Abstract
As cloud computing becomes more prevalent in various domains, such as e-commerce, healthcare, education, etc., there is a growing demand for cloud-based applications that can perform complex tasks by integrating multiple cloud services. Despite QoS-aware automatic service composition has been extensively studied, conventional approaches face limitations in evaluating intelligent services and ensuring correctness and reliability for AI systems. To address these challenges, we propose five metrics for differentiating between intelligent and non-intelligent services and evaluating service composition solutions based on user-defined metrics constraints. We also explore ways to improve system correctness and reliability, and adapt these approaches to fit with AI systems. Building on these insights, we propose ASC4AI, a novel automatic service composition framework designed specifically for AI systems, which can automatically generate service composition solutions that meet user-defined functional and metrics constraints. Furthermore, we implement ASC4AI as a user-friendly tool that minimizes technical complexity for developers.
| Original language | English |
|---|---|
| Pages (from-to) | 197-202 |
| Number of pages | 6 |
| Journal | Proceedings of the International Conference on Software Engineering and Knowledge Engineering, SEKE |
| Volume | 2023-July |
| DOIs | |
| State | Published - 2023 |
| Event | 35th International Conference on Software Engineering and Knowledge Engineering, SEKE 2023 - Hybrid, San Francisco, United States Duration: 1 Jul 2023 → 10 Jul 2023 |
Keywords
- Artificial intelligent systems
- Automatic service composition
- Service composition patterns
- Service metrics