An Integrated AI Framework for Predictive Performance Optimization in Cloud-Connected Intelligent Devices

  • Authors

    • Thaneswaran Department of CSE, MAM College of Engineering, India. Author

    DOI:

    https://doi.org/10.67228/3142788X/IJMLPA-V9I3P102

    Published 07-06-2026

  • Artificial Intelligence, Predictive Performance Optimization, Cloud-Connected Intelligent Devices, Edge Computing, Internet of Things, Machine Learning, Resource Allocation, Adaptive Orchestration, Energy Efficiency, Predictive Analytics

    Issue

    Vol. 9 No. 3 (2026)

    Section

    Articles

  • Abstract

    Things (IoT) has enabled intelligent devices to support real-time monitoring and automated decision-making. However, performance optimization remains challenging due to fluctuating workloads, network latency, energy constraints, and limited computational resources. This article proposes an integrated AI framework for predictive performance optimization in cloud-connected intelligent devices. The framework combines real-time monitoring, machine-learning-based prediction, adaptive resource allocation, cloud-edge task orchestration, and feedback-driven optimization. It aims to balance response time, throughput, energy consumption, resource utilization, and reliability while ensuring privacy and operational stability. A conceptual evaluation methodology is proposed to compare the framework with conventional resource-management approaches. Since experimental validation has not yet been conducted, performance improvements are presented as hypotheses for future testing. The framework provides a foundation for intelligent resource management in healthcare, smart manufacturing, transportation, smart buildings, and industrial IoT, while highlighting future research opportunities in federated learning, digital twins, reinforcement learning, and explainable AI.

  • References

    [1] Chen, X., Jiao, L., Li, W., & Fu, X. (2016). Efficient multi-user computation offloading for mobile-edge cloud computing. IEEE/ACM Transactions on Networking, 24(5), 2795–2808. https://doi.org/10.1109/TNET.2015.2487344

    [2] Dean, J., & Barroso, L. A. (2013). The tail at scale. Communications of the ACM, 56(2), 74–80. https://doi.org/10.1145/2408776.2408794

    [3] Harchol-Balter, M. (2013). Performance modeling and design of computer systems: Queueing theory in action. Cambridge University Press.

    [4] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

    [5] Seknametla, P. R., & Sunkara, R. (2023). GitOps at Scale: Multi-Cluster Kubernetes Management Using Declarative Infrastructure Pipelines.

    [6] Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(4), 2322–2358. https://doi.org/10.1109/COMST.2017.2745201

    [7] Kotadiya, U., Arora, A. S., & Yachamaneni, T. (2024). Intelligent Orchestration of Cloud-Native Applications Using Google Cloud Platform and Microservices-Based Architectures. International Journal of AI, BigData, Computational and Management Studies, 5(4), 106-114.

    [8] Gantikota, S. (2025). Privacy-By-Design Engineering Under GDPR and CCPA: Practical Patterns for Cross-Border Data Handling In Cloud-Based Applications. International Journal of AI, BigData, Computational and Management Studies, 6(1), 227-231. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V6I1P123

    [9] Mell, P., & Grance, T. (2011). The NIST definition of cloud computing (NIST Special Publication 800-145). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-145

    [10] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39. https://doi.org/10.1109/MC.2017.9

    [11] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198

    [12] Paruchuri, J. K. (2021). Lakehouse architecture: Unifying data lakes and data warehouses. International Journal of Computer Techniques (IJCT), 8(1), 1-15.

    [13] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.

    [14] Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020). Convergence of edge computing and deep learning: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(2), 869–904. https://doi.org/10.1109/COMST.2020.2970550

    [15] Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762. https://doi.org/10.1109/JPROC.2019.2918951

    [16] Uddandarao, D. P., Mahajan, A., & Krishnamsetty, P. Double Machine Learning for Downstream Causal Measurement: A Hybrid Econometric-ML Framework for Feature Valuation.

    [17] Brahmandam, L. M. K. (2024). Performance Engineering for Multi-Tenant Analytic Workloads on Snowflake: An Empirical Study of Clustering, Materialized Views, Query Tuning, and Virtual Warehouse Sizing Across Production Reference Deployments at Billion-Row Scale. International Journal of AI, BigData, Computational and Management Studies, 5(1), 198-207. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V5I1P120

  • Downloads