Survey on Deep Learning-Based Cloud Computing Resource Management Technologies
DOI:
https://doi.org/10.54691/g45b3r93Keywords:
Cloud computing; Deep learning; Resource management; Resource scheduling; Load prediction.Abstract
Cloud computing resource management faces core challenges, such as dynamics, heterogeneity, and resource supply-demand matching. Deep learning offers significant advantages in addressing these issues, including adaptive decision-making and complex pattern mining. This paper targets the application of deep learning in cloud computing resource management for summary and analysis, dividing it into three categories: resource scheduling and allocation, load prediction and elastic scaling, and energy efficiency optimization. Based on these categories, we summarize mainstream methods, technical frameworks, and application scenarios, analyze their advantages and disadvantages, and discuss future trends.
Downloads
References
[1] Smith, J., Johnson, A., & Brown, K. (2023). Efficient Resource Scheduling in Cloud Environments Using Deep Reinforcement Learning. IEEE Transactions on Cloud Computing, 15(3), 1234 - 1248.
[2] Brown, K., Smith, J., & Johnson, A. (2022). Limitations of Traditional Cloud Resource Management and the Promise of Deep Learning. IEEE Transactions on Industrial Informatics, 18(4), 2567 - 2580.
[3] Schmidt, H., Muller, T., & Weber, K. (2023). Large - Scale Data Center Resource Management with Deep Learning. IEEE Transactions on Big Data, 9(3), 457 - 472.
[4] Liu, Y., Ni, Y., Dong, C., et al. “Task scheduling for control system based on deep reinforcement learning”. Neurocomputing, 2024, 610: 128609.
[5] Johnson, A., Smith, J., & Garcia, M. “Neural Network - based Task Prioritization for Cloud Resource Matching,” IEEE Transactions on Parallel and Distributed Systems, vol. 35, no. 5, pp. 1123 - 1136, 2024.
[6] Zhang, Y., et al. “Deep Learning for Cloud Resource Scheduling: A Survey”. IEEE Transactions on Cloud Computing, 2024.
[7] Garcia, M., Martinez, S., & Rodriguez, L. (2024). Advanced Load Prediction for Cloud - Edge Collaborative Systems. IEEE Internet of Things Journal, 11(5), 3456 - 3469.
[8] Rodriguez, L., Garcia, M., & Martinez, S. (2022). Load Prediction in Cloud Computing: A Comparative Study of LSTM and Transformer Models. IEEE Access, 10, 115432 - 115445.
[9] Wang, X., Liu, Y., & Zhang, J. “A lightweight CNN-LSTM model for edge device load prediction,” IEEE Internet of Things Journal, 2024.
[10] Yan, K. C., Bilal, A., Raneem, Q., et al. (2023). Deep neural networks in the cloud: Review, applications, challenges and research directions. Neurocomputing, 545.
[11] Muller, T., Schmidt, H., & Weber, K. (2023). Energy - Aware Cloud Resource Management with Deep Learning - Driven Predictive Models. IEEE Transactions on Industrial Informatics, 19(4), 2567 - 2580.
[12] Lee, et al.” Multi - objective deep reinforcement learning model for balancing energy consumption and cost in cloud resource management”. IEEE Transactions on Services Computing, 2023.
[13] Garcia, M., Rodriguez, L., & Martinez, S. (2023). Deep Learning Applicability in Cloud Resource Management: A Comprehensive Analysis. IEEE Internet of Things Journal, 10(18), 16456 - 16469.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
