Mobile social media networks caching with convolutional neural network

Nowadays, people use mobile social media networks such as Twitter and Facebook to connect with others. In this work, we discuss the problem of context-aware data caching in the heterogeneous small cell networks (HSCNs) to reduce the service delay for the end users. In the data-caching model, there a...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) pp. 83 - 88
Main Authors Tsai, Kuo Chun, Wang, Li, Han, Zhu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2018
Subjects
Base stations
Cache storage
caching
Conferences
deep learning
Delays
HetNet
Machine learning
mobile social media network
natural language processing
Resource management
Social network services
Online AccessGet full text

Cover

More Information
Summary:Nowadays, people use mobile social media networks such as Twitter and Facebook to connect with others. In this work, we discuss the problem of context-aware data caching in the heterogeneous small cell networks (HSCNs) to reduce the service delay for the end users. In the data-caching model, there are three types of cache entities, which are edge caching elements (CAEs), small cell base stations (SBSs), and macro cell base stations (MBS). We propose a deep learning model using the convolutional neural network (CNN) to apply sentence analysis on the data and extract information content in the data from end users. We can predict the data that will most likely to be requested by the end users to reduce service latency by caching the data close to the end users by the interest of the end users. We shows the effectiveness of our proposed algorithm by comparing with other approaches in our simulation.
DOI:10.1109/WCNCW.2018.8368988