A Cognitive Cross-Layer Architecture for Next-Generation Tactical Networks

In this paper, a unified cognitive cross-layer architecture is proposed for the next-generation IP-based mobile tactical networks, where each node in the network can sense and learn from its situational and contextual information, and then it will respond the changes of environment by adapting system parameters and network services based on the learned results. In this way, it can provide Quality of Services (QoS) to multimedia services while fully utilizing network resources. The core of the proposed architecture is a unified cross-layer controller which provides both vertical system control and the horizontal network control. The vertical system adaptation is guided by the horizontal network control based on network data mining techniques, leading to a multi-scale cross-layer architecture for distributive and autonomous QoS provisioning in mobile tactical networks. Therefore, the proposed architecture can support the design requirements of next-generation mobile tactical networks, such as autonomy, self-configuration, self-organization, scalability, adaptability, and simplicity, to provide multimedia services such as video clips, images, voice, and text messages. The implementation of the proposed cross-layer architecture is also briefly discussed in this paper. A related paper discusses some modeling and simulation results that validate the gains that can be made by using a cross-layer approach in implementing next generation mobile tactical networks.