π€ AI Summary
Distributed storage systems face dual challenges: data heterogeneity caused by uneven data access and device heterogeneity arising from time-varying node reliability. This work proposes a novel convertible coding scheme that, for the first time, unifies the handling of both types of heterogeneity. Building upon the theory of linear convertible codes and leveraging the structural properties of ReedβMuller codes, the scheme introduces an explicit, low-overhead mechanism for code conversion and derives fundamental lower bounds on read/write conversion costs applicable to any linear code. The proposed approach significantly reduces reconfiguration and maintenance overhead in dynamic environments, offering an efficient and theoretically optimal coding solution for scenarios characterized by simultaneous data and device heterogeneity.
π Abstract
Distributed storage systems must handle both data heterogeneity, arising from non-uniform access demands, and device heterogeneity, caused by time-varying node reliability. In this paper, we study convertible codes, which enable the transformation of one code into another with minimum cost in the merge regime, addressing the latter. We derive general lower bounds on the read and write costs of linear code conversion, applicable to arbitrary linear codes. We then focus on Reed-Muller codes, which efficiently handle data heterogeneity, addressing the former issue, and construct explicit conversion procedures that, for the first time, combine both forms of heterogeneity for distributed data storage.