ARQ Diversity in Fading Random Access Channels

Abstract

A cross-layer optimization approach is adopted for the design of symmetric random access wireless systems. Instead of the traditional collision model, a more realistic physical layer model is considered. Based on this model, an Incremental Redundancy Automatic Repeat reQuest (IR-ARQ) scheme, tailored to jointly combat the effects of collisions, multi-path fading, and additive noise, is developed. The Diversity-Multiplexing-Delay tradeoff (DMDT) of the proposed scheme is analyzed for fully-loaded queues, and compared with that of Gallager tree algorithm for collision resolution and the network-assisted diversity multiple access (NDMA) protocol of Tsatsanis et al.. The fully-loaded queue model is then replaced by one with random arrivals, under which these protocols are compared in terms of the stability region, average delay and diversity gain. Overall, our analytical and numerical results establish the superiority of the proposed IR-ARQ scheme and reveal some important insights. For example, it turns out that the performance is optimized, for a given total throughput, by maximizing the probability that a certain user sends a new packet and minimizing the transmission rate employed by each user.