On the Fault Tolerant Distributed Data Caching using LDPC Codes in Cellular Networks

Abstract

The proliferation of mobile data has worked its way to become commonplace, the base stationmobile data communication has reached unprecedented levels, which in turn heavily overloaded the underlying infrastructure. To reduce the burden on the base stations, intra-cell communication between the local devices, known as Device-to-Device communication, is utilized for distributed data caching.Nevertheless, due to the continuous departure of existing nodes and the arrival of newcomers, the absence of the cached data may lead to permanent data loss within the same cell. In this study, we propose and analyze the use of a class of LDPC codes as a viable fault tolerance alternative for distributed data caching in cellular networks. To that end, a novel repair algorithm for LDPC codes is proposed in a distributed caching context. This novel algorithm is designed to exploit the minimal direct base station communication which does not exist in the traditional distributed storage literature. To assess the versatility of LDPC codes in a distributed data caching scenario as well as to compare the performance of the proposed algorithm with respect to the other well-known methods such as classic Reed-Solomon, Minimum Bandwidth Regenerating codes and Minimum Storage Regenerating codes, novel theoretical and experimental evaluations are derived and presented. Essentially, the theoretical/numerical results for bandwidth consumption using the base station as well as neighboring devices for repairing a lost node are presented. According to the simulation and theoretical results, when the difference between the cost

LDPC Kodlarında Artık Veri Kullanımı Residual Data Usage in LDPC Codes

“…In this distribution method, it is aimed to save storage space instead of saving time in repair operations. Equation (5) shows the relationship between j. storage node and i. symbol that is non-residual, while equation (6) shows the relationship between j. storage node and i. symbol that is residual.…”

“…Erasure correcting codes are generally used in coded caching paradigm and these codes have the potential to reduce the amount of storage space required relative to that of the uncoded caching [2]- [4]. One of the options to fulfill the requirements of the coded caching is presented as low density parity check (LPDC) codes in [5]. Several studies considered LDPC codes for distributed systems as well [6]- [10].…”