Reliability Gain of Network Coding in Lossy Wireless Networks

Abstract

The capacity gain of network coding has been extensively studied in wired and wireless networks. Recently, it has been shown that network coding improves network reliability by reducing the number of packet retransmissions in lossy networks. However, the extent of the reliability benefit of network coding is not known. This paper quantifies the reliability gain of network coding for reliable multicasting in wireless networks, where network coding is most promising. We define the expected number of transmissions per packet as the performance metric for reliability and derive analytical expressions characterizing the performance of network coding. We also analyze the performance of reliability mechanisms based on rateless codes and automatic repeat request (ARQ), and compare them with network coding. We first study network coding performance in an access point model, where an access point broadcasts packets to a group of K receivers over lossy wireless channels. We show that the expected number of transmissions using ARQ, compared to network coding, scales as (logK) as the number of receivers becomes large. We then use the access point model as a building block to study reliable multicast in tree and extended access point models. In addition to scaling results, we derive expressions for the expected number of transmissions for finite multicast groups, and use them to study the impact of multicast group size and coding block size on the performance of different reliability schemes. Our results show that network coding significantly reduces the number of retransmissions in lossy networks compared to an end-to-end ARQ scheme. However, rateless coding and link-by-link ARQ achieve performance results comparable to that of network coding.