Caching Policy for Cache-Enabled D2D Communications by Learning User Preference

Prior works in a designing caching policy do not distinguish content popularity with user preference. In this paper, we illustrate the caching gain by exploiting individual user behavior in sending requests. After showing the connection between the two concepts, we provide a model for synthesizing user preference from content popularity. We then optimize the caching policy with the knowledge of user preference and activity level to maximize the offloading probability for cache-enabled device-to-device communications, and develop a low-complexity algorithm to find the solution. In order to learn user preference, we model the user request behavior resorting to probabilistic latent semantic analysis, and learn the model parameters by the expectation maximization algorithm. By analyzing a Movielens data set, we find that the user preferences are less similar, and the activity level and topic preference of each user change slowly over time. Based on this observation, we introduce a prior knowledge-based learning algorithm for user preference, which can shorten the learning time. Simulation results show a remarkable performance gain of the caching policy with user preference over existing policy with content popularity, both with realistic data set and synthetic data validated by the real data set.

[1]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[2]  Deniz Gündüz,et al.  Learning-based optimization of cache content in a small cell base station , 2014, 2014 IEEE International Conference on Communications (ICC).

[3]  Rui Zhang,et al.  Cooperative Local Caching Under Heterogeneous File Preferences , 2015, IEEE Transactions on Communications.

[4]  Alexandros G. Dimakis,et al.  Femtocaching and device-to-device collaboration: A new architecture for wireless video distribution , 2012, IEEE Communications Magazine.

[5]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[6]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[7]  Alexandros Nanopoulos,et al.  Modeling Users Preference Dynamics and Side Information in Recommender Systems , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[8]  Andreas F. Molisch,et al.  Cache-Enabled Device-to-Device Communications: Offloading Gain and Energy Cost , 2016, IEEE Transactions on Wireless Communications.

[9]  Chenyang Yang,et al.  Energy-Saving Pushing Based on Personal Interest and Context Information , 2016, 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring).

[10]  Samir Ranjan Das,et al.  Understanding traffic dynamics in cellular data networks , 2011, 2011 Proceedings IEEE INFOCOM.

[11]  Alexandros G. Dimakis,et al.  Base-station assisted device-to-device communications for high-throughput wireless video networks , 2012, ICC.

[12]  Thomas Hofmann,et al.  Latent semantic models for collaborative filtering , 2004, TOIS.

[13]  Chenyang Yang,et al.  Caching Policy Optimization for D2D Communications by Learning User Preference , 2017, 2017 IEEE 85th Vehicular Technology Conference (VTC Spring).

[14]  Tracy Camp,et al.  A survey of mobility models for ad hoc network research , 2002, Wirel. Commun. Mob. Comput..

[15]  Kishor S. Trivedi.  Probability and Statistics with Reliability, Queuing, and Computer Science Applications , 1984 .

[16]  Alexandros G. Dimakis,et al.  FemtoCaching: Wireless video content delivery through distributed caching helpers , 2011, 2012 Proceedings IEEE INFOCOM.

[17]  Virgílio A. F. Almeida,et al.  Characterization and Analysis of User Profiles in Online Video Sharing Systems , 2010, J. Inf. Data Manag..

[18]  HofmannThomas.  Latent semantic models for collaborative filtering , 2004 .

[19]  Jan Vondrák,et al.  Maximizing a Monotone Submodular Function Subject to a Matroid Constraint , 2011, SIAM J. Comput..

[20]  Serge Fdida,et al.  A survey on predicting the popularity of web content , 2014, Journal of Internet Services and Applications.

[21]  Xiaofei Wang,et al.  Cache in the air: exploiting content caching and delivery techniques for 5G systems , 2014, IEEE Communications Magazine.

[22]  Mérouane Debbah,et al.  Proactive small cell networks , 2013, ICT 2013.

[23]  Mehdi Bennis,et al.  Living on the edge: The role of proactive caching in 5G wireless networks , 2014, IEEE Communications Magazine.

[24]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[25]  Dong Liu,et al.  Energy Efficiency of Downlink Networks With Caching at Base Stations , 2015, IEEE Journal on Selected Areas in Communications.

[26]  M. Draief,et al.  Placing dynamic content in caches with small population , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[27]  Giuseppe Caire,et al.  Wireless Device-to-Device Caching Networks: Basic Principles and System Performance , 2013, IEEE Journal on Selected Areas in Communications.

[28]  Meixia Tao,et al.  Modeling, Analysis, and Optimization of Coded Caching in Small-Cell Networks , 2017, IEEE Transactions on Communications.

[29]  Abdallah Khreishah,et al.  A Provably Efficient Online Collaborative Caching Algorithm for Multicell-Coordinated Systems , 2015, IEEE Transactions on Mobile Computing.

[30]  Dong Liu,et al.  Caching at the wireless edge: design aspects, challenges, and future directions , 2016, IEEE Communications Magazine.

[31]  Zongpeng Li,et al.  Youtube traffic characterization: a view from the edge , 2007, IMC '07.

[32]  Bartlomiej Blaszczyszyn,et al.  Optimal geographic caching in cellular networks , 2014, 2015 IEEE International Conference on Communications (ICC).

[33]  Yang Yang,et al.  Semigradient-Based Cooperative Caching Algorithm for Mobile Social Networks , 2016, 2016 IEEE Global Communications Conference (GLOBECOM).

[34]  Terry Williams,et al.  Probability and Statistics with Reliability, Queueing and Computer Science Applications , 1983 .

[35]  Hui Liu,et al.  Push-Based Wireless Converged Networks for Massive Multimedia Content Delivery , 2014, IEEE Transactions on Wireless Communications.

[36]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[37]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[38]  Ahmed Helmy,et al.  Modeling Time-Variant User Mobility in Wireless Mobile Networks , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[39]  Pablo Rodriguez,et al.  I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system , 2007, IMC '07.

[40]  Mehdi Bennis,et al.  Big data meets telcos: A proactive caching perspective , 2015, Journal of Communications and Networks.

[41]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.

[42]  Mehrbakhsh Nilashi,et al.  Collaborative filtering recommender systems , 2013 .

[43]  H. Vincent Poor,et al.  A Learning-Based Approach to Caching in Heterogenous Small Cell Networks , 2015, IEEE Transactions on Communications.

[44]  Martha Larson,et al.  Collaborative Filtering beyond the User-Item Matrix , 2014, ACM Comput. Surv..

[45]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..

[46]  Ying Wang,et al.  Clustered device-to-device caching based on file preferences , 2016, 2016 IEEE 27th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[47]  Urs Niesen,et al.  Fundamental limits of caching , 2012, 2013 IEEE International Symposium on Information Theory.

[48]  Min Sheng,et al.  Learning-Based Content Caching and Sharing for Wireless Networks , 2017, IEEE Transactions on Communications.