On a unifying product form framework for redundancy models

Abstract

Using redundancy to minimize latency in parallel server systems has become very popular in recent years. While there are several variants of a redundancy-based system, the general notion of redundancy is to create multiple copies of the same job that will be sent to a subset of servers. By allowing for redundant copies, the aim is to minimize the system latency by exploiting the variability in the queue lengths of the different queues. Several recent works have both empirically and theoretically showed that redundancy can help in reducing the response time of a system.