This paper presents a novel decision making framework for cognitive radio networks. The traditional continuous process of sensing, analysis, reasoning, and adaptation in a cognitive cycle has been divided into two levels. In the first level, the process of sensing and adaptation runs over the radio transmission hardware during run-time. In the second level, the process of analysis and reasoning runs in the background in offline mode. This arrangement offloads the convergence time and complexity problem of reasoning process during run-time. For implementation of the first level, a random neural network (RNN) based controller trained on an open loop case based database on the cloud has been designed. For the second level, a genetic algorithm (GA) based reasoning and an RNN based learning has been developed. The proposed framework is used to address the uplink power control problem of long-term evolution (LTE) system. The performance of RNN is compared with artificial neural network (ANN) and state-of-the-art fractional power control (FPC) scheme in terms of essential cognitive engine (CE) design requirements, capacity, and coverage optimization (CCO). The simulation results have shown that RNN based CE can achieve comparable results with faster adaptation, even subject to severe environment changes without the need of retraining.
- cognitive radio; cognitive engine design requirements; decision making framework; coverage and capacity optimization; Random neural network; Long-term evolution system