Abstract
As the popularity of cloud platforms and container grows rapidly, managing clouds has become an important issue. For example, failed containers on cloud platforms would trigger automatic restart mechanism. However, the failed containers caused by user error are not fixable by restart, and may lead to the loop between failure and restart. Therefore, the looping failure will harm the overall performance of cloud. In this paper, we propose to identify possible container failures, where the utility behavior of containers (e.g., CPU usage, GPU usage, I/O throughput, etc) are factored in, in a machine learning approach. We propose a light-weight neural network EEGNet-SE to support fast inference in real-time. In addition, EEGNet-SE is able to distinguish dynamic relations between each utility for different tasks. We conduct a real cloud container dataset from Taiwan Cloud Computing (TWCC) platform. Experimental results manifest that EEGNet-SE boosts the performance and efficiency simultaneously, and outperforms the other state-of-the-art methods in terms of accuracy.
| Original language | English |
|---|---|
| Title of host publication | 2021 22nd Asia-Pacific Network Operations and Management Symposium, APNOMS 2021 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 358-361 |
| Number of pages | 4 |
| ISBN (Electronic) | 9784885523328 |
| DOIs | |
| State | Published - 08 09 2021 |
| Externally published | Yes |
| Event | 22nd Asia-Pacific Network Operations and Management Symposium, APNOMS 2021 - Virtual, Online, Taiwan Duration: 08 09 2021 → 10 09 2021 |
Publication series
| Name | 2021 22nd Asia-Pacific Network Operations and Management Symposium, APNOMS 2021 |
|---|
Conference
| Conference | 22nd Asia-Pacific Network Operations and Management Symposium, APNOMS 2021 |
|---|---|
| Country/Territory | Taiwan |
| City | Virtual, Online |
| Period | 08/09/21 → 10/09/21 |
Bibliographical note
Publisher Copyright:© 2021 IEICE.
Keywords
- Cloud Container Failure Detection
- Multivariate Time-series Classification
- Neural Network
Fingerprint
Dive into the research topics of 'On Detecting Cloud Container Failures from Computing Utility Sequences'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver