research-article

Public Access

PERCEIVE: deep learning-based cellular uplink prediction using real-time scheduling patterns

Authors:

Sandesh Dhawaskar Sathyanarayana,

Sangeeta Ramakrishnan,

Sangtae HaAuthors Info & Claims

MobiSys '20: Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services

Pages 377 - 390

https://doi.org/10.1145/3386901.3388911

Published: 15 June 2020 Publication History

All formats PDF

Abstract

As video calls and personal broadcasting become popular, the demand for mobile live streaming over cellular uplink channels is growing fast. However, current live streaming solutions are known to suffer from frequent uplink throughput fluctuations causing unnecessary video stalls and quality drops. As a remedy to this problem, we propose PERCEIVE, a deep learning-based uplink throughput prediction framework. PERCEIVE exploits a 2-stage LSTM (Long Short Term Memory) design and makes throughput predictions for the next 100ms. Our extensive evaluations show that PERCEIVE, trained with LTE network traces from three major operators in the U.S., achieves high accuracy in the uplink throughput prediction with only 7.67% mean absolute error and outperforms existing prediction techniques. We integrate PERCEIVE with WebRTC, a popular video streaming platform from Google, as a rate adaptation module. Our implementation on the Android phone demonstrates that it can improve PSNR by up to 6dB (4x) over the default WebRTC while providing less streaming latency.

References

[1]

iPerf- The ultimate speed test tool for TCP, UDP and SCTP, June 2016. https://iperf.fr/iperf-download.php.

[2]

AccuBattery, 2019. https://accubatteryapp.com.

[3]

FFmpeg, October 2019. https://www.ffmpeg.org/download.html.

[4]

3GPP. LTE: Evolved Universal Terrestrial Radio Access (E-UTRA); Physical layer procedures (Release 15). http://www.3gpp.org/dynareport/36213.htm, 2019.

[5]

Arora, A. Why Random Forests can't predict trends and how to overcome this problem?, December 2018. http://shorturl.at/hmyD8.

[6]

Arun, V., and Balakrishnan, H. Copa: Practical Delay-Based Congestion Control for the Internet. In Proceedings of USENIX NSDI (2018).

Digital Library

[7]

Baig, G., He, J., Qureshi, M. A., Qiu, L., Chen, G., Chen, P., and Hu, Y. Jigsaw: Robust Live 4K Video Streaming. In Proceedings of ACM MobiCom (2019).

Digital Library

[8]

Balasingam, A., Bansal, M., Misra, R., Nagaraj, K., Tandra, R., Katti, S., and Schulman, A. Detecting if LTE is the Bottleneck with BurstTracker. In Proceedings of ACM MobiCom (2019).

Digital Library

[9]

Bega, D., Gramaglia, M., Fiore, M., Banchs, A., and Costa-Perez, X. DeepCog: Cognitive Network Management in Sliced 5G Networks with Deep Learning. In Proceedings of IEEE INFOCOM (2019).

Digital Library

[10]

Bu, T., Li, L., and Ramjee, R. Generalized Proportional Fair Scheduling in Third Generation Wireless Data Networks. In Proceedings of IEEE INFOCOM 2006 (April 2006).

[11]

Bui, N. IMDEA-OWL, August 2017. https://git.networks.imdea.org/nicola_bui/imdeaowl.

[12]

Bui, N., and Widmer, J. OWL: A Reliable Online Watcher for LTE Control Channel Measurements. In Proceedings of the 5th Workshop on All Things Cellular: Operations, Applications and Challenges (2016).

Digital Library

[13]

Chakraborty, A., Navda, V., Padmanabhan, V. N., and Ramjee, R. Coordinating Cellular Background Transfers Using Loadsense. In Proceedings of ACM MobiCom (2013).

Digital Library

[14]

Chen, T., Goodfellow, I., and Shlens, J. Net2net: Accelerating learning via knowledge transfer. arXiv preprint arXiv:1511.05641 (2015).

[15]

Chollet, F., et al. Keras. https://github.com/fchollet/keras, 2019.

[16]

Cisco. Cisco Visual Networking Index, 2016--2021, June 2017. https://newsroom.cisco.com/press-release-content?type=webcontent&articleId=1853168.

[17]

Clevert, D.-A., Unterthiner, T., and Hochreiter, S. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 (2015).

