Efficient Cache Availability Management in Information-Centric Networks

TL;DR

This paper proposes a distributed caching architecture for Information-centric networks that significantly improves cache storage efficiency and reduces server load by using controlled traffic redirection and selective caching.

Contribution

It introduces a novel distributed cache management approach that enhances cache utilization and reduces signaling overhead in ICN.

Findings

9-fold increase in cache storage efficiency

20% reduction in server load

Efficient cache utilization with minimal signaling

Abstract

In-network caching is one of the fundamental operations of Information-centric networks (ICN). The default caching strategy taken by most of the current ICN proposals is caching along--default--path, which makes popular objects to be cached redundantly across the network, resulting in a low utilization of available cache space. On the other hand, efficient use of network-wide cache space requires possible cooperation among caching routers without the use of excessive signaling burden. While most of the cache optimization efforts strive to improve the latency and the overall traffic efficiency, we have taken a different path in this work and improved the storage efficiency of the cache space so that it is utilized to its most. In this work we discuss the ICN caching problem, and propose a novel distributed architecture to efficiently use the network-wide cache storage space based on distributed caching. The proposal achieves cache retention efficiency by means of controlled traffic redirection and selective caching. We utilize the ICN mechanisms and routing protocol messages for decision making, thus reducing the overall signaling need. Our proposal achieves almost 9-fold increase in cache storage efficiency, and around 20% increase in server load reduction when compared to the classic caching methods used in contemporary ICN proposals.