Web services QoS prediction via matrix completion with structural noise
With the rapid development of service-oriented computing, more and more Web services with the same or similar function are deployed on the Internet. Usually, before selecting the most suitable service, users need to predict QoS of unused services from the service invoking history. Due to the lack of...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2015-06-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2015118/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With the rapid development of service-oriented computing, more and more Web services with the same or similar function are deployed on the Internet. Usually, before selecting the most suitable service, users need to predict QoS of unused services from the service invoking history. Due to the lack of effective supervision and constraint mechanisms, some number of the rows in the QoS sample matrix is often contaminated by the structural noise, which leads to a sharp decrease for QoS prediction performance. In order to address this problem, an efficient Web services QoS prediction approach via matrix completion with structural noise is proposed by formulating Web services QoS prediction problem as a L2,1-norm regularized matrix completion problem. The proposed approach can not only exactly detect the position where the data is contaminated, but also effectively predict the missing QoS values. Finally, experimental results performed on a real public dataset demonstrate the feasibility of our proposed approach. |
|---|---|
| ISSN: | 1000-436X |