User aware edge caching in 5G wireless networks

Abstract

Wireless technology has become an ultimate weapon in today’s world. Caching has emerged as a vital tool in modern communication systems for reducing peak data rates by allowing popular files to be pre-fetched and then stored at the edge of the network. Caching at small cell base stations has recently been proposed to avoid bottlenecks in the limited capacity backhaul connection link to the core network. For predicting the popularity of the content, we need to analyze the behavior of the user, understanding collectively the behavior beneficial for content trend forecasting and improve network performance. The proposed model predicts the intensity of human emotions through social media (Twitter) and the classifier evaluates the features which are related to user behaviors and, finally, values of features are pushed to the user profile. We further demonstrate how emotions extracted from Twitter can be utilized to improve the forecasting, describing things in a new way which can further be exploited as an optimization basis for network performance enhancement.