Cross-layer design for wireless networks with cognitive controllers

A new approach to wireless network design featuring a cognitive controller stack component is presented. The controller uses system status information from the protocol components to tune the behavior of the network stack to achieve a given performance objective. A controller design strategy using a machine learning algorithm and a simulator is proposed, implemented, and tested. Results with ad-hoc wireless networks show the architecture and design strategy are capable of producing a network stack that outperforms the existing protocol stack for given performance objectives. The techniques presented give network designers the flexibility to easily tune the performance of their networks to suit their application.