Neighborhood search and admission control in cooperative caching networks

Abstract

In-network caching of content is a popular technique for eliminating redundant traffic from the network and improve the performance of network applications. In this paper we present a novel cooperative caching strategy to improve performance of in-network caches. Our cooperative scheme is composed of an admission policy for the incoming data and a content exchange protocol between neighbor network caches to improve the search zone. The admission policy enforces that a previously cached data is not unnecessary replicated in other caches, resulting in more space for new data. The content exchange protocol allows for exchange on cached data, increasing the hit rate for incoming requests. The benefits are twofold: first, we reduce the redundant content caching in the network, and second, we improve the hit rate by informing the content cached in the nearby caches. As a proof-of-concept, we have implemented a prototype and evaluated its performance using different large-scale topologies against standard non-cooperative caching algorithms. Our numerical results show that both admission and content exchange policies yield large performance gains over standard algorithms.

A Distributed Caching based on Neighbor Cooperation in CCN

“…Content requests for different content are generated based on content popularity which follows the Zipf-distribution. We set the period of exchange message between neighbors to 120 s and compare the performance of NCCS against: the Leave Cache Everywhere (LCE) algorithm [3], and the Neighbor Search (NS) algorithm [10]. In LCE, each node cache everything received with the Least Frequently Used (LFU) replacement algorithm.…”

“…In addition, considering that the availability of cached content varies over time, nodes should avoid exchanging short-lived items which belong to the category of the unpopular content.In fact, our approach is focus on eliminating redundancy caused by these relative popular contents.So each node will only exchange its caches of these relative popular contents. We can also use Bloom Filters to encode the information of cached items as in [10]. In practice, each node independ ently sets up the criteria to classify the content to control which content items to exchange.…”

“…However all content are only cached in those "important" nodes, which results in unbalanced resource utilization between nodes. In [10], authors proposed a cached bit admission policy to ensure just one node along the delivery path caches the content. But the way about how to choose the node is not declared.…”

Enhancing in-network caching by coupling cache placement, replacement and location

“…The works in [18], [19] propose to aggressively advertise the reachability of cached content in the routing system, but it is impractical as it imposes significant burden on the routing system in terms of maintaining dynamic states of a large number of high volatile cached items. Instead, Breadcrumbs [20] adopts an implicit and best effort approach towards cache location by storing the most recent direction and time that an item was forwarded.…”

CCndnS: A strategy for spreading content and decoupling NDN caches

“…the core contains copies of the content at the edge. One way to reduce this redundancy is for the caches to run some coordination protocol [32], [7]. The coordination may require the measurement of content popularity [16], [33].…”