On Efficient and Social-Aware Object Allocation in Named Data Networks Using Matching Theory
Mahsa Ehsanpour, Siavash Bayat, Ali Mohammad Afshin Hemmatyar · 2018
Existence of cache space in each node of the network is one of the fundamental characteristics of Named Data Networks (NDN) which makes it a promising architecture for data dissemination over the Internet. Most of the existing caching strategies consider on-path caching, which aims to replicate popular objects redundantly inside the network. Furthermore, while most of the existing works focus on the bandwidth utilization and latency improvement, we introduce a novel criteria to elevate the efficiency of cache utilization in order to make the most use of the cache space within the network. In this paper, we propose a distributed algorithm based on matching theory that associates the content objects with the cache-enabled nodes such that the total social welfare of the network is maximized. Further, we prove that the resulting matching is stable. Through extensive simulation results, convergence of our proposed scheme to the centralized solution is demonstrated and its outperformance against the default applied caching scheme in NDN is verified in terms of both social welfare and hit ratio.