Learning at the Edge: Smart Content Delivery in Real World Mobile Social Networks

The explosive growth of network traffic in recent years is largely attributed to the rising demand of content delivery in mobile networks. MSN has become the top mobile application, ranked by the number of daily active users and the daily time spent by users. This introduces new challenges for content delivery due to highly dynamic distribution of mobile users and their requests for content. It is important for content providers to understand how edge users' mobility and their consumed social content can affect the network traffic in the underlying content distribution network. To study this problem, we present a machine learning based framework for predicting the dynamics of content demands of MSN users at the network edge. It employs a smart content delivery scheme to dynamically deliver the content to users according to their future demands as predicted. We compare four regression models in predicting the number of requests to certain content. Then we evaluate the performance of the smart content delivery scheme over a realworld commercial content distribution network for WeChat.

[1]  Dario Pompili,et al.  Cooperative Hierarchical Caching in 5G Cloud Radio Access Networks , 2017, IEEE Network.

[2]  Kaigui Bian,et al.  Mobile Social Big Data: WeChat Moments Dataset, Network Applications, and Opportunities , 2018, IEEE Network.

[3]  Xiaofei Wang,et al.  D2D Big Data: Content Deliveries over Wireless Device-to-Device Sharing in Large-Scale Mobile Networks , 2018, IEEE Wireless Communications.

[4]  George C. Polyzos,et al.  Addressing niche demand based on joint mobility prediction and content popularity caching , 2016, Comput. Networks.

[5]  Zhou Su,et al.  Content distribution over content centric mobile social networks in 5G , 2015, IEEE Communications Magazine.

[6]  Kaigui Bian,et al.  Proactive Video Push for Optimizing Bandwidth Consumption in Hybrid CDN-P2P VoD Systems , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[7]  Vikram Krishnamurthy,et al.  Adaptive Scheme for Caching YouTube Content in a Cellular Network: Machine Learning Approach , 2017, IEEE Access.

[8]  Ying Wang,et al.  A novel design for content delivery over software defined mobile social networks , 2015, IEEE Network.

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

[10]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[11]  Min Chen,et al.  Data-Driven Computing and Caching in 5G Networks: Architecture and Delay Analysis , 2018, IEEE Wireless Communications.

[12]  Alireza Sadeghi,et al.  Optimal and Scalable Caching for 5G Using Reinforcement Learning of Space-Time Popularities , 2017, IEEE Journal of Selected Topics in Signal Processing.

[13]  Gwendal Simon,et al.  Congestion Avoidance and Load Balancing in Content Placement and Request Redirection for Mobile CDN , 2018, IEEE/ACM Transactions on Networking.

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