摘要：Background: With the rapid development of advanced technologies such as cloud computing and big data, there are numerous cloud services with the same functionality and Quality of Service (QoS) on the Internet. Under the open network environment, the QoS of cloud services has strong dynamics and its accuracy becomes a key factor to deciding the success of service selection and service combination. How to accurately predict the QoS of cloud services becomes a key scientific problem to be solved in the service computing. Materials and Method: In order to solve this problem, this study proposes a method to predict the QoS of cloud services based on the case-based reasoning of optimized support vector machine; considering the network environment and load of cloud services, on the basis of the influence of the characteristics of tasks to be handled on the QoS of cloud services. The method firstly predicts the load of cloud service when being called in the future based on the optimized support vector machine, in combination of the predicted information of load and task characteristics and it predicts the QoS value of cloud services based on the case-based reasoning technology when dealing with specific tasks. Results: The experimental results show us that the QoS prediction method proposed in the study has higher prediction accuracy. Conclusion: This method has advantages to improve the quality of network service.
