Adaptive Federated Analytics Frameworks for Distributed Enterprise Data Systems

  • Authors

    • Dr. R. Kartikeyan Assosciate Professor, Department of IT, PSG College of Arts and Science, Coimbatore, Tamil Nadu, India. Author
    • B. Sithik Shah Research scholar, Department of IT, PSG College of Arts and Science, Coimbatore, Tamil Nadu, India. Author

    DOI:

    https://doi.org/10.67228/30713498/IJADSMC-2024PI6B7Q

    Published 01-04-2022

  • Federated Analytics, Distributed Enterprise Systems, Privacy-Preserving Analytics, Adaptive Aggregation, Enterprise Intelligence, Distributed Computing, Secure Data Analytics, Hybrid Cloud Systems

    Issue

    Vol. 7 No. 1 (2024)

    Section

    Articles

    How to Cite

    [1]
    K. R and S. Shah, “Adaptive Federated Analytics Frameworks for Distributed Enterprise Data Systems”, IJADSMC, vol. 7, no. 1, pp. 01–16, Jan. 2022, doi: 10.67228/30713498/IJADSMC-2024PI6B7Q.

  • Abstract

    As enterprise data grows across cloud, edge, and geographically distributed environments, traditional centralized analytics face challenges related to privacy, security, scalability, and regulatory compliance. To address these issues, this study proposes an Adaptive Federated Analytics Framework (AFAF) for distributed enterprise data systems. The framework enables collaborative analytics without sharing raw data by incorporating adaptive node selection, dynamic aggregation, privacy-preserving mechanisms, and communication optimization techniques. Unlike conventional federated approaches, AFAF dynamically evaluates node reliability, computational capacity, data quality, and network conditions to improve analytical performance. The framework integrates differential privacy, secure multi-party computation (SMPC), and encrypted aggregation to ensure enterprise-grade security and compliance. Experimental evaluations in hybrid cloud enterprise environments demonstrate improvements in analytical accuracy, aggregation efficiency, communication overhead, convergence stability, scalability, and fault tolerance compared with traditional federated systems. The framework also supports real-time analytics through adaptive participation thresholds and aggregation frequencies, enabling timely insights from distributed data sources. Results indicate that AFAF provides a scalable, secure, and efficient platform for privacy-preserving enterprise intelligence, with future enhancements including AI-driven orchestration, blockchain-based trust management, and autonomous analytics optimization.

  • References

    [1] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proc. 20th Int. Conf. Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, USA, 2017, pp. 1273–1282.

    [2] J. Konečný, H. B. McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, and D. Bacon, “Federated Learning: Strategies for Improving Communication Efficiency,” arXiv preprint arXiv:1610.05492, 2016.

    [3] Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated Machine Learning: Concept and Applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 1–19, 2019.

    [4] P. Kairouz et al., “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2021.

    [5] B. McMahan and D. Ramage, “Federated Learning: Collaborative Machine Learning without Centralized Training Data,” Google AI Research White Paper, 2017.

    [6] C. Dwork, “Differential Privacy,” in Proc. 33rd International Colloquium on Automata, Languages and Programming (ICALP), Venice, Italy, 2006, pp. 1–12.

    [7] C. Dwork and A. Roth, “The Algorithmic Foundations of Differential Privacy,” Foundations and Trends in Theoretical Computer Science, vol. 9, no. 3–4, pp. 211–407, 2014.

    [8] C. Gentry, “Fully Homomorphic Encryption Using Ideal Lattices,” in Proc. 41st ACM Symposium on Theory of Computing (STOC), Bethesda, MD, USA, 2009, pp. 169–178.

    [9] K. Bonawitz et al., “Practical Secure Aggregation for Privacy-Preserving Machine Learning,” in Proc. ACM SIGSAC Conference on Computer and Communications Security (CCS), Dallas, TX, USA, 2017, pp. 1175–1191.

    [10] A. C. Yao, “Protocols for Secure Computations,” in Proc. 23rd Annual Symposium on Foundations of Computer Science (FOCS), Chicago, IL, USA, 1982, pp. 160–164.

    [11] B. Zhao, K. Lee, and H. Shin, “Adaptive Federated Learning with Dynamic Client Selection,” IEEE Access, vol. 9, pp. 135742–135755, 2021.

    [12] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated Optimization in Heterogeneous Networks,” in Proc. Machine Learning and Systems (MLSys), Austin, TX, USA, 2020, pp. 429–450.

    [13] S. Wang, T. Tuor, T. Salonidis, K. K. Leung, C. Makaya, T. He, and K. Chan, “Adaptive Federated Learning in Resource-Constrained Edge Computing Systems,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1205–1221, 2019.

    [14] Y. Lin, S. Han, H. Mao, Y. Wang, and W. Dally, “Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training,” in Proc. International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.

    [15] J. Dean and S. Ghemawat, “MapReduce: Simplified Data Processing on Large Clusters,” Communications of the ACM, vol. 51, no. 1, pp. 107–113, Jan. 2008.

    [16] Gajula, S. (2023). A review of anomaly identification in finance frauds using machine learning system. International Journal of Current Engineering and Technology, 13(6), 568–575. https://ijcet.evegenis.org/index.php/ijcet/article/view/820.

  • Downloads