# Diversified caching algorithm with cooperation between edge servers

## TL;DR

This paper introduces a new caching algorithm for edge servers that improves performance by collaborating between servers and increasing cache diversity.

## Contribution

The novel diversified caching method leverages inter-server collaboration to improve cache hit rates and service efficiency in edge computing.

## Key findings

- The proposed method improves cache hit rates by 27.01–37.43%.
- It reduces average service delay by 25.57–30.68%.
- The algorithm maintains good performance even as the edge computing platform scales.

## Abstract

Edge computing makes up for the high latency of the central cloud network by deploying server resources in close proximity to users. The storage and other resources configured by edge servers are limited, and a reasonable cache replacement strategy is conducive to improving the cache hit ratio of edge services, thereby reducing service latency and enhancing service quality. The spatiotemporal correlation of user service request distribution brings opportunities and challenges to edge service caching. The collaboration between edge servers is often ignored in the existing research work for caching decisions, which can easily lead to a low edge cache hit rate, thereby reducing the efficiency of edge resource use and service quality. Therefore, this article proposes a diversified caching method to ensure the diversity of edge cache services, utilizing inter-server collaboration to enhance the cache hit rate. After the service request reaches the server, if it misses, the proposed algorithm will judge whether the neighbor node can provide services through the cache information of the neighbor node, and then the server and the neighbor node jointly decide how to cache the service. At the same time, the performance of the proposed diversified caching method is evaluated through a large number of simulation experiments, and the experimental results show that the proposed method can improve the cache hit rate by 27.01–37.43%, reduce the average service delay by 25.57–30.68%, and with the change of the scale of the edge computing platform, the proposed method can maintain good performance.