$\text{M}^{3}$ -STEP: Matching-Based Multi-Radio Multi-Channel Spectrum Trading With Evolving Preferences

Spectrum trading not only improves spectrum utilization but also benefits both secondary users (SUs) with more accessing opportunities and primary users (PUs) with monetary gains. Although the existing centralized designs consider the special features of spectrum trading (e.g., frequency reuse, interference mitigation, multi-radio multi-channel transmissions, and so on), they still have to face many practical but challenging issues, such as the new infrastructure deployment, the extra control overhead, and the scalability issues. To address those issues, in this paper, we propose a novel matching-based multi-radio multi-channel spectrum trading (M
³
-STEP) scheme in cognitive radio (CR) networks. We employ conflict graph to characterize the interference relationship among SUs with multiple CR radios, and formulate the centralized PUs' revenue maximization problem under multiple constrains. In view of the NP-hardness of solving the problem and no existence of centralized entity, we develop the M
³
-STEP algorithms based on conflict graph observed by PUs, solve the problem via dynamic matching with evolving preferences, and prove its pairwise stability. Simulation results show that the proposed M
³
-STEP algorithm achieves close to optimal performance and outperforms other distributed algorithms without considering spectrum reuse.