmonic band-width of the previous few video chunks to predict the current network bandwidth, and chooses the next video chunk at the highest bitrate according to the predicted bandwidth.”
BackgroundDeepReal: Short-form Video Streaming with Fine-grained Bitrate Adaptation
Zhang, G., Guo, J. M., Xiao, M., Yu, D., & Cheng, X. (2024) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon64284.2024.10934831 · Cited by 2
“For instance, both Dashlet [5] and PDAS [6] employ MPC-based logic [7], which is particularly vulnerable to bandwidth changes due to its heavy reliance on an accurate throughput estimation [8, 9] (see measurement results in §II-B).”
User-Tailored Video Adaptation in Dynamic Environments
Choi, W., Chen, J., & Yoon, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3564327 · Cited by 2
“Early rule-based methods have been replaced by reinforcement learning and supervised learning techniques, trained on large-scale traces to achieve better average performance [15].”
Tao, L., Gong, Y., Jin, S., & Zhao, J. (2017) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1145/3127540.3127574 · Cited by 2
“Current studies show that it is possible to accurately predict future available resources at short-and medium-term scales [3, 11].”
BackgroundA Highly Accurate Transportation Mode Recognition Using Mobile Communication Quality
Kawakami, W., Kanai, K., Wei, B., & Katto, J. (2018) · IEICE Transactions on Communications · doi:10.1587/transcom.2018sep0013 · Cited by 2
Qiao, C., Li, G., Wang, J., & Liu, Y. (2019) · International Workshop on Quality of Service · doi:10.1145/3326285.3329038 · Cited by 2
Improving Robustness of DASH Against Network Uncertainty
Wang, B., & Ren, F. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00134 · Cited by 2
“Concurrent works have confirmed the QoE degradation in cellular networks [13] and the negative impact of inaccurate prediction [8, 10].”
BackgroundExploiting the layer correlation to improve DASH scheduling with scalable video coding
Zhang, G., Wu, Y., Han, X., Gao, Q., & Chen, J. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107116 · Cited by 2
HDA Video Transmission Scheme for DASH
Wen, T., Cai, W., Wang, A., Liang, J., & Zhao, L. (2020) · IEEE Access · doi:10.1109/access.2020.2982193 · Cited by 2
“Some of these algorithms are based on network bandwidth estimation (‘‘rate-based’’ algorithms [2], [3]).”
BackgroundMachine Learning based Bandwidth Prediction for Dynamic Adaptive Streaming over HTTP
Yoo, S., Kim, G., Kim, M., Kim, Y., Park, S., & Kim, D. (2020) · JOURNAL OF ADVANCED INFORMATION TECHNOLOGY AND CONVERGENCE · doi:10.14801/jaitc.2020.10.2.33 · Cited by 2
DIG: A Data-Driven Impact-Based Grouping Method for Video Rebuffering Optimization
Meng, S., Qiao, C., Li, J., Wang, Y., & Guo, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98355-0_4 · Cited by 2
Hide & Seek: Traffic Matrix Completion and Inference Using Hidden Information
Sacco, A., Esposito, F., & Marchetto, G. (2023) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51644.2023.10060329 · Cited by 2
Illuminating the hidden challenges of data-driven CDNs
Benson, T. (2023) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3578356.3592574 · Cited by 2
Modelling resource allocation in uncertain system environment through deep reinforcement learningPreprint
Gandhi, N., & Mishra, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09461 · Cited by 2
“Reinforcement learning maintains balance between exploration and exploitation to obtain optimal result [7].”
BackgroundMethodWireless Network Instabilities in the Wild: Measurement, Applications (Non)Resilience, and OS Remedy
Cui, Y., Jiang, Y., Lai, Z., Chen, X. C., Hu, Y., Tan, K., Dai, M., Zheng, K., & Li, Y. (2018) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2018.2885872 · Cited by 1
CoarseUCB: A Context-Aware Bitrate Adaptation Algorithm for VBR-encoded Video Streaming
Yang, C., Zhou, G., Hu, M., Zhao, Q., & Wu, D. (2024) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc61514.2024.10592326 · Cited by 1
Data-Driven Video Scene Importance Estimation for Adaptive Video Streaming
Choi, W., & Yoon, J. (2024) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn61752.2024.10624977 · Cited by 1
“To improve user QoE, many efforts [1]–[4] have been made to understand network conditions and accurately predict future conditions.”
BackgroundYi, L., Qin, Y., & Huang, R. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3604930 · Cited by 3
Joint Optimization of Handoff and Video Rate in LEO Satellite Networks
Park, K., He, Z., Luo, C., Xu, Y., Qiu, L., Ge, C., & Muaz, M. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571207 · Cited by 1
“While there are fewer NOAA satellites, they share similar characteristics as Starlink ( e.g. , predictable trajectories and comparable speeds).”
