Hierarchical cooperative caching in mobile opportunistic social networks

Abstract

Abstract-A mobile opportunistic social network (MOSN) is a new type of delay tolerant network (DTN), in which the mobile users contact each other opportunistically. While cooperative caching in the Internet has been studied extensively, cooperative caching in MOSNs is a considerably different and challenging problem due to the probabilistic nature of contact among the mobile users in MOSNs. In order to reduce the total access delay, we let the mobile users cooperatively cache these data items in their limited buffer space. We balance between selfishness (caching the data items according to its own preference) and unselfishness (helping other nodes to cache). The friends with higher contact frequency may share similar interests, hence, caching the data items for friend users can lead to some benefit. In this paper, we present a hierarchical cooperative caching scheme, which divides the buffer space into three components: self, friends, and strangers. In the self component, mobile users cache the data items according to their preference. In the friends component, mobile users help their friends to cache some data items. In the strangers component, mobile users randomly cache the remaining data items. We formally analyze the access delay of the proposed scheme. The effectiveness of our approach is verified through extensive real world trace-driven simulations.Index Terms-Access delay, cooperative caching, mobile opportunistic social networks (MOSNs), Zipf-like distribution.

Information-centric mobile caching network frameworks and caching optimization: a survey

“…A cooperative caching framework for mobile nodes is proposed in [43], in which the buffer storage of each mobile node is divided into three parts: namely self, friends and strangers. Each cache node stores its most frequently accessed data items in the self part.…”

“…In [43], a hierarchical cooperative caching scheme is presented in a mobile opportunistic social network. The cache of the mobile users is divided into three hierarchical components: self, friends, and strangers.…”

“…Minimizing caching failure probability or maximizing caching hit rate are formulated in [33,34,53,62,104]. From the perspective of simulation, tracebased simulation is used to evaluate user experience delay in [30,43,107], and discrete event-driven simulators are adopted to evaluate caching hit rate in [45,46,58].…”

“…Discrete event-driven simulator is used in [45,46,54,58], and trace-based simulation is performed in [30,43,106,107].…”

“…The state-of-the-art cache insertion policies mainly consists of Caching Everything Everywhere (CEE) [56](refer to "ALL-CACHE" in [46],"leave copy everywhere (LCE)"in [57]), Leave Copy Down (LCD) [46,56,57], Caching with Probability (Prob(p)) [46,56,57], ProbCache [18], WAVE [58], Breadcrumbs [47], Ditto Ad hoc based network Edge based caching( in every node and in the server) [42-48, 59, 89, 92] Hybrid network Edge based caching (in APs, BSs and mobile devices) [3, 5, 7, 49, 51-55, 85, 86, 122] [59], Partial Cache [60], Interest-based cooperative caching (ICC) [46], Proactive Content Pushing Scheme (PCP) [61], Hierarchical Cooperative Caching(HCC) [43] and Mobility/Popularity-Based Caching Strategy(MPCS) [62],etc. The principles of the cache insertion policies are summarized below.…”