Bayesian combination-based Web service QoS prediction method

Abstract

The present invention discloses a Bayesian combination-based Web service QoS prediction method, and proposes that a Bayesian combination prediction model predicts QoS. The method comprises: identifying a time-series feature; according to an identification result, selecting an appropriate basic prediction model; training the selected model; and performing prediction by using a loop structure of prediction-weight adjustment-prediction. In a prediction process, by adjusting again and again weights in a basic prediction model, a result approaches a model with optimal prediction effects, relatively good prediction precision is maintained. In order to verify a prediction result, QoS attributes such as a response time, a throughput and reliability are predicted; experimental results are compared by using two manners: precision analysis and effectiveness estimation; the experiment shows that, with time sequence samples being different in feature, the Bayesian combination prediction model can maintain high prediction precision, is close to an optimal prediction model, and exhibits better and more stable prediction performance.

Description

Technical field [0001] The invention relates to a Web service QoS prediction method based on Bayesian combination. Several combination models are used to predict time series, the results are evaluated through model evaluation standards, and the model weights are adjusted in time to optimize test results. Background technique [0002] Service-oriented systems are increasingly accessing third-party Web services through the Internet. Quality assurance and software maintenance are controlled by third parties, and software execution and management also depend on third parties. The execution capability and service quality of service-oriented systems are increasingly dependent on the services provided by third parties. However, in the complex and changeable Internet environment, this reliance on third-party services will bring uncertain problems and make the services unsatisfactory. QoS (Quality of Service, quality of service) requirements. Therefore, it is necessary to predict the qua...

AI Technical Summary

Problems solved by technology

A single model usually has good forecasting accuracy in a certain period of time, but various forecasting methods have special information characteristics and applicable occasions. At present, there is no algorithm that can maintain absolutely excellent forecasting performance under different conditions and at different times.

Images