Web service QoS monitoring method in mobile edge environment

Abstract

The invention discloses a Web service QoS monitoring method in a mobile edge environment. According to the method, user and service information and QoS attribute data of Web services are collected andsubjected to data preprocessing to obtain a data set conforming to edge environment characteristics, and QoS monitoring under the edge environment is achieved through a Gaussian hidden Bayesian probability monitoring method. When data preprocessing is carried out, after samples with missing data are removed, clustering division is carried out according to geographic positions of services, and position information and QoS data sample flow of an edge server are obtained. A part of samples are learned, the prior probability is calculated for each edge server, meanwhile, the value of a parent attribute is calculated to weaken the dependency of values between attributes, a Gaussian hidden Bayesian classifier is constructed, and therefore the accuracy of a monitoring result is improved. In themonitoring process, the mobility of the user is considered, the corresponding classifier is called, the KNN algorithm is combined, and finally the monitoring result is obtained.

Description

Technical field [0001] The invention relates to a web service QoS monitoring method, in particular to a web service QoS monitoring method in a mobile edge environment, and belongs to the field of Internet technology. Background technique [0002] With the promotion of traditional Web services by new technologies such as cloud computing and big data, the demand for services between enterprises and even individuals is gradually turning into interaction between services. Quality of Service (QoS) is a collection of a set of non-functional attributes of Web services. It is an important indicator to measure the quality of third-party services. Each QoS attribute represents quality information of a certain aspect of Web services, such as response time, throughput, and reliability. Sex and so on. In a complex and ever-changing environment, the operating environment and operating quality of Web services are also changing all the time. In order for the service to adapt to the real-time ch...

AI Technical Summary

Problems solved by technology

However, in the face of short-term and fast-changing data in the mobile edge environment, the existing methods may cause deviations in monitoring results due to user mobility, and the dependency between attribute values ​​​​is ignored in the monitoring process.

Images