Collaborative Cognitive Content Dissemination and Query in Heterogeneous Mobile Opportunistic Networks

Abstract

This paper investigates complex challenges of opportunistic discovery of content stored in remote mobile devices and delivery to the requesting nodes in heterogeneous mobile disconnection prone environments. We propose new latency aware collaborative cognitive caching approach suitable for content dissemination and query in heterogeneous opportunistic mobile networks and dynamic workloads. Utilising fully localised and ego networks multi-layer predictive heuristics about dynamically changing topology, dynamic resources and varying popularity content, our cognitive caching achieves high success ratio, low delays and high caching efficiency for very different real world dynamically changing mobile topologies.

Understanding Complementary Multi-layer Collaborative Heuristics for Adaptive Caching in Heterogeneous Mobile Opportunistic Networks

“…In the third set of experiments, we evaluate the performance of five forwarding protocols with resource awareness and our cognitive collaborative caching algorithms built on the content layer [1] in order to analyse the effect of our adaptive content-aware caching protocol on content dissemination and query performance in mobile disconnection prone environments in the presence of dynamic content request patterns, dynamic mobility and connectivity.…”

“…Authors in [13] studied the effect of content popularity ranking in cooperative caching schemes on delay tolerant mobile network and designed a mathematical model of mobile content sharing network based on file popularity distribution, user mobility and delay tolerance. Our previous work [1] described CafRepCache as our early proof of concept about new latency aware collaborative cognitive caching approach in heterogeneous opportunistic mobile networks which utilises fully localised and ego networks multi-layer predictive heuristics about dynamically changing topology, resources and popularity content. In this paper, we discuss and investigate the impact of each CafRepCache's complementary multilayer heuristics on the performance of end to end content retrieval in mobile heterogeneous opportunistic environments.…”

“…Our adaptive collaborative caching framework CafRepCache has a distributed cross-layer structure [1] and multi-dimensional design space as shown in Fig. 1.…”

“…We first describe in detail our multi-layer complementary analytics, heuristics and utilities in the below section, then evaluate the influences of each heuristic and utility on the performance of content dissemination and query. [1,10]: similarity, betweenness and tie strength that is used to direct the traffic to higher centrality nodes for caching contents or forwarding requests in order to increase the chance that requested contents are delivered successfully to subscribers (i.e. the success ratio).…”

“…Current mobile edge/fog computing leverage in-network caching to address complex challenges of improving the reliability of content dissemination and query while reducing the delay and traffic load on the network. In our previous work, we proposed CafRepCache [1], a multi-layer framework that combines real time adaptive multi-path content and interest forwarding, with adaptive cognitive collaborative caching in heterogeneous mobile disconnection-prone environments. CafRepCache addresses complex open questions on end-to-end content retrieval which includes content discovery, content caching and content delivery process, thus aims to maximise cache hit ratio, success ratio while minimizing latency and packet loss.…”