# Generalized piggybacking codes for distributed storage systems

## TL;DR

This paper introduces a generalized piggybacking coding scheme for distributed storage that reduces repair bandwidth and computational complexity by optimizing the proportion of protected instances, outperforming existing designs.

## Contribution

It extends piggybacking codes by analyzing protected instances, optimizing their proportion, and demonstrating improved repair efficiency and lower complexity.

## Key findings

- Proportion of protected instances affects repair bandwidth.
- Optimized codes approach zero repair ratio as parity nodes increase.
- Lower computational complexity than existing piggybacking codes.

## Abstract

This paper generalizes the piggybacking constructions for distributed storage systems by considering various protected instances and piggybacked instances. Analysis demonstrates that the proportion of protected instances determines the average repair bandwidth for a systematic node. By optimizing the proportion of protected instances, the repair ratio of generalized piggybacking codes approaches zero instead of 50% as the number of parity check nodes tends to infinity. Furthermore, the computational complexity for repairing a single systematic node cost by generalized piggybacking codes is less than that of the existing piggybacking designs.