基于拍卖理论和高斯过程回归学习的频谱分配算法  

A spectrum allocation algorithm based on auction theory and Gaussian process regression

作　　者：刘觉夫[1] 杨将[1] 王建旭[1] 胡静[1] 

机构地区：[1]华东交通大学信息工程学院,江西南昌330013

出　　处：《计算机工程与科学》2016年第5期914-920,共7页Computer Engineering & Science

基　　金：国家自然科学基金(61163055);江西省研究生创新专项资金(YC2014-X004)

摘　　要：针对认知无线网络中认知用户的频谱分配问题,提出了一种基于拍卖理论和高斯过程回归学习的频谱分配算法。该算法基于VCG拍卖模型,考虑认知用户对通信质量的要求,构造出更有效的收益函数。在频谱拍卖过程中,认知用户通过学习拍卖历史数据预测其他认知用户的竞价,并最优化其竞价策略。频谱拍卖人根据各认知用户提交的竞价来分配频谱资源。理论分析和仿真结果证明了该算法是有效的,并且能够提高频谱利用率和认知用户的收益。We propose a spectrum allocation algorithm based on the auction theory and Gaussian process regression in cognitive wireless networks. Based on vickrey-clarke-groves（VCG ） auction mod- el, the algorithm takes the requirement for communication quality of cognitive users into consideration, and formulates a more effective utility function. During the auction, cognitive users predict the bids of other cognitive users by utilizing historical auction data to optimize their bidding strategy. The auction- eer assigns spectrum according to all the bids of cognitive users. Theoretical analysis and simulation re- sults prove the effectiveness of the proposed algorithm, and verify that it can enhance spectrum utiliza- tion and the earnings of cognitive users.

关 键 词：拍卖模型 频谱分配 高斯过程回归 VCG机制 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]