时空感知下基于结构相似度的Web服务质量预测

随着云计算等新型服务计算的兴起,Web服务数量日益增长,相同或相似功能的Web服务也逐渐增多.为了向用户推荐更高质量的服务,精确地预测Web服务的QoS值成为亟待解决的重要问题.传统的协同过滤方法已经被广泛应用于QoS预测和Web服务推荐中,但因为数据稀疏和噪声问题导致QoS预测性能不好.为提高QoS预测的性能,文中通过分析用户服务QoS矩阵的时空特征,提出了一种基于全局和局部结构相似度的稀疏矩阵分解模型.该方法将QoS矩阵的相邻时间相似用户的网络环境相似性这一特征融入到矩阵分解中,并利用分解的因子对QoS矩阵进行低秩填充.这种方式在一定程度上消除了数据稀疏和噪声的影响.在真实Web服务调用数据集上进行实验,结果表明,该方法在预测精度上优于典型的协同过滤算法(相比于NMF,其MAE值最大下降了3.25％,RMSE值最大下降了6.65％;相比于SVD,其MAE值最大下降了3.67％,RMSE值最大下降了7.01％),能够有效地解决数据稀疏和噪声的问题.

A structure similarity based quality prediction approach for Web service in the spatial-temporal scenario

With the rapid development of new service computing types like cloud computing, the amount of Web services becomes increasingly massive, as is also the case for Web services with the same or similar functions. One of the most important issues in high-quality Web services recommendation is to identify the QoS value of Web services. Traditional collaborative filtering approaches have been widely employed in QoS prediction and Web Service recommendation. However, they suffer from the sparse and noisy data issues, which definitely cause the low performance of QoS predictions. In order to attain high prediction performance, the paper proposed a novel sparse matrix factorization approach based on the spatial-temporal features of user-service QoS matrix,in which the proposed model took the occurence of similar network environment between similar users in neighbor moment into consideration, and constructed a global and local structure similarity based sparse matrix factorization machine. With the decomposed factors, we could get a low rank matrix completion, which helped to eliminate the impacts of sparse and noisy data in QoS prediction. To evaluate the performance of the proposed approach, a set of extensive experiments were conducted using real-world dataset. The experimental results show that the proposed model outperforms the traditional collaborative filtering approaches (the MAE value decreases by 3.25% and RMSE value by 6.65% compared with those of NMF; MAE value decreases by 3.67%, and RMSE by 7.01% compared with those of SVD), which indicates that it can effectively resolve sparse and noisy data issues.