# Distributed Edge Caching Scheme Considering the Tradeoff Between the Diversity and Redundancy of Cached Content

## TL;DR

This paper introduces a distributed edge caching scheme that optimally balances content diversity and redundancy to minimize network transmission costs, using particle swarm optimization and simulation analysis.

## Contribution

It formulates a novel redundancy caching problem and applies an adapted PSO algorithm to find the optimal redundancy ratio for cost reduction.

## Key findings

- Optimal redundancy ratio depends on backhaul to RAN cost ratio and file popularity distribution.
- Network total cost can be reduced by up to 54% with optimal caching.
- Cost reduction can reach up to 57% under typical request patterns.

## Abstract

Caching popular contents at the edge of cellular networks has been proposed to reduce the load, and hence the cost of backhaul links. It is significant to decide which files should be cached and where to cache them. In this paper, we propose a distributed caching scheme considering the tradeoff between the diversity and redundancy of base stations' cached contents. Whether it is better to cache the same or different contents in different base stations? To find out this, we formulate an optimal redundancy caching problem. Our goal is to minimize the total transmission cost of the network, including cost within the radio access network (RAN) and cost incurred by transmission to the core network via backhaul links. The optimal redundancy ratio under given system configuration is obtained with adapted particle swarm optimization (PSO) algorithm. We analyze the impact of important system parameters through Monte-Carlo simulation. Results show that the optimal redundancy ratio is mainly influenced by two parameters, which are the backhaul to RAN unit cost ratio and the steepness of file popularity distribution. The total cost can be reduced by up to 54% at given unit cost ratio of backhaul to RAN when the optimal redundancy ratio is selected. Under typical file request pattern, the reduction amount can be up to 57%.