Video on Demand Streaming Using RL-based Edge Caching in 5G Networks

TL;DR

This paper proposes an RL-based edge caching scheme for 5G networks that adapts to content popularity, improving delay and backhaul traffic, and demonstrates its effectiveness through implementation and KPI measurement.

Contribution

Introduces a reinforcement learning-based caching method for 5G edge networks, implemented as VNFs, enhancing VoD streaming performance.

Findings

Increased cache hit ratio in 5G edge caching

Effective adaptation to time-location-dependent content popularity

Scalable and reliable VoD streaming with RL-based caching

Abstract

Edge caching can significantly improve the 5G networks' performance both in terms of delay and backhaul traffic. We use a reinforcement learning-based (RL-based) caching technique that can adapt to time-location-dependent popularity patterns for on-demand video contents. In a private 5G, we implement the proposed caching scheme as two virtual network functions (VNFs), edge and remote servers, and measure the cache hit ratio as a KPI. Combined with the HLS protocol, the proposed video-on-demand (VoD) streaming is a reliable and scalable service that can adapt to content popularity.