Cooperative learning for reduced complexity cross-layer Cognitive Radio

摘要: A Cognitive Radio (CR) network has to adapt operations of all secondary users meet performance goals while avoiding interfering the primary (PN) beyond a set limit. For this, this paper considers distributed cross-layer resource allocation CR algorithm. While approach notably improves in terms average end-to-end distortion and network's congestion rate, it increases number iterations needed find solution. In paper, extra complexity is addressed through novel cooperative learning algorithm where peer nodes cooperate first distributing tasks, followed by sharing complementary learned information. The does not rely on availability expert that have already performed process. Simulation results show technique reduces approximately 45% with small very acceptable sacrifice performance.