Breadcrumbs: Efficient, Best-Effort Content Location in Cache Networks

Abstract

Abstract-For several years, web caching has been used to meet the ever increasing Web access loads. A fundamental capability of all such systems is that of inter-cache coordination, which can be divided into two main types: explicit and implicit coordination. While the former allows for greater control over resource allocation, the latter does not suffer from the additional communication overhead needed for coordination.In this paper, we consider a network in which each router has a local cache that caches files passing through it. By additionally storing minimal information regarding caching history, we develop a simple content caching, location, and routing systems that adopts an implicit, transparent, and best-effort approach towards caching. Though only best effort, the policy outperforms classic policies that allow explicit coordination between caches.

Implementation and Evaluation of a Controller-Based Forwarding Scheme for NDN

“…Finally, Rosensweig et al [18] add new tables in nodes enabling to monitor incoming traffic and forward Interest according to these statistics. But tracking all the incoming traffic in each node without coordination between them can produce a huge amount of redundancy, and seriously impact the network's performances with all the memory access needed.…”

A cooperation-driven ICN-based caching scheme for mobile content chunk delivery at RAN

“…Note P rob caching (j) ≡ 1 for each in-coming chunk under a universal caching policy that caches everything everywhere [3], [13]. With Eq.…”

WAVE: Popularity-based and collaborative in-network caching for content-oriented networks

“…WAVE uses the least recently used (LRU) approach, the most representative cache replacement algorithm used in cache networks [7], [16]. Note that WAVE can use other cache replacement algorithms such as least frequently used (LFU) or least recently/frequently used (LRFU).…”

“…There are many issues to be solved such as architectural designs [2], [3], [4], [5], content name-based routing [6], [7], security [2], [3], [8], and legacy application support [9], [10]. We focus on in-network caching.…”

“…As the access count increases, WAVE exponentially increases the number of chunks to be cached and disseminates them more widely. We assume that content routers (or C-routers, for short) will cache the chunks of files by exploiting in-network storages [2], [3], [4], [5], [6], [7]. If only a subset of the routers have the storage modules, they can form an overlay caching network among themselves 1 .…”