基于联邦学习的在线短视频内容分发策略

doi:10.11772/j.issn.1001-9081.2020121936

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1551-1556.DOI: 10.11772/j.issn.1001-9081.2020121936

所属专题： 2020年全国开放式分布与并行计算学术年会（DPCS 2020）

• 2020年全国开放式分布与并行计算学术年会（DPCS 2020） • 上一篇下一篇

基于联邦学习的在线短视频内容分发策略

董文涛^1,2, 李卓^1,2, 陈昕²

1. 网络文化与数字传播北京市重点实验室(北京信息科技大学), 北京 100101;
2. 北京信息科技大学计算机学院, 北京 100101

收稿日期:2020-11-04 修回日期:2021-03-29 出版日期:2021-06-10 发布日期:2021-06-21
通讯作者: 李卓
作者简介:董文涛(1995-),男,山东菏泽人,硕士研究生,主要研究方向:边缘计算;李卓(1983-),男,河南南阳人,副教授,博士,CCF会员,主要研究方向:移动无线网络、分布式计算;陈昕(1965-),男,江西南昌人,教授,博士,CCF会员,主要研究方向:网络性能评价、网络安全。
基金资助:
国家自然科学基金资助项目（61872044）；北京市青年拔尖人才培育计划资助项目（CIT&TCD201804055）；网络文化与数字传播北京市重点实验室开放课题资助项目（ICDDXN001）。

Online short video content distribution strategy based on federated learning

DONG Wentao^1,2, LI Zhuo^1,2, CHEN Xin²

1. Beijing Key Laboratory of Internet Culture and Digital Dissemination Research(Beijing Information Science and Technology University), Beijing 100101, China;
2. Computer School, Beijing Information Science and Technology University, Beijing 100101, China

Received:2020-11-04 Revised:2021-03-29 Online:2021-06-10 Published:2021-06-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61872044), the Beijing Municipal Program for Young Top Talent Cultivation (CIT&TCD201804055),the Open Program of Beijing Key Laboratory of Internet Culture and Digital Dissemination Research (ICDDXN001).

摘要/Abstract

摘要： 为提升短视频内容分发的精度，分析用户所属社交群体的兴趣倾向和对短视频内容的个性化需求，在基于主动推荐方式的短视频应用场景中，以视频内容提供商利润最大化为优化目标，设计了一种短视频内容分发策略。首先，基于联邦学习，利用用户群本地相册数据训练兴趣预测模型，提出用户群兴趣向量预测算法并得到用户群的兴趣向量表示；然后，以用户群的兴趣向量作为输入，基于组合置信上界（CUCB）算法实时设计相应的短视频内容分发策略，从而使视频内容提供商获取的长期利润最大化。所提策略获得的平均利润相对稳定且明显优于单纯基于CUCB的短视频分发策略得到的平均利润；与置信上界（UCB）策略和随机策略相比，所提策略使得视频内容提供商获得的总利润分别提高了12%和30%。实验结果表明，所提短视频内容分发策略能有效地提升短视频分发的精度，从而进一步提高视频内容提供商获取的利润。

关键词: 移动边缘计算, 内容分发, 联邦学习, 短视频, 用户群兴趣向量

Abstract: To improve the accuracy of short video content distribution, the interest tendencies and the personalized demands for short video content of social groups that the users belong to were analyzed, and in the short video application scenarios based on the active recommendation approaches, a short video content distribution strategy was designed with the goal of maximizing the profit of video content providers. Firstly, based on the federated learning, the interest prediction model was trained by using the local album data of the user group, and the user group interest vector prediction algorithm was proposed and the interest vector representation of the user group was obtained. Secondly, using the interest vector as the input, the corresponding short video content distribution strategy was designed in real time based on the Combinatorial Upper Confidence Bound (CUCB) algorithm, so that the long-term profit obtained by the video content providers was maximized. The average profit obtained by the proposed strategy is relatively stable and significantly better than that obtained by the short video distribution strategy only based on CUCB; in terms of total profit of video providers, compared with the Upper Confidence Bound (UCB) strategy and random strategy, the proposed strategy increases by 12% and 30% respectively. Experimental results show that the proposed short video content distribution strategy can effectively improve the accuracy of short video distribution, so as to further increase the profit obtained by video content providers.