[18]

Deng, H., Ling, K., Guo, J., and Peng, C. Unveiling the Missed 4.5G Performance In the Wild. In Proceedings of ACM HotMobile (2020).

Digital Library

[19]

Deng, H., Peng, C., Fida, A., Meng, J., and Hu, Y. C. Mobility Support in Cellular Networks: A Measurement Study on Its Configurations and Implications. In Proceedings of ACM IMC (2018).

Digital Library

[20]

Ettus Research. USRP B210. http://www.ettus.com/all-products/ub210-kit/, 2019.

[21]

Fouladi, S., Emmons, J., Orbay, E., Wu, C., Wahby, R. S., and Winstein, K. Salsify: Low-Latency Network Video through Tighter Integration between a Video Codec and a Transport Protocol. In Proceedings of USENIX NSDI (2018).

[22]

free range statistics. Extrapolation is tough for trees!, December 2016. http://freerangestats.info/blog/2016/12/10/extrapolation.

[23]

Ghosh, A., Kumar, H., and Sastry, P. Robust loss functions under label noise for deep neural networks. In Proceedings of AAAI Conference on Artificial Intelligence (2017).

[24]

Gong, Y., Liu, L., Yang, M., and Bourdev, L. Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014).

[25]

Google. WebRTC playout-delay, October 2018. https://webrtc.org/experiments/rtp-hdrext/playout-delay/.

[26]

Google. Recommended upload encoding settings. https://support.google.com/youtube/answer/1722171?hl=en, 2019.

[27]

Google. Tensorflow Lite. https://www.tensorflow.org/lite/, 2019.

[28]

Google. Tensorflow Model Optimization Toolkit. https://www.tensorflow.org/model_optimization, 2019.

[29]

Google. WebRTC Native Code. https://webrtc.org/native-code/, 2019.

[30]

Guo, Y., Qian, F., Chen, Q. A., Mao, Z. M., and Sen, S. Understanding On-device Bufferbloat for Cellular Upload. In Proceedings of ACM IMC (2016).

Digital Library

[31]

Han, S., Mao, H., and Dally, W. J. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015).

[32]

Hochreiter, S., and Schmidhuber, J. Long short-term memory. Neural Computation 9, 8 (1997), 1735--1780.

Digital Library

[33]

Holmer, S., Lundin, H., Carlucci, G., Cicco, L. D., and Mascolo, S. A Google Congestion Control Algorithm for Real-Time Communication. IETF draft, January 2017. https://tools.ietf.org/pdf/draft-ietf-rmcat-gcc-02.pdf.

[34]

Huang, Y., Li, S., Hou, Y. T., and Lou, W. GPF: A GPU-based Design to Achieve -100 μs Scheduling for 5G NR. In Proceedings of ACM MobiCom (2018).

Digital Library

[35]

Jansen, B., Goodwin, T., Gupta, V., Kuipers, F., and Zussman, G. Performance evaluation of webrtc-based video conferencing. SIGMETRICS Perform. Eval. Rev. 45, 3 (Mar. 2017), 56--68.

[36]

Kingma, D. P., and Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).

[37]

Kulkarni, A., Seetharam, A., Ramesh, A., and Herath, J. D. DeepChannel: Wireless Channel Quality Prediction Using Deep Learning. IEEE Transactions on Vehicular Technology 69, 1 (2020), 443--456.

[38]

Kumar, S., Hamed, E., Katabi, D., and Erran Li, L. LTE Radio Analytics Made Easy and Accessible. In Proceedings of ACM SIGCOMM (2014).

[39]

Kurdoglu, E., Liu, Y., Wang, Y., Shi, Y., Gu, C., and Lyu, J. Real-time Bandwidth Prediction and Rate Adaptation for Video Calls over Cellular Networks. In Proceedings of ACM MMSys (2016).

Digital Library

[40]

Lee, H., Flinn, J., and Tonshal, B. RAVEN: Improving Interactive Latency for the Connected Car. In Proceedings of ACM MobiCom (2018).

Digital Library

[41]

Lee, J., Lee, J., Im, Y., Sathyanarayana, S. D., Rahimzadeh, P., Zhang, X., Hollingsworth, M., Joe-Wong, C., Grunwald, D., and Ha, S. CASTLE over the Air: Distributed Scheduling for Cellular Data Transmissions. In Proceedings of ACM MobiSys (2019).

