Primary Rate-Splitting Achieves Capacity for the Gaussian Cognitive Interference Channel

Abstract

The cognitive interference channel models cognitive overlay radio systems, where cognitive radios overhear the transmission of neighboring nodes. Capacity for this channel is not known in general. For the Gaussian case capacity is known in three regimes, usually denoted as the "weak interference", "very strong interference" and "primary decodes cognitive". This paper provides a new capacity result, based on rate-splitting of the primary user's message into a public and private part and that generalizes the capacity results in the "very strong interference" and "primary decodes cognitive" regimes. This result indicates that capacity of the cognitive interference channel not only depends on channel conditions but also the level of cooperation with the primary user.