Finite-Length Analysis for Wireless Super-Dense Networks Exploiting Coded Random Access Over Rayleigh Fading Channels

This paper presents finite-length performance analysis for wireless super-dense networks comprising two multiway relays (SDN-2MWR) to support full data-exchange among massive number of users/devices over Rayleigh fading channels. In practice, finite-length analysis is important since the networks should serve users/devices with low latency indicated by short number of time-slots. Due to the nature of massive number of users/devices, where scheduling over massive number of users (usually in hundred or thousand) is difficult, we exploit random access with a capability of error correction resembling low density parity check (LDPC) codes. In this paper, we show that the dynamic of Rayleigh fading is even beneficial to generate two independent graphs captured by the first and the second relay without requiring all users send messages independently to each relay. Independent graphs are essential in SDN-2MWR to ensure the probability of successful decoding as high as possible and to significantly reduce error-floor in finite-length setting. Based on the theoretical network capacity bound indicating the maximum achievable traffic supported by the networks, we found that for SDN-2MWR a significant gain closer to the bound with lower packet-loss-rate (compared to the dense network with a single relay) is achievable without assuming ideal independent graph even with simple degree distributions without irregularity.