Digital Library

[42]

Lee, S., Choudhury, S., Khoshnevis, A., Xu, S., and Lu, S. Downlink MIMO with Frequency-Domain Packet Scheduling for 3GPP LTE. In Proceedings of IEEE INFOCOM 2009 (April 2009).

[43]

Li, L., Xu, K., Li, T., Zheng, K., Peng, C., Wang, D., Wang, X., Shen, M., and Mijumbi, R. A Measurement Study on Multi-path TCP with Multiple Cellular Carriers on High Speed Rails. In Proceedings of ACM SIGCOMM (2018).

Digital Library

[44]

Li, Y., Peng, C., Yuan, Z., Li, J., Deng, H., and Wang, T. Mobileinsight: Extracting and analyzing cellular network information on smartphones. In Proceedings of ACM MobiCom (2016).

Digital Library

[45]

Liaw, A., Wiener, M., et al. Classification and regression by randomforest. R news 2, 3 (2002), 18--22.

[46]

Liu, L., Li, H., and Gruteser, M. Edge Assisted Real-Time Object Detection for Mobile Augmented Reality. In Proceedings of ACM MobiCom (2019).

Digital Library

[47]

Liu, X., Sridharan, A., Machiraju, S., Seshadri, M., and Zang, H. Experiences in a 3g network: Interplay between the wireless channel and applications. In Proceedings of ACM MobiCom (2008).

Digital Library

[48]

LTE Quick Reference. RSRP, RSRQ, RSSI, SINR Interplay. https://www.sharetechnote.com/html/Handbook_LTE_RSRP_RSRQ_SINR_Interplay.html, 2020.

[49]

Luo, C., Ji, J., Wang, Q., Chen, X., and Li, P. Channel State Information Prediction for 5G Wireless Communications: A Deep Learning Approach. IEEE Transactions on Network Science and Engineering 7, 1 (2020), 227--236.

[50]

Mao, H., Netravali, R., and Alizadeh, M. Neural Adaptive Video Streaming with Pensieve. In Proceedings of ACM SIGCOMM (2017).

Digital Library

[51]

Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013).

[52]

MobileInsight. Running Your Customized Plugin on the Phone, October 2018. http://www.mobileinsight.net/tutorial-plugin.html.

[53]

Nair, V., and Hinton, G. E. Rectified linear units improve restricted boltzmann machines. In Proceedings of ICML (2010).

[54]

Narayanan, A., Ramadan, E., Carpenter, J., Liu, Q., Liu, Y., Qian, F., and Zhang, Z.-L. A First Look at Commercial 5G Performance on Smartphones. In Proceedings of The Web Conference (2020).

Digital Library

[55]

Park, S., Lee, J., Kim, J., Lee, J., Ha, S., and Lee, K. ExLL: An Extremely Low-latency Congestion Control for Mobile Cellular Networks. In Proceedings of ACM CoNEXT (2018).

Digital Library

[56]

Ray, D., Kosaian, J., Rashmi, K. V., and Seshan, S. Vantage: Optimizing video upload for time-shifted viewing of social live streams. In Proceedings of ACM SIGCOMM (2019).

Digital Library

[57]

Sainath, T. N., Kingsbury, B., Sindhwani, V., Arisoy, E., and Ramabhadran, B. Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In Proceedings of IEEE international conference on acoustics, speech and signal processing (2013).

[58]

Steinwart, I., Christmann, A., et al. Estimating conditional quantiles with the help of the pinball loss. Bernoulli 17, 1 (2011), 211--225.

[59]

tokbox. Video Chatterbox Nation, 2018. https://tokbox.com/resources/video-chatterbox-2018.

[60]

Wang, J., Tang, J., Xu, Z., Waing, Y., Xue, G., Zhang, X., and Yang, D. Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach. In Proceedings of IEEE INFOCOM (2017).

[61]

Wikipedia. Coefficient of variation. https://en.wikipedia.org/wiki/Coefficient_of_variation, 2019.

[62]

Wikipedia. Memory-mapped file. https://en.wikipedia.org/wiki/Memory-mapped_file, 2019.

[63]

Wikipedia. Peak signal-to-noise ratio. https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio, 2019.

[64]

Winstein, K., Sivaraman, A., and Balakrishnan, H. Stochastic forecasts achieve high throughput and low delay over cellular networks. In Proc. of USENIX NSDI (2013).

