RW-MC:基于随机游走的自适应矩阵填充算法

摘要

Concerning the continually perceiving performance of virtual access points (VAP) was urgent in soft-ware-defined wireless network (SDWN), with the features of VAPs' measurement data (VMD), a self-adaptive matrix completion algorithm based on random walk was proposed, named RW-MC. Firstly, the discrete ratio and covering ratio of VMD account for a sample determination model was used to claim initial samples. Secondly, random walk model was implemented for generating sampling data points in the next iteration. Finally, a self-adaptive sampling redress model concerning the differences between the current error rates and normalize error rates of neighboring completion matrices. The experiments show that the approach can collect the real-time sensory data, meanwhile, maintain a relatively low error rate for a small sampling rate.%为了对软件定义无线网络系统中虚拟接入点(VAP)状态信息进行实时测量,根据实际网络中虚拟接入点性能的数据特征,提出一种基于随机游走的自适应矩阵填充算法(RW-MC).首先,基于离散度和覆盖度的采样模型确定初始样本点;然后,利用随机游走模型对之前时隙的采样点序列建模分析,确定新时隙的测量点;最后,比较相邻窗口的恢复矩阵中重叠部分的误差率与标准误差,实现测量点的动态自适应.实验表明,该测量方法能够在低采样率、低误差的情况下实现对全网VAP实时感知.