Market-Based Resource Management for Cognitive Radios Using Machine Learning

With the growth in wireless network technologies and the emergence of cognitive radios, the need arises for mechanisms to effectively manage the resources involved in such environments. In this paper, we propose a market-based resource management approach for cognitive radios using machine learning, consisting of a negotiation phase where nodes are allocated resources in order to meet their requested bit rate, and a learning phase where nodes adjust their pricing of the resources in order to steer the cognitive radio environment towards the greater network good. We are interested in improving the utilization of the resources through price adjustments as compared to the case where the prices are kept fixed. We perform extensive simulations to study the performance of the proposed resource management mechanism in the cognitive radio environment.