基于深度学习的智能移动边缘网络缓存

doi:10.7523/j.issn.2095-6134.2020.01.015

中国科学院大学学报 ›› 2020, Vol. 37 ›› Issue (1): 128-135.DOI: 10.7523/j.issn.2095-6134.2020.01.015

基于深度学习的智能移动边缘网络缓存

宋旭鸣^1,2,3, 沈逸飞³, 石远明³

1 中国科学院上海微系统与信息技术研究所, 上海 200050;
2 中国科学学院大学, 北京 100049;
3 上海科技大学信息科学与技术学院, 上海 201210

收稿日期:2018-11-02 修回日期:2019-01-09 发布日期:2020-01-15
通讯作者: 宋旭鸣
基金资助:
国家自然科学基金（61601290）和上海扬帆计划（16YF1407700）资助

Intelligent mobile edge network caching based on deep learning

SONG Xuming^1,2,3, SHEN Yifei³, SHI Yuanming³

1 Shanghai Institute of Microsystem & Information Technology, Chinese Academy of Sciences, Shanghai 200050, China;
2 University of Chinese Academy of Sciences, Beijing 100049, China;
3 School of Information Science & Technology, ShanghaiTech University, Shanghai 201210, China

Received:2018-11-02 Revised:2019-01-09 Published:2020-01-15

摘要/Abstract

摘要： 针对移动边缘网络缓存问题，提出把计算资源推送到网络边缘，使边缘接入热点能有数据分析能力，构建基于深度学习的深度缓存策略，进一步提升缓存效率。在边缘接入热点处构建基于长短期记忆神经网络模型的缓存内容文件流行度预测系统，通过分析本地数据给出内容文件流行度预测。把内容文件流行度预测系统整合到移动边缘网络缓存系统中最大化缓存命中率，提出深度缓存策略，大大提升移动边缘网络缓存性能。在真实视频数据集上进行测试，实验结果表明：提出的内容流行度预测系统的准确度高于现有最优方法；提出的深度缓存策略与传统的缓存算法相比，在相同的缓存命中率指标下大约仅需一半的缓存存储空间。

关键词: 移动边缘网络缓存, 深度学习, 长短期记忆神经网络, 内容文件流行度预测, 缓存命中率

Abstract: In view of mobile edge network caching problem, computation resources are further pushed to the network edge to enable data analysis and to build deep learning-based caching strategy at access points, thereby boosting caching gain. The long short term memory (LSTM)-based neural network is proposed to predict the future content popularity by analysing the local data, which is further used to optimize content replacement for the cache hit rate maximization and construct deep caching strategy. Real-world dataset is used to validate the effectiveness of the proposed deep caching strategy. Numerical results demonstrate that our content popularity prediction method outperforms the state-of-art prediction method. Compared with traditional methods, the caching system needs only approximately half storage space to achieve the same cache hit rate.

Key words: mobile edge network caching, deep learning, long short term memory(LSTM) neural network, file popularity prediction, cache hit rate

中图分类号:

TN92

宋旭鸣, 沈逸飞, 石远明. 基于深度学习的智能移动边缘网络缓存[J]. 中国科学院大学学报, 2020, 37(1): 128-135.

SONG Xuming, SHEN Yifei, SHI Yuanming. Intelligent mobile edge network caching based on deep learning[J]. , 2020, 37(1): 128-135.