Digital Library

[65]

Xie, X., and Zhang, X. POI360: Panoramic Mobile Video Telephony over LTE Cellular Networks. In Proceedings of ACM CoNEXT (2017).

Digital Library

[66]

Xie, X., Zhang, X., Kumar, S., and Li, L. E. piStream: Physical Layer Informed Adaptive Video Streaming over LTE. In Proceedings of ACM MobiCom (2015).

Digital Library

[67]

Xie, X., Zhang, X., and Zhu, S. Accelerating Mobile Web Loading Using Cellular Link Information. In Proceedings of ACM MobiSys (2017).

Digital Library

[68]

Xu, F., Li, Y., Wang, H., Zhang, P., and Jin, D. Understanding mobile traffic patterns of large scale cellular towers in urban environment. IEEE/ACM Transactions on Networking 25, 2 (April 2017), 1147--1161.

Digital Library

[69]

Xu, Q., Mehrotra, S., Mao, Z., and Li, J. PROTEUS: Network Performance Forecast for Real-time, Interactive Mobile Applications. In Proceedings of ACM MobiSys (2013).

Digital Library

[70]

Yue, C., Jin, R., Suh, K., Qin, Y., Wang, B., and Wei, W. LinkForecast: Cellular Link Bandwidth Prediction in LTE Networks. IEEE Transactions on Mobile Computing 17, 7 (July 2018), 1582--1594.

[71]

Zhang, C., and Patras, P. Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks. In Proceedings of ACM MobiHoc (2018).

Digital Library

[72]

Zhou, A., Zhang, H., Su, G., Wu, L., Ma, R., Meng, Z., Zhang, X., Xie, X., Ma, H., and Chen, X. Learning to coordinate video codec with transport protocol for mobile video telephony. In Proceedings of ACM MobiCom (2019).

Digital Library

[73]

Zhu, M., and Gupta, S. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017).

[74]

Zhu, Y., Dong, X., and Lu, T. An Adaptive and Parameter-Free Recurrent Neural Structure for Wireless Channel Prediction. IEEE Transactions on Communications 67, 11 (2019), 8086--8096.

Cited By

Lai ZLi ZWu QLi HLiu WLiu YXie XLi YLiu J(2024)Mind the Misleading Effects of LEO Mobility on End-to-End Congestion ControlProceedings of the 23rd ACM Workshop on Hot Topics in Networks10.1145/3696348.3696867(34-42)Online publication date: 18-Nov-2024
https://dl.acm.org/doi/10.1145/3696348.3696867
Yu EZhou JLi ZTyson GLi WZhang XXu ZXie G(2024)Mustang: Improving QoE for Real-Time Video in Cellular Networks by Masking JitterACM Transactions on Multimedia Computing, Communications, and Applications10.1145/367239920:9(1-23)Online publication date: 10-Jun-2024
https://dl.acm.org/doi/10.1145/3672399
Zhang MLi JZhao HShen LLiu JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)StarStream: Live Video Analytics over Space NetworkingProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680785(7909-7917)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680785
Show More Cited By

Index Terms

PERCEIVE: deep learning-based cellular uplink prediction using real-time scheduling patterns
1. Networks

Recommendations

Range-Based Scheme for Adjusting Transmission Power of Femtocell in Co-Channel Deployment

In heterogeneous networks, femtocells are introduced to improve the network capacity. However, dense deployment of femtocells leads to undesirable interference, which degrades the performance of the system. The interference can be managed and mitigated ...
On improving SINR in LTE HetNets with D2D relays

Femtos, with frequency reuse one, can be deployed in hotspots, offices and residences alike to provide high indoor data rates and reduce traffic load on Macro. However, arbitrarily deployed Femtos could decrease SINR significantly because of inter-cell ...
QoS Guaranteed Resource Allocation Scheme for Cognitive Femtocells in LTE Heterogeneous Networks with Universal Frequency Reuse

In this paper, we propose a novel resource allocation scheme for co-channel interference avoidance in LTE heterogeneous networks with universal spectrum reuse where both macro users (MUs) and cognitive femto base stations (FBSs) within the same ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

