A two-phase learning approach integrated with multi-source features for cloud service QoS prediction
Saved in:
| Title: | A two-phase learning approach integrated with multi-source features for cloud service QoS prediction |
|---|---|
| Authors: | Chen, Fuzan, Yang, Jing, Feng, Haiyang, Wu, Harris, Li, Minqiang |
| Source: | Frontiers of Engineering Management. 12:117-127 |
| Publisher Information: | Springer Science and Business Media LLC, 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Artificial Intelligence and Robotics, Theory and Algorithms, Similarity measure, Data Science, Matrix factorization, QoS prediction, Cloud service, Deep neural network, Recommendation, Technology and Innovation, Quality |
| Description: | Quality of Service (QoS) is a key factor for users when choosing cloud services. However, QoS values are often unavailable due to insufficient user evaluations or provider data. To address this, we propose a new QoS prediction method, Multi-source Feature Two-phase Learning (MFTL). MFTL incorporates multiple sources of features influencing QoS and uses a two-phase learning framework to make effective use of these features. In the first phase, coarse-grained learning is performed using a neighborhood-integrated matrix factorization model, along with a strategy for selecting high-quality neighbors for target users. In the second phase, reinforcement learning through a deep neural network is used to capture interactions between users and services. We conducted several experiments using the WS-Dream data set to assess MFTL’s performance in predicting response time QoS. The results show that MFTL outperforms many leading QoS prediction methods. |
| Document Type: | Article |
| File Description: | application/pdf |
| Language: | English |
| ISSN: | 2096-0255 2095-7513 |
| DOI: | 10.1007/s42524-025-4038-x |
| Rights: | CC BY |
| Accession Number: | edsair.doi.dedup.....ef0fcee82c23e7e85b8b9c23f5b0a8a7 |
| Database: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Quality of Service (QoS) is a key factor for users when choosing cloud services. However, QoS values are often unavailable due to insufficient user evaluations or provider data. To address this, we propose a new QoS prediction method, Multi-source Feature Two-phase Learning (MFTL). MFTL incorporates multiple sources of features influencing QoS and uses a two-phase learning framework to make effective use of these features. In the first phase, coarse-grained learning is performed using a neighborhood-integrated matrix factorization model, along with a strategy for selecting high-quality neighbors for target users. In the second phase, reinforcement learning through a deep neural network is used to capture interactions between users and services. We conducted several experiments using the WS-Dream data set to assess MFTL’s performance in predicting response time QoS. The results show that MFTL outperforms many leading QoS prediction methods. |
|---|---|
| ISSN: | 20960255 20957513 |
| DOI: | 10.1007/s42524-025-4038-x |