MPC 2 : A novel MPC-based cache-aware adaptive video streaming over HTTP
Wu, H., Xiao, Y., Zhang, C., Gong, P., & Wu, D. O. (2026) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2026.104448 · Cited by 1
Game Theory Based Bitrate Adaptation for Dash.Js Reference Player
Bentaleb, A., Begen, A. C., & Zimmermann, R. (2018) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2018.8551495 · Cited by 1
“PANDA & CS2P Estimators: This component implements two algorithms for the throughput estimation of a segment using PANDA [8] and CS2P [9].”
MethodInfluentialImplementation of Quantum Decision-Making Based Recommendation Method for Adaptive Bitrate Streaming
Otoshi, T., & Murata, M. (2019) · Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN) · doi:10.1109/icin.2019.8685920 · Cited by 1
“There is also the server-side bitrate control method [3].”
MethodImproving Adaptive Video Streaming through Session Classification
Akhtar, Z., Le, A. M., Nam, Y. S., Chen, J. A., Govindan, R., Katz-Bassett, E., Rao, S., & Zhan, J. (2019) · Journal of Data and Information Quality · doi:10.1145/3309682 · Cited by 1
“1 Very often, video sessions running in a similar situation characterized by some common session features would share similar network conditions (Jiang et al. 2016; Sun et al. 2016).”
BackgroundMethodInfluentialQoE Control for Dynamic Adaptive Video Streaming Over HTTP at Access Point
Yuan, Y., Lin, S., & Zhou, G. (2019) · IEEE International Conference on Industrial Internet (ICII) · doi:10.1109/icii.2019.00053 · Cited by 1
“Traditional research on DASH focuses on designing adaptive bitrate selection algorithms [4] [5] [6] [7] [8] [9], but such solutions are usually based on independent end-to-end closed-loop adaptation between one client and the video content server, which does not coordinate among multiple clients.”
BackgroundMethodInfluentialMachine Learning based User QoE Evaluation for Video Streaming over Mobile Network
Zhu, Y., Sun, T., Li, Q., Lu, L., Duan, X., & Li, W. (2020) · International Conference on Smart Data Services · doi:10.1109/smds49396.2020.00010 · Cited by 3
“Ensuring user QoE becomes ever so important [1]-[5].”
BackgroundMachine Learning Application in the Hybrid Optical Wireless Networks
Naik, D., & De, T. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-9516-5_41 · Cited by 1
Design and analysis of a fair, efficient and stable multi-server adaptive streaming protocol
Zhang, S., Liu, G., Ji, X., & Wan, S. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107371 · Cited by 1
Datacenter Traffic Optimization with Deep Reinforcement Learning
Chen, L., Lingys, J., Chen, K., & Liao, X. (2021) · Wiley eBooks · doi:10.1002/9781119675525.ch10 · Cited by 1
Akcay, M. N. (2021) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3458305.3478461 · Cited by 1
“A number of other data-driven machine learning solutions have also emerged: CS2P [38], AMP [8], CFA [25], PREM [43], LiveNAS [28], Pytheas [26] and DDS [16].”
BackgroundChimera: exploiting UAS flight path information to optimize heterogeneous data transmission
Shirey, R., Rao, S., & Sundaram, S. (2021) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp52444.2021.9651923 · Cited by 1
Nam, Y. S., Gao, J., Bothra, C., Ghabashneh, E., Rao, S., Ribeiro, B., Zhan, J., & Zhang, H. (2022) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/3489048.3522641 · Cited by 1
CTC: Content-Aware Tailoring of Adaptive Video Streaming using Multi-Head Critic Network
Choi, W., & Yoon, J. (2023) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn57995.2023.10199483 · Cited by 1
“To accurately predict the future bandwidth, CS2P [7] and Fugu [3] adopt supervised learning.”
Yi, Y., Li, X., Xu, Y., Li, W., Hu, J., Taishan, X., Ren, X., & Lu, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-39698-4_5 · Cited by 1
Adaptive Streaming Continuous Learning System for Video Analytics
Li, T., Li, Q., Zhang, M., Yuan, Z., & Jiang, Y. (2024) · International Workshop on Quality of Service · doi:10.1109/iwqos61813.2024.10682886 · Cited by 1
Adapting Swarm Applications: A Systematic and Quantitative Approach
Zhang, B. (2018) · eScholarship (California Digital Library)
An Adaptive Bitrate Algorithm Based on Estimation and Video Adaptation for Improving QoE in DASH
Jabbar, S. Q., Kadhim, D. J., & Li, Y. (2018) · International Conference on Computer Science, Electronics and Communication Engineering (CSECE) · doi:10.2991/csece-18.2018.41
“The state-of-the-art for adaptive bitrates algorithms can be generally divided as buffer-based [4], rate-based [5] and hybrid strategies [6][7].”