参考文献

[1] Bi S Z, Zhang R, Ding Z, et al. Wireless communications in the era of big data[J]. IEEE Communications Magazine, 2015, 53(10):190-199.
[2] CISCO, Inc. Cisco visual networking index:global mobile data traffic forecast[R/OL]. (2017-02)[2018-10-20]. https://www.cisco.com/c/en/us/soltions/collateral/service-provider/visual-networking-index-vni/mobile-white-paper-c11-520862.html.
[3] Maddah M, Niesen U. Fundamental limits of caching[J]. IEEE Transactions on Infromation Theory, 2014, 60(5):2856-2867.
[4] Bastug E, Bennis M, Debbah M. Living on the edge:the role of proactive caching in 5g wireless networks[J]. IEEE Communications Magazine, 2014, 52(8):82-89.
[5] 余江, 邱玲. 密集小站网络下基于协作滤波的缓存内容决策和用户归属[J]. 中国科学院大学学报, 2016, 33(6):802-807.
[6] Mohamed A, Traverso S, Giaccone P et al. Analyzing the performance of lru caches under non-stationary traffic patterns[J]. ArXiv Preprint, 2013, 1301.4909.
[7] Jaleel A, Theobald K, Steely S, et al. High performance cache replacement using re-reference interval prediction (RRIP)[C]//ACM SIGARCH Computer Architecture News. New York:ACM, 2010:60-71.
[8] Müller S, Atan O, Schaar M, et al. Context-aware proactive content caching with service differentiation in wireless networks[J]. IEEE Transactions on Wireless Communications, 2017, 16(2):1024-1036.
[9] Li S H, Xu J, Schaar M, et al. Trend-aware video caching through online learning[J]. IEEE Transactions on Multimedia, 2016, 18(12):2503-2516.
[10] Azimi S, Simeone O, Sengupta A, et al. Online edge caching and wireless delivery in fog-aided networks with dynamic content popularity[J]. IEEE Journal on Selected Areas in Communications, 2018, 36(6):1189-1202.
[11] Somuyiwa S, György A, Gündüz D. A reinforcement-learning approach to proactive caching in wireless networks[J]. IEEE Journal on Selected Areas in Communications, 2018, 36(6):1331-1344.
[12] Szabo G, Huberman B. Predicting the popularity of online content[J]. Communications of the ACM, 2010, 53(8):80-88.
[13] Trzciński T, Rokita P. Predicting popularity of online videos using support vector regression[J]. IEEE Transactions on Multimedia, 2017, 19(11):2561-2570.
[14] Wang X F, Han Y W, Wang C Y, et al. In-Edge AI:intelligentizing mobile edge computing caching and communication by federated learning[J]. ArXiv Preprint, 2018, 1809.07857.
[15] Lei L, You L, Dai G Y, et al. A deep learning approach for optimizing content delivering in cache-enabled HetNet[C]//Wireless Communication Systems (ISWCS), 2017 International Symposium on. Bologna:IEEE, 2017:449-453.
[16] Martello S, Pisinger D, Toth P. New trends in exact algorithms for the 0~1 Knapsack problem[J]. European Journal of Operational Research, 2000, 123(2):325-332.
[17] Ma N, Tian G D, Zhou X. A lip-reading recognition approach based on long short-term memory[J]. Journal of University of Chinese Academy of Sciences, 2018, 35(1):109-117.
[18] Friedman J, Hastie T, Tibshirani R. The elements of statistical learning[M]. New York:Springer Series in Statistics, 2001.
[19] Werbos P.J. Backpropagation through time:what it does and how to do it[J]. IEEE Proceedings, 1990, 78(10):1550-1560.
[20] Sak H, Senior A, Beaufays F. Long short-term memory recurrent neural network architectures for large scale acoustic modeling[C]//Fifteenth annual Conference of the International Speech Communication Association. Singapore:ISCA Archive, 2014:338-342.
[21] Goodfellow I, Bengio Y, Courville A, et al. Deep learning[M]. Cambridge:MIT press, 2016.
[22] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[23] Rossi D, Rossini G. Caching performance of content centric networks under multi-path routing[J]. Relatório técnico, Telecom ParisTech, 2011:1-6.
[24] Amer R, Butt M, Bennis M, et al. Delay analysis for wireless D2D caching with inter-cluster cooperation[C]//2017 IEEE Global Communications Conference (GLOBECOM). Sigapore:IEEE, 2017:1-7.

基于深度学习的智能移动边缘网络缓存

Intelligent mobile edge network caching based on deep learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	肖亚楠, 周伟, 崔杰, 刘亭亭, 肖灵. 一种LSTM神经网络和卡尔曼滤波相结合的复合材料承载预测方法[J]. 中国科学院大学学报, 2021, 38(3): 374-381.
[2]	周龙, 王伟强, 吕科. FACR：一种快速且准确的车辆识别器[J]. 中国科学院大学学报, 2021, 38(1): 130-136.
[3]	李森, 彭玲, 胡媛, 池天河. 基于FD-RCF的高分辨率遥感影像耕地边缘检测[J]. 中国科学院大学学报, 2020, 37(4): 483-489.
[4]	卢凯旋, 李国清, 陈正超, 昝露洋, 李柏鹏, 高建威. 基于负样本多通道优化SSD网络的钢铁厂提取[J]. 中国科学院大学学报, 2020, 37(3): 352-359.
[5]	闫凯, 沈汀, 陈正超, 闫弘轩. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020, 37(3): 360-367.
[6]	刘洋, 罗晨希, 罗铁坚. 和积网络的性质分析及其有效性验证算法[J]. 中国科学院大学学报, 2020, 37(1): 136-143.