Journal
SERVICE-ORIENTED COMPUTING, ICSOC 2017
Volume 10601, Issue -, Pages 287-294Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-69035-3_20
Keywords
Service composition; Substitution; Quality of Service (QoS); Deep learning; LSTMs
Ask authors/readers for more resources
In this paper, we propose a deep learning approach for long-term Quality of Service (QoS)-based service composition. Existing techniques for quality-aware service composition mostly focus on static QoS values observed during composition time. They do not consider potential QoS fluctuations in the long run when selecting services for composition or substitution. Our approach uses deep recurrent Long Short Term Memories (LSTMs) to forecast future QoS. The predicted QoS values are used to accurately recommend components and substitutes in long-term service compositions. Experiments show promising results compared to existing QoS prediction techniques.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available