MobiSys '20: Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services

June 2020

496 pages

ISBN:9781450379540

DOI:10.1145/3386901

General Chairs:
Eyal de Lara
University of Toronto
,
Iqbal Mohomed
Samsung AI Centre Toronto
,
Program Chairs:
Jason Nieh
Columbia University
,
Elizabeth M. Belding
UC Santa Barbara

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMOBILE: ACM Special Interest Group on Mobility of Systems, Users, Data and Computing

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 June 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Conference

MobiSys '20

Sponsor:

SIGMOBILE

MobiSys '20: The 18th Annual International Conference on Mobile Systems, Applications, and Services

June 15 - 19, 2020

Ontario, Toronto, Canada

Acceptance Rates

Overall Acceptance Rate 274 of 1,679 submissions, 16%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

56
Total Citations
View Citations
3,423
Total Downloads

Downloads (Last 12 months)688
Downloads (Last 6 weeks)93

Reflects downloads up to 13 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Lai ZLi ZWu QLi HLiu WLiu YXie XLi YLiu J(2024)Mind the Misleading Effects of LEO Mobility on End-to-End Congestion ControlProceedings of the 23rd ACM Workshop on Hot Topics in Networks10.1145/3696348.3696867(34-42)Online publication date: 18-Nov-2024
https://dl.acm.org/doi/10.1145/3696348.3696867
Yu EZhou JLi ZTyson GLi WZhang XXu ZXie G(2024)Mustang: Improving QoE for Real-Time Video in Cellular Networks by Masking JitterACM Transactions on Multimedia Computing, Communications, and Applications10.1145/367239920:9(1-23)Online publication date: 10-Jun-2024
https://dl.acm.org/doi/10.1145/3672399
Zhang MLi JZhao HShen LLiu JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)StarStream: Live Video Analytics over Space NetworkingProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680785(7909-7917)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680785
Wang HZhang RLi CXue ZPeng YPang XZhang YRen SShi S(2024)Twist: A Multi-site Transmission Solution for On-demand Video StreamingProceedings of the ACM on Networking10.1145/36562972:CoNEXT2(1-19)Online publication date: 13-Jun-2024
https://dl.acm.org/doi/10.1145/3656297
Ye WHu XSleder SZhang ADayalan UHassan AFezeu RJajoo ALee MRamadan EQian FZhang ZSekar VYu MSeneviratne AVeitch D(2024)Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and PredictionProceedings of the ACM SIGCOMM 2024 Conference10.1145/3651890.3672250(340-357)Online publication date: 4-Aug-2024
https://dl.acm.org/doi/10.1145/3651890.3672250
Wang YZhao DHuang CYang FGao TZhou AZhang HMa HDu YChen A(2024)TrafAda: Cost-Aware Traffic Adaptation for Maximizing Bitrates in Live StreamingIEEE/ACM Transactions on Networking10.1109/TNET.2023.328581232:1(96-109)Online publication date: Feb-2024
https://doi.org/10.1109/TNET.2023.3285812
Raca DZahran ASreenan CSinha RHalepovic EGopalakrishnan V(2024)Device-Based Cellular Throughput Prediction for Video Streaming: Lessons From a Real-World EvaluationIEEE Transactions on Machine Learning in Communications and Networking10.1109/TMLCN.2024.33525412(318-334)Online publication date: 2024
https://doi.org/10.1109/TMLCN.2024.3352541
Tan ZZhao JLi YXu YGuo YLu S(2024)LDRP: Device-Centric Latency Diagnostic and Reduction for Cellular Networks Without RootIEEE Transactions on Mobile Computing10.1109/TMC.2023.326780523:4(2748-2764)Online publication date: Apr-2024
https://doi.org/10.1109/TMC.2023.3267805
Denizer BLandsiedel O(2024)BandSeer: Bandwidth Prediction for Cellular Networks2024 IEEE 49th Conference on Local Computer Networks (LCN)10.1109/LCN60385.2024.10639706(1-8)Online publication date: 8-Oct-2024
https://doi.org/10.1109/LCN60385.2024.10639706
Pérez PFiandrino CFiore MWidmer J(2024)An In-Depth Analysis of Advanced Time Series Forecasting Models for the Open RANIEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)10.1109/INFOCOMWKSHPS61880.2024.10620742(1-6)Online publication date: 20-May-2024
https://doi.org/10.1109/INFOCOMWKSHPS61880.2024.10620742
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

ePub

View this article in ePub.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents