Cloud service QoS prediction method based on multi-source feature learning

Abstract

The invention provides a cloud service QoS prediction method based on multi-source feature learning. The method comprises the following steps of extracting explicit features of users and services by utilizing context data of the users and the services, based on an implicit factor embedding method combining matrix decomposition and a neural network, extracting deep implicit features of users and services from the user-service matrix, splicing the explicit features and the implicit features to obtain a multi-source feature matrix corresponding to the user-service call record, and learning to obtain a local-global feature combination of the multi-source feature matrix by using a joint deep network based on a convolutional neural network, thereby obtaining QoS prediction of the cloud service by the user. According to the method, the high-order feature combination is learned from the multi-source information, and the influence of the feature sequence on the feature combination learning is fully considered, so that the QoS prediction precision is effectively improved.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a cloud service QoS prediction method based on multi-source feature learning. Background technique [0002] As a service-oriented architecture technology, cloud service provides users with services on demand through the Internet provided by cloud computing providers. However, with the increasing popularity of service computing, more and more homogeneous cloud services are born, making it difficult for users to judge the extent to which cloud services with the same functions can meet their personal needs. In this case, Quality of Service (QoS), which describes the non-functional attributes of services, becomes the key to distinguish the difference between homogeneous cloud services. [0003] Quality of Service is a combination of several qualities that describe non-functional attributes of a service, such as response time, throughput, reputation, etc. However, in a...

AI Technical Summary

Problems solved by technology

[0005] However, the increasing diversity and dynamics of the cloud environment pose many new challenges to QoS prediction in service recommendation, one of the key challenges is how to extract and learn the deep features of users / services, while the existing methods express Obvious lack of ability

In addition, collaborative filtering technology mainly predicts missing QoS values ​​by collecting historical information of similar users or services. However, in most cases, such methods only use the information of QoS matrix and ignore many other key factors.

For example, QoS values ​​measured at the client side (response time, throughput, availability, etc.) can vary widely when affected by unpredictable network connections or heterogeneous user environments

Various environmental characteristics such as geographical location and network status will have a great impact on the QoS value, and it is difficult for single-dimensional context information to fully reflect complex environments

Images