On the Fault Tolerant Distributed Data Caching using LDPC Codes in Cellular Networks
share
The proliferation of mobile data has worked its way to become commonplace, the base station-mobile 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 of downloading a symbol from base station and from other network nodes is not dramatically high, we demonstrate that LDPC codes can be considered as a viable fault-tolerance alternative in cellular systems with caching capabilities for both low and high code rates.
READ FULL TEXT