Key words: mobile edge computing, content distribution, federated learning, short video, user group interest vector

中图分类号:

TP393.01

董文涛, 李卓, 陈昕. 基于联邦学习的在线短视频内容分发策略[J]. 计算机应用, 2021, 41(6): 1551-1556.

DONG Wentao, LI Zhuo, CHEN Xin. Online short video content distribution strategy based on federated learning[J]. Journal of Computer Applications, 2021, 41(6): 1551-1556.

参考文献

[1] Cisco. Cisco annual internet report(2018-2023)white paper[EB/OL].[2020-07-09]. https://www.cisco.com/c/en/us/solutions/collateral/executive-perspectives/annual-internet-report/white-paperc11-741490. html.
[2] 王广增. 关于5G移动通信关键技术的分析及其未来发展前景分析[J]. 中国新通信, 2015, 17(19):56.(WANG G Z. Analysis of 5G mobile communication key technologies and analysis of their future development prospects[J]. China New Telecommunications, 2015,17(19):56.)
[3] OUGHTON E, FRIAS Z, RUSSELL T, et al. Towards 5G:scenario-based assessment of the future supply and demand for mobile telecommunications infrastructure[J]. Technological Forecasting and Social Change,2018,133:141-155.
[4] 抖音短视频APP. 2019年抖音数据报告[EB/OL].[2020-07-09]. https://lmtw.com/mzw/content/detail/id/180878. (Douyin short video APP. 2019 Douyin data report[EB/OL].[2020-07-09]. https://lmtw.com/mzw/content/detail/id/180878.)
[5] ZHANG M,LUO H,ZHANG H. A survey of caching mechanisms in information-centric networking[J]. IEEE Communications Surveys and Tutorials,2015,17(3):1473-1499.
[6] LI C,TONI L,ZOU J,et al. QoE-driven mobile edge caching placement for adaptive video streaming[J]. IEEE Transactions on Multimedia,2018,20(4):965-984.
[7] 王舒平, 张毅, 韦文闻, 等. 内容分发网络预取技术综述[J]. 电子技术应用, 2019, 45(4):23-28.(WANG S P,ZHANG Y,WEI W W,et al. Overview of prefetching technology in content deliver networks[J]. Application of Electronic Technique,2019,45(4):23-28.)
[8] ULLAH S,THAR K,HONG C S. Management of scalable video streaming in information centric networking[J]. Multimedia Tools and Applications,2017,76(20):21519-21546.
[9] 柳兴, 杨震, 王新军, 等. 移动边缘计算中的内容分发加速策略[J]. 计算机应用, 2020, 40(5):1389-1391.(LIU X,YANG Z, WANG X J,et al. Content distribution acceleration strategy in mobile edge computing[J]. Journal of Computer Applications, 2020,40(5):1389-1391.)
[10] CHEN M,LEUNG V C M. From cloud-based communications to cognition-based communications:a computing perspective[J]. Computer Communications,2018,128:74-79.
[11] CHEN M,HAO Y,LIN K,et al. Label-less learning for traffic control in an edge network[J]. IEEE Network,2018,32(6):8-14.
[12] LECUN Y,BENGIO Y,HINTON G. Deep learning[J]. Nature, 2015,521(7553):436.
[13] DEVOOGHT R, BERSINI H. Collaborative filtering with recurrent neural networks[EB/OL].[2020-07-09]. https://arxiv.org/pdf/1608.07400.pdf.
[14] LI C,LIU J,OUYANG S. Characterizing and predicting the popularity of online videos[J]. IEEE Access,2016,4:1630-1641.
[15] LIU W,ZHANG J,LIANG Z,et al. Content popularity prediction and caching for ICN:a deep learning approach with SDN[J]. IEEE Access,2018,6:5075-5089.
[16] CHEN M,SAAD W,YIN C,et al. Echo state networks for proactive caching in cloud-based radio access networks with mobile users[J]. IEEE Transactions on Wireless Communications,2017,16(6):3520-3535.
[17] TSAI K C,WANG L,HAN Z,et al. Mobile social media networks caching with convolutional neural network[C]//Proceedings of the 2018 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE,2018:83-88.
[18] THAR K,TRAN N H,OO T Z,et al. DeepMEC:mobile edge caching using deep learning[J]. IEEE Access,2018,6:78260-78275.
[19] BONAWITZ K,EICHNER H,GRIESKAMP W,et al. Towards federated learning at scale:system design[EB/OL].[2020-07-09]. https://arxiv.org/pdf/1902.01046.pdf.
[20] WANG S,TUOR T,SALONIDIS T,et al. Adaptive federated learning in resource constrained edge computing systems[J]. IEEE Journal on Selected Areas in Communications,2019,37(6):1205-1221.
[21] HAO Y,HU L,QIAN Y,et al. Profit maximization for video caching and processing in edge cloud[J]. IEEE Journal on Selected Areas in Communications,2019,37(7):1632-1641.
[22] HOWARD A G,ZHU M,CHEN B,et al. MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2020-07-09]. https://arxiv.org/pdf/1704.04861.pdf.
[23] CHEN W, WANG Y, YUAN Y. Combinatorial multi-armed bandit:general framework, results and applications[C]//Proceedings of the 2013 30th International Conference on Machine Learning. New York:JMLR. org,2013:151-159.

