Predicting Quality of Cloud Services for Selection

Predicting quality of services (QoS) is an important need when ranking cloud services for selection. QoS values of cloud services usually depend heavily on the user’s and service’s environments. Therefore, personalized QoS value prediction for cloud services is more desirable to users. Collaborative Filtering (CF) has recently been applied to personalized QoS prediction for services on the Web. However, seldom did they take the context information of service users and services into consideration. The following paper presents a CF-based method for predicting QoS values of cloud services. The method exploits not only the QoS information of users and services, but also one type of the most important context information of users and services, i.e., their geographic locations. Experiments conducted on a real dataset show that geographic location information is indeed helpful for improving the QoS prediction performance. The experimental results also demonstrate that the proposed method is significantly better than previous methods in prediction accuracy.