Deep Learning Model for Content Aware Caching at MEC Servers

Abstract

In recent years, mobile data traffic has increased enormously with an increase of mobile and smart devices. The global mobile data traffic is set to increase manifold in the coming years. With the rise in mobile data traffic and heterogeneous mobile devices, substantial improvement has been achieved in wireless media technology in providing a varied range of multimedia services. These multimedia services are often resource-hungry and require high-speed data and low latency transmissions. High-speed networks like the fifth-generation (5G) network helps in faster data delivery resulting in less congestion at the backhaul links and higher transmission capacity. Integrating Mobile Edge Computing (MEC) capabilities into the cellular architecture provides advantages like intelligent and efficient context-aware caching and video adaptations for content delivery. The primary objective of this work is to reduce the overall backhaul congestion and access delay by increasing the cache hit rate at the MEC server. This work proposes a deep learning-based model for caching at the MEC servers based on the content popularity at different time slots of a day. Experimental results reveal that the proposed model outperforms the state-of-the-art standard caching approaches, improves the cache hit probability by almost 21%, and decreases backhaul usage and access delay by approximately 18%.