Rapid Web server QoS (Quality of Service) prediction method based on user metadata

Abstract

The invention discloses a rapid Web server QoS (Quality of Service) prediction method based on user metadata. According to the method, the field of a request user is accurately selected through use of the metadata (geographic position information and history QoS record) of a user, and meanwhile the accuracy of prediction is effectively increased through a matrix decomposition algorithm for fusing user extension intrinsic attributes. The solving efficiency is increased greatly through a matrix decomposition acceleration technology, so that real-time response to the individual QoS inquiry requests of a plurality of users is realized.

Description

technical field [0001] The invention belongs to the technical field of Web services, and in particular relates to a fast Web service QoS prediction method based on user metadata. Background technique [0002] Driven by the wave of Internet services in the Web 2.0 era, the main form, operation mode, production mode and use mode of traditional software systems are undergoing tremendous changes. The widespread deployment and application of Web services has brought continuous impetus to industry and academia, and promoted the continuous development of disciplines in the field of services. Under the impetus of the industry, the QoS (Quality of Service) attribute, which is the basis of service science, has also attracted the attention of many service subject researchers. In recent years, QoS-based paradigms have also been widely used in service selection, service discovery, service composition, service recommendation, and service monitoring, greatly promoting the development of s...

AI Technical Summary

Problems solved by technology

However, this calculation method has the following two disadvantages: (1) The PCC method needs to do statistical learning on the QoS in the historical records, which heavily depends on the accuracy and completeness of the data

In the QoS historical records, each item is determined by the actual network environment used by the user. The objectivity of this data directly reduces the accuracy of the PCC similarity calculation.

[0005] At the same time, the current mainstream QoS prediction work still has the problem of too long system solution time

In fact, too long running time will cause problems for all parties: for researchers, it is not desirable for researchers to obtain QoS data resources through long learning time

However, current accurate QoS prediction methods require a lot of time to learn data attributes, and also lack practical analysis of the complexity of core algorithms

Images