| 摘要: | 研究期間：10108~10207;The goal of this project will be focused on designing distributed wideband spectrum sensing schemes, for which the recently developed compressive sensing techniques are applied in wideband interweaving cognitive radio (CR) networks. The overall objective is to improve the spectrum sensing capability and transmission opportunity exploitation by dealing with the following two critical challenges. On one hand, the growth of heterogeneous broadband wireless communication not only offers high data rate service for primary users, but also provides opportunistic dynamic spectrum access for CR users. The wideband spectrum sensing, however, imposes impractical burden on analogy-to-digital converter and digital signal processing with Nyquist-rate sampling. On the other hand, the hidden terminal problem, which stems from several wireless fading effects, constitutes a major performance degradation factor for monitoring the vacant spectrum hole. To provide reliable spectrum sensing at affordable complexity, in this project, we will resort to compressive sensing and cooperative sensing for wideband CR networks by utilizing the inherent sparsity and diversity nature in spectral and spatial domains, respectively. The first half of this two-year effort will be concentrated on designing several wideband compressive spectrum sensing techniques, including anti-noise schemes, adaptive schemes for sensing matrices, and robust schemes for quantized sensing matrices, to facilitate the future applications in practical communication environments. The focus of the second-year effort is to investigate one-hop cooperative spectrum sensing techniques for distributed wideband CR networks. Two potential methodologies, joint sparsity models and Bayesian compressive sensing with factor graphs, will be utilized to design the cooperative wideband spectrum sensing schemes. Meanwhile, we will analyze the performance of the distributed cooperative CR networks and the required cooperative radius to achieve sufficiently good performance. The outcomes of this project will be the basic cognitive system models, joint sparsity cognitive models, factor graphs for distributed CR networks, and several wideband spectrum sensing schemes, which are based on compressive sensing, with anti-noise, adaptive and robust capabilities. Furthermore, two essential distributed wideband spectrum sensing schemes, derived from joint sparsity models and Bayesian probabilities, will be provided, along with a theoretical analysis on the performance of the distributed CR networks. Computer simulation and theoretical analysis will be conducted to evaluate the overall system performance. |
