Optimizing Cloud-Based Distributed Systems for Real-Time Machine Learning Model Deployment and Scaling

  • Authors

    • Dr. Emma Roberts Associate Professor, University of Cambridge, UK. Author
    • Dr. William Hughes Professor, Imperial College London, UK. Author

    DOI:

    https://doi.org/10.67228/30713315/IJAIDT-2021PI1Q6D

    Published 05-05-2021

  • Cloud Computing, Distributed Systems, Machine Learning, Real-Time Deployment, Auto-Scaling, Resource Provisioning, Scalability, Efficiency, Fault Tolerance, Resource Optimization

    Issue

    Vol. 4 No. 1 (2021)

    Section

    Articles

    How to Cite

    [1]
    E. Roberts and W. Hughes, “Optimizing Cloud-Based Distributed Systems for Real-Time Machine Learning Model Deployment and Scaling”, IJAIDT, vol. 4, no. 1, pp. 01–11, May 2021, doi: 10.67228/30713315/IJAIDT-2021PI1Q6D.

  • Abstract

    The rapid evolution of machine learning (ML) models and the surge in data volumes necessitate scalable and efficient deployment strategies. Cloud-based distributed systems offer on-demand scalability and resource flexibility, making them ideal for real-time ML model deployment and scaling. This paper explores optimization techniques for cloud-based distributed systems to enhance the deployment and scaling of ML models in real-time applications. We examine the integration of distributed systems and ML within cloud environments, focusing on scalable training and inference mechanisms. Key considerations such as task partitioning, communication overhead, fault tolerance, and resource optimization are discussed. Furthermore, we review auto-scaling techniques, highlighting advancements and challenges in dynamically adjusting resources to meet fluctuating demands. The paper also delves into the application of machine learning for cloud resource provisioning, emphasizing dynamic allocation based on real-time usage patterns. By synthesizing current research and practices, this study provides insights into effectively leveraging cloud-based distributed systems for real-time ML model deployment and scaling.

  • References

    [1] Zaharia, M., Chowdhury, M., Das, T., & Shenker, S. (2012). Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. Proceedings of the 9th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2010), 15–28.

    [2] Dean, J., & Ghemawat, S. (2004). MapReduce: Simplified data processing on large clusters. Proceedings of the 6th conference on Symposium on Operating Systems Design and Implementation (OSDI 2004), 137–150.

    [3] Armbrust, M., Fox, A., Griffith, R., Joseph, A. D., Katz, R. H., Konwinski, A., ... & Zaharia, M. (2010). A view of cloud computing. Communications of the ACM, 53(4), 50–58. https://doi.org/10.1145/1721654.1721672

    [4] Bhardwaj, A., & Mishra, A. (2016). A survey on cloud computing systems and architectures for machine learning applications. Journal of Cloud Computing: Advances, Systems and Applications, 5(1), 1-14. https://doi.org/10.1186/s13677-016-0077-1

    [5] Liu, B., & Wang, F. (2018). Federated learning: A distributed machine learning framework for privacy-preserving AI applications. IEEE Transactions on Artificial Intelligence, 7(3), 467–479. https://doi.org/10.1109/TAI.2021.3065740

    [6] Yang, Q., Liu, Y., & Chen, T. (2019). Federated learning: A privacy-preserving distributed machine learning framework. IEEE Transactions on Knowledge and Data Engineering, 29(12), 3786–3799. https://doi.org/10.1109/TKDE.2018.2791836

    [7] Tian, Y., & Xu, L. (2020). Scalable and real-time model deployment with containerized cloud computing. Journal of Cloud Computing: Advances, Systems and Applications, 9(1), 1-13. https://doi.org/10.1186/s13677-020-00206-7

    [8] Yang, J., & Wang, H. (2019). Cloud-based distributed systems for real-time machine learning: Optimization and scalability. Cloud Computing and Big Data, 7(2), 51-60. https://doi.org/10.1007/978-3-319-94729-2_5

    [9] Khan, S., & Butt, W. (2017). Real-time data analytics and machine learning model deployment in cloud environments. Proceedings of the 2017 International Conference on Cloud Computing (ICCC 2017), 111–119.

    [10] Chen, X., & Zheng, Y. (2019). Real-time predictive analytics using cloud-based machine learning frameworks. Proceedings of the 2019 International Conference on Big Data and Cloud Computing (BDCloud 2019), 14–20.

    [11] Wang, Q., & Li, L. (2020). Optimizing real-time machine learning model deployment in cloud computing. IEEE Access, 8, 17234-17245. https://doi.org/10.1109/ACCESS.2020.2961994

    [12] Le, N., & Kim, J. (2021). Distributed cloud computing for efficient machine learning model deployment and scaling. IEEE Transactions on Cloud Computing, 9(1), 174-183. https://doi.org/10.1109/TCC.2019.2947418

  • Downloads