MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0
IEEE Journal of Selected Areas in Sensors · 2024 · 1 · 36-48
DOI: 10.1109/jsas.2024.3396440 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal of Selected Areas in Sensors, 2024. Verfasst von Muhammed Golec und 8 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Tianjin Science and Technology Planning, Ministry of Education of the Turkish Republic.
Abstract (Originalsprache)
The integration of serverless edge computing and the Industrial Internet of Things (IIoT) has the potential to optimize industrial production. However, cold start latency is one of the main challenges in this area, resulting in resource waste. To address this issue, we propose a new machine learning-based resource management framework called MASTER which utilizes an extreme gradient boosting (XGBoost) model to predict the cold start latency for Industry 4.0 applications for performance optimization. Furthermore, we created a new cold start dataset using an IIoT scenario (i.e. predictive maintenance) to validate the proposed MASTER framework in serverless edge computing environments. We have evaluated the performance of the MASTER framework using a real-world serverless platform, Google Cloud Platform for single-step prediction (SSP) and multiple-step prediction (MSP) operations and compared it with existing frameworks that used deep deterministic policy gradient (DDPG) and long short-term memory (LSTM) models. The experimental results show that the XGBoost-based resource management framework is the most successful model in predicting cold start with mean absolute percentage error (MAPE) values of 0.23 in SSP and 0.12 in MSP. It has been also identified that the Linear Regression model (utilized in the MASTER framework) has the least computational time (0.03 seconds) as compared to other deep learning and machine learning models considered in this work. Finally, we compare the energy consumption and $\text{CO}_{2}$ emissions of all models to emphasize resource awareness.
Förderung
- National Natural Science Foundation of China
- Tianjin Science and Technology Planning
- Ministry of Education of the Turkish Republic
- HE ACES Project
Zitieren
APA
Golec, M., Gill, S. S., Wu, H., Can, T. C., Golec, M., Cetinkaya, O., Cuadrado, F., Parlikad, A. K., & Uhlig, S. (2024). MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0. IEEE Journal of Selected Areas in Sensors, 1, 36-48. https://doi.org/10.1109/jsas.2024.3396440
Vancouver
Golec M, Gill SS, Wu H, Can TC, Golec M, Cetinkaya O, et al. MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0. IEEE Journal of Selected Areas in Sensors. 2024;1:36-48. doi:10.1109/jsas.2024.3396440
BibTeX
@article{Golec2024,
author = {Golec, Muhammed and Gill, Sukhpal Singh and Wu, Huaming and Can, Talat Cemre and Golec, Mustafa and Cetinkaya, Oktay and Cuadrado, Felix and Parlikad, Ajith Kumar and Uhlig, Steve},
title = {MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0},
journal = {IEEE Journal of Selected Areas in Sensors},
year = {2024},
volume = {1},
pages = {36--48},
doi = {10.1109/jsas.2024.3396440}
}
EUVIMED