BackgroundSamba, A. (2018) · theses.fr (ABES) · doi:10.70675/bc6916fez4b18z4926z8030zd57465e5c66f · Cited by 2
The computer desktop image compression based on clustering algorithm
Gui, D. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5892
Relay strategy in online mobile games: a data-driven approach
Zhu, G., Lv, K., Ma, G., & Gu, W. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414595
“The network performance could be improved significantly if a relay session is selected appropriately[20, 33].”
BackgroundCognitive Autonomy for Network‐Optimization
Mwanje, S. S., Ul‐Islam, M. N., & Liao, Q. (2020) · Wiley eBooks · doi:10.1002/9781119586449.ch8
VBSSR: Variable Bitrate Encoded Video Streaming with Super-Resolution on HPC Education Platform
Wu, R., Zhou, G., Hu, M., & Wu, D. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-0010-4_20
A Hybrid Bitrate Control Approach for Smooth Video Streaming in DASH
Liu, T., Sun, Y., Ding, L., Zhi, C., Yang, F., Qian, L., & Xu, Y. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-1194-0_27
Self-citationNew approaches to improving live video delivery over content delivery networks
Wang, H. (2020) · UVic’s Research and Learning Repository (University of Victoria)
Crowd Intelligence Empowered Video Transmission in Ultra-low-bandwidth Constrained Circumstances
Qiao, H., Yang, Z., Liang, B., & Ji, W. (2020) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00116
“They have to deal with complex situations, including different QoE requirements [17]–[19] and highly variable network throughput [20], [21].”
BackgroundOptical Wireless System Performance, Deployment, and Optimization
Ruggeri, E., Tsakyridis, A., Vagionas, C., Miliou, A. N., Malekzai, S., Agapiou, G. S., Datseris, G., & Stavroulakis, G. (2021) · Springer eBooks · doi:10.1007/978-3-030-74648-3_9
Artificial Accurate Time-stamp in Network Adapters
Wasko, W., Levi, D., Geula, T., & Mandelbaum, A. (2021) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00218
Glisic, S., & Lorenzo, B. (2022) · Wiley eBooks · doi:10.1002/9781119790327.ch7
Zeng, D., Gu, L., Pan, S., & Guo, S. (2019) · SpringerBriefs in computer science · doi:10.1007/978-3-030-32942-6_1
Xie, A., & Wang, X. (2019) · Springer eBooks · doi:10.1007/978-3-319-32903-1_90-1
Internet Multimedia Content Distribution
Li, Z.-N., Drew, M. S., & Liu, J. (2021) · Texts in computer science · doi:10.1007/978-3-030-62124-7_16
Xie, A., & Wang, X. (2020) · Springer eBooks · doi:10.1007/978-3-319-78262-1_90
Dynamic Push for HTTP Adaptive Streaming with Deep Reinforcement Learning
Du, H., Yuan, D., Zhang, W., & Zheng, Q. (2021) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads53394.2021.00112
BeeCast: A Device-to-Device Collaborative Video Streaming System
Alghamdi, A., Balah, Y., Albejadi, M., & Felemban, M. (2022) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc55113.2022.9825355
Cocktail: Video Streaming Qoe Optimization with Chunk Replacement and Guided LearningPreprint
Lee, A., Bae, H., & Kim, C.-K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4469647
Evaluation of an Adaptive Multimedia Streaming in Mobile Cloud Computing for Slow-Speed Networks
Ojo, O. E., Oyinloye, O., Adejimi, A. O., & Adejumo, T. (2023) · African Scientific Reports · doi:10.46481/asr.2023.2.2.100
PatchSR: Achieving HD Video Streaming with Pre-downloaded Universal SR Models
Xu, J., Luo, Z., Wang, Z., Zhou, G., & Hu, M. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594664
“• Rate-based (RB) [37], which employs downloads of previous video chunks to predict the available network bandwidth and requests the next video chunk at the highest bitrate based on the prediction results.”
BackgroundExtremely Low Latency Interactive Streaming over an 802.11 Wireless Link
Kim, S., Lee, J., & Cho, C.-H. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-spring57618.2023.10199675
Improving Live Augmented Reality With Neural Configuration Adaptation
Chen, N., Zhang, S., & Lu, S. L. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-0230-9.ch007
QoE optimization based on Adaptive Bitrate Control for Multi-party Interactive Live Streaming
Wang, J., & Gao, Y. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580564
“In addition, Sun et al. [7] proposed a rate adaptive optimization system CS2P based on large-scale data-driven throughput prediction.”
