Rapprochement between instantly decodable and random linear network coding

In this paper, a new network coding model is proposed to unify instantly decodable network coding (IDNC) and random linear network coding (RLNC), which have been considered to be incompatible in the literature. This model is based on a novel definition of generation, which is built upon optimal IDNC solutions. Under this model, IDNC and RLNC are only two extreme cases with specific generation sizes. Throughput and delay properties of this model, measured by block completion time and packet decoding delay, respectively, are studied, which fill the gap between IDNC and RLNC and thus provide a good understanding on the throughput-delay tradeoff of network coding. An efficient adaptive scheme is then designed, which allows in-block switch among IDNC and different levels of RLNC, so that the system's throughput and delay can be fine-tuned to meet the real-time requirements of the application. Extensive simulations are performed to demonstrate how the proposed generation size interacts with the number of receivers and the channel quality to affect the overall system performance.