基于联邦学习的在线短视频内容分发策略

Online short video content distribution strategy based on federated learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郭棉, 张锦友. 移动边缘计算环境中面向机器学习的计算迁移策略[J]. 计算机应用, 2021, 41(9): 2639-2645.
[2]	王家瑞, 谭国平, 周思源. 高速车联网场景下分簇式无线联邦学习算法[J]. 计算机应用, 2021, 41(6): 1546-1550.
[3]	王艺洁, 凡佳飞, 王陈宇. 云边环境下基于博弈论的两阶段任务迁移策略[J]. 计算机应用, 2021, 41(5): 1392-1398.
[4]	毛莺池, 徐雪松, 刘鹏飞. 基于稳定匹配的多用户任务卸载策略[J]. 计算机应用, 2021, 41(3): 786-793.
[5]	罗长银, 陈学斌, 马春地, 王君宇. 面向区块链的在线联邦增量学习算法[J]. 计算机应用, 2021, 41(2): 363-371.
[6]	王岱巍, 徐高潮, 李龙. 无人机辅助的移动边缘计算中的任务分配策略[J]. 计算机应用, 2021, 41(10): 2928-2936.
[7]	吴雨芯, 蔡婷, 张大斌. 移动边缘计算中基于Stackelberg博弈的算力交易与定价[J]. 计算机应用, 2020, 40(9): 2683-2690.
[8]	罗斌, 于波. 移动边缘计算中基于粒子群优化的计算卸载策略[J]. 计算机应用, 2020, 40(8): 2293-2298.
[9]	柳兴, 杨震, 王新军, 朱恒. 移动边缘计算中的内容分发加速策略[J]. 计算机应用, 2020, 40(5): 1389-1391.
[10]	黄冬艳, 付中卫, 王波. 计算资源受限的移动边缘计算服务器收益优化策略[J]. 计算机应用, 2020, 40(3): 765-769.
[11]	张君如, 赵晓焱, 袁培燕. 面向用户隐私保护的联邦安全树算法[J]. 计算机应用, 2020, 40(10): 2980-2985.
[12]	袁培燕, 蔡云云. 移动边缘计算中一种贪心策略的内容卸载方案[J]. 计算机应用, 2019, 39(9): 2664-2668.
[13]	余韵, 连晓灿, 朱宇航, 谭国平. 增强现实场景下移动边缘计算资源分配优化方法[J]. 计算机应用, 2019, 39(1): 22-25.
[14]	刘靖, 赵文举. 融合P2P技术的云平台快速内容分发方法[J]. 计算机应用, 2017, 37(1): 31-36.
[15]	邓志刚, 曾国荪, 谭云兰, 熊焕亮. 云存储内容分发网络中的能耗优化方法[J]. 计算机应用, 2016, 36(6): 1515-1519.