MethodDesigning transport scheme of 3D naked-eye system
Zheng, R., Feng, X., & Ren, F. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.103988
Video Content Adaptive Transmission Technology Based on Reinforcement Learning
Guo, W., & Jia, R. (2024) · doi:10.1145/3694908.3696176
Bidirectional Bandwidth Coordination Under Half-Duplex Bottlenecks for Video Streaming
Chen, J. W., Wang, B., Xu, Z., Zhang, Y., Wang, M., Xu, M., & Meng, Z. (2024) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp61940.2024.10858534
Feng, F., Zhang, Y., Zheng, X., Bi, T., & Jiang, T. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3581922
“Toaddressthesechallenges,adaptivebitrate(ABR)algo-rithmshavebeenwidelyemployedinpopularvideostreaming platforms(e.g.,Netflix,Kuaishou,iQiyi,etc.)[2],[3],[4],[5], [6],[7].”
Revisiting the Relation between QoS and QoE to improve predictive Models in Adaptive StreamingPreprint
Guarnieri, T., Almeida, J. M., & Vieira, A. B. (2025) · Research Square · doi:10.21203/rs.3.rs-7455416/v1
Jin, Z., Qi, P., Gao, R., Jing, Y., & Tao, D. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613109
Enhancing Multi-stream Scheduling with Dynamic Priority and Bitrate Adaptation
Yin, J., Li, Y., Xu, Y., & Huang, C. (2025) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb65076.2025.11165588
“Current ABR algorithms can be categorized into three groups: buffer-based ABR algorithms [12]–[14], rate-based ABR algorithms [15]–[17], and hybrid ABR algorithms [18]–[26].”
Into the Wild: Real-World Testing for ML-Based ABR
Hoffman, B., Dietmüller, A., Mishra, A., & Vanbever, L. (2025) · Workshop on Practical Adoption Challenges of ML for Systems (PACMI) · doi:10.1145/3766882.3767186
Bao, Y., Zhang, J., Yi, C. X., Zhang, D., & Fu, R. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02106-1
Watch, Skip, Repeat: Hotspot-Aware Joint Optimization for Video Streaming
Sheng, D., Qi, Q., Wang, J., & Liao, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754579
Yin, X. (2016) · KiltHub Repository · doi:10.1184/r1/6721325
Self-citationLi, W., He, C., Meng, F., Zhang, X., Zhang, Z., & Liang, Y. (2026) · IEEE Communications Letters · doi:10.1109/lcomm.2026.3651360
“Many traditional ABR approaches [6], [7], [8], [9], [10] have been designed to adaptively select downloading bitrates for video chunk based on network throughput or buffer occupancy, targeting to improve the user’s QoE.”
Chen, J., Yu, Y., Wang, L., Chen, Y., Huang, T., & Sun, L. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3656223
“Previous work: Existing advanced bandwidth prediction algorithms like VOD-based Lumos [10] and delay-based predictors CS2P [16] and T3P [17] all assume knowledge of remaining segment sizes and typical transmission without inter-chunk idle time, which clearly differs from various uncertainty…”
Accurate is Not Necessarily the Best: Edge-Assisted Bitrate Re-Adaptation for Video Streaming
Shi, W., Lang, W., Li, Q., Wang, C., Shen, G., Li, L., Xu, Y., Jiang, Y., & Muntean, G. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3661954
“Sun et al. [41] designed CS2P, a method that involves extensive analysis of network throughput stability and predictability, based on a data-driven throughput prediction model.”
Generalizing Adaptive Video Streaming With Mixture of Experts in Heterogeneous Wireless Networks
Wang, S., Li, B., Cao, X., & Xie, L. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3665094
“Thefor-mertypicallyemploycontrolrulestomakebitratedecisions basedonestimatednetworkconditions[2],andplaybackbuffer size[3],ordirectlyusingmodelpredictivecontrol(MPC)[4].”
Metadata
- Authors
- Sun, Y., Yin, X., Jiang, J., Sekar, V., Lin, F., Wang, N., Liu, T., & Sinopoli, B.
- Affiliations
- ICT/CAS
- Capital Medical University (CN)
- iQIYI (China) (CN)
- Venue
- Proceedings of the 2016 ACM SIGCOMM Conference
- Publisher
- ACM
- Published
- 2016-08-22
- Pages
- 272-285
- OpenAlex
- W2482797934
- Cited by
- 407
- References
- 38
- Citations by year
- 2026: 20 · 2025: 25 · 2024: 40 · 2023: 43 · 2022: 40 · 2021: 57 · 2020: 55 · 2019: 50 · 2018: 54 · 2017: 21 · 2016: 2
- FWCI
- 36.18
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM SIGCOMM Conference (SIGCOMM) (publishedVersion)
- Funders
- National Science Foundation (1345305)
- National Natural Science Foundation of China (2012CB315802, 61379133, 61133015)
- National Key Research and Development Program of China (2012CB315802)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Networks and Communications › Caching and Content Delivery
- Keywords
- throughput prediction, bitrate adaptation, video streaming, quality of experience, hidden Markov models, session clustering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.