面向Web服务QoS预测的非负矩阵分解模型

Non-negative matrix factorization model for Web service QoS prediction

针对目前QoS预测算法准确度不高的问题,提出通过挖掘已有QoS观测数据中的近邻信息和隐含特征信息而实现服务QoS预测的方法.建立QoS预测的矩阵分解因子模型,将QoS预测问题转化为稀疏QoS矩阵下的模型参数期望最大化(EM)估计问题,提出结合近邻信息的非负矩阵分解算法NCNMF+EM对该问题进行求解.算法综合利用了QoS矩阵中的近邻信息和隐含特征信息,可以实现对不同类型QoS属性值的准确预测.实验结果表明,采用该方法可以显著地提高服务QoS的预测准确度,且算法的运行时间随着矩阵规模的增大呈线性增长,可以应用于大规模的QoS预测问题中.

An effective Web service QoS prediction approach was presented by utilizing the neighbor information and latent feature information of the observed QoS data.A matrix factor model for service QoS prediction was presented.Then an expectation-maximization（EM）estimation scenario was designed to learn the model based on the available QoS data.A neighbor information combined non-negative matrix factorization algorithm NCNMF＋EM was proposed to implement the scenario.The approach fully utilizes the information of the observed data,and can achieve high prediction accuracy.Experimental results demonstrate that the approach achieves better prediction accuracy than other state-of-the-art approaches.The computational time of the algorithm is linear with the scale of QoS matrix,which indicates that the approach is applicable to large scale QoS prediction problem.