FEDERATED MACHINE LEARNING IN MICROSERVICES ARCHITECTURE: AN ARTIFICIAL INTELLIGENCE APPROACH FOR PRIVACY-PRESERVING DISTRIBUTED SYSTEMS

Laia Alegret Miguel  Journal

FEDERATED MACHINE LEARNING IN MICROSERVICES ARCHITECTURE: AN ARTIFICIAL INTELLIGENCE APPROACH FOR PRIVACY-PRESERVING DISTRIBUTED SYSTEMS

Authors

Laia Alegret Miguel Journal

Federated Learning & Privacy-Preserving AI Engineer, USA.

Keywords:

Federated Learning, Microservices, Privacy-Preserving AI, Distributed Systems, Edge Computing, Containerization, Secure AI Collaboration

Synopsis

Purpose: This study explores the integration of Federated Learning (FL) into microservices-based distributed systems, emphasizing privacy-preserving mechanisms for data-driven AI applications.

Design/methodology/approach: The paper presents a structured approach combining Federated Learning with containerized microservices, enabling decentralized model training across edge devices while maintaining data locality. It uses qualitative comparative analysis of prior implementations, theoretical modeling, and architecture mapping.

Findings: FL within microservices ensures high scalability and modular design while preserving data privacy. The approach mitigates data leakage and supports secure collaboration across heterogeneous systems without compromising performance.

Practical implications: Organizations can deploy privacy-sensitive AI applications in regulated sectors (e.g., healthcare, banking) using FL embedded within microservices, leading to easier policy compliance and system resilience.

Originality/value: This research uniquely aligns Federated Learning with microservice orchestration, filling the gap in privacy-aware AI system architecture and offering a deployable blueprint for real-world applications.

References

[1] Zhang, Y., Salehinejad, H., & Barfett, J. (2019). Privacy Preserving Deep Learning with Distributed Encoders. IEEE Global Communications Conference. https://ieeexplore.ieee.org/document/8969086

[2] Sharma, A. (2019). A Multi-Layered Framework for Secure Distributed Computing. AIJCST,

[3] Kumar, R. (2017). Privacy-Preserving Machine Learning Models. IJAIML,

[4] Desai, R. (2017). Federated Learning: A Decentralized Approach to AI. IJAIML,

[5] Gummadi, V. P. K. (2019). Microservices architecture with APIs: Design, implementation, and MuleSoft integration. Journal of Electrical Systems, 15(4), 130–134. https://doi.org/10.52783/jes.9328

[6] Oloke, K. (2019). Federated Financial Decision Engines. ResearchGate,

[7] Dash Karan, D.A. (2019). The Future of Data Analytics. ResearchGate,

[8] Patel, M.D. (2019). AI-Enabled Threat Prediction. AIJCST,

[9] Esposito, C., & Castiglione, A. (2017). Security in Microservices for Health Networks. IEEE Communications, https://ieeexplore.ieee.org/document/8030494

[10] Agarwal, A., Dowsley, R., & McKinney, N. (2019). Privacy-Preserving Regression in EEG Systems. IEEE Neural Systems Conference,

[11] D’Hondt, T., Wilbik, A., Grefen, P., & Ludwig, H. (2019). Federated BPM Systems. ACM Proceedings, https://dl.acm.org/doi/10.1145/3365871.3365890