Stream reasoning-based control of caching strategies in CCN routers

Abstract

Abstract. Content-Centric Networking (CCN) research addresses the mismatch between the modern usage of the Internet and its outdated architecture. Importantly, CCN routers may locally cache frequently requested content in order to speed up delivery to end users. Thus, the issue of caching strategies arises, i.e., which content shall be stored and when it should be replaced. In this work, we employ novel techniques towards intelligent administration of CCN routers that autonomously switch between existing strategies in response to changing content request patterns. In particular, we present a router architecture for CCN networks that is controlled by rule-based stream reasoning, following the recent formal framework LARS which extends Answer Set Programming for streams. The obtained possibility for flexible router configuration at runtime allows for faster experimentation and may thus help to advance the further development of CCN. Moreover, the empirical evaluation of our feasibility study shows that the resulting caching agent may give significant performance gains.

Ticker: A system for incremental ASP-based stream reasoning

“…For an experimental evaluation, we consider two scenarios in the context of content-centric network management, where smart routers need to manage packages dynamically (Beck et al 2017).…”

“…lfu ← n high r 9 : done ← fifo r 5 : lru ← n mid r 10 : random ← not done conn Setup A1 replaces tuple windows in rules r 1 -r 3 by time windows [as in Beck et al (2017)]; setup A2 uses the program as shown. The input signals alpha(V ) are generated such that a random mode high, medium or low is repeatedly chosen and kept for twice the window size.…”

I-DLV-sr: A Stream Reasoning System based on I-DLV

“…For the former analysis, we considered two benchmarks: Content Caching and Heavy Join. Content Caching (Beck et al . 2017;Eiter et al .…”

“…2019) is a real-world benchmark that requires to manage the caching policy of a video content over an incoming stream that describes the evolving popularity level of the content. Besides the original problem (Beck et al . 2017), we considered a slightly different version that deals with more than one event per time point (we refer to a true atom at a time point in the stream as an "event").…”