A Novel Hybrid Model for Docker Container Workload Prediction

• Published in: IEEE eTransactions on network and service management Vol. 20; no. 3; p. 1
• Main Authors: Zhang, Liangkang, Xie, Yulai, Jin, Minpeng, Zhou, Pan, Xu, Gongming, Wu, Yafeng, Feng, Dan, Long, Darrell
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Autoregressive models; Cloud computing; Containers; Docker; Hybrid systems; Load modeling; Logic gates; LSTM; Predictive models; Real time; Resource management; Resource utilization; Smoothing; Smoothing methods; Statistical analysis; Time series analysis; Triple exponential smoothing; Workload; Workload prediction; Workloads
• ISSN: 1932-4537; 1932-4537
• DOI: 10.1109/TNSM.2023.3248803

The emergence of containers dramatically simplifies and facilitates the development and deployment of applications. More and more enterprises deploy their applications on the container cloud platform. For cloud service providers, an effective container workload prediction method is a must to achieve efficient utilization of cloud resources. However, the existing methods are either rarely based on container load characteristics or cannot make accurate real-time predictions. In this paper, we propose a Docker container workload proactive prediction method using a hybrid model combining triple exponential smoothing and long short-term memory (LSTM), which not only can capture both short-term and long-term dependencies in container resource time series but also smooth the container resource utilization data. In order to improve the prediction accuracy of the hybrid model, those two single models are combined using the mean absolute percentage error (MAPE) method. Besides, we design a real-time Docker workload prediction system for the hybrid model. Our experiments show that the mean absolute percentage error of the hybrid model is decreased by an average of 3.24%, 12.18%, 13.42%, 43.45%, and 50.69% compared with the LSTM, the triple exponential smoothing, ES-ARIMA, Bayesian Ridge Regression and BiLSTM with an acceptable time and computational cost overhead.