Designing Scalable Artificial Intelligence Systems Using Microservices-Based Machine Learning Architectures

Authors

  • Andreu Unai Pedro Luis AI Systems Architect, Egypt Author

Keywords:

Microservices, Machine Learning, AI Scalability, System Architecture, Cloud AI, Containerization

Abstract

Purpose: This paper investigates the design of scalable artificial intelligence (AI) systems using microservices-based machine learning (ML) architectures.

Design/methodology/approach: A structured literature review was conducted on studies published before 2020 to assess architectural patterns, scalability mechanisms, and performance implications of microservices in ML deployments.

Findings: Microservices-based ML enhances scalability, flexibility, and continuous deployment in AI systems. However, issues such as orchestration complexity, service dependencies, and latency challenges remain.

Practical implications: This architectural approach facilitates modular deployment of AI components, promoting rapid innovation and fault isolation in large-scale enterprises.

Originality/value: This paper synthesizes key architectural paradigms and proposes an integrated framework combining ML workflows and containerized microservices for real-world scalability.

References

Chakraborty, A., Ganguly, S., & Das, S. (2019). Architectural Pattern for Implementing XAI as a Service. Artificial Intelligence and Optimization, Taylor & Francis. https://doi.org/10.1201/9781003592969-7

Chang, H., Kodialam, M., & Lakshman, T. V. (2019). Microservice Fingerprinting and Classification Using Machine Learning. IEEE ICNP, 1–10. https://ieeexplore.ieee.org/document/8888077

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

Devarakonda, R. R. (2017). A Microservices-Based Approach for Scalable Deployment of ML Models. SSRN. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5234707

Kaul, D. (2019). Blockchain-Powered Cyber-Resilient Microservices. SSRN. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5096255

Gummadi, V. P. K. (2020). API design and implementation: RAML and OpenAPI specification. Journal of Electrical Systems, 16(4). https://doi.org/10.52783/jes.9329

Prosper, J. (2018). AI-Powered Enterprise Architectures for Omni-Channel Sales. ResearchGate. https://www.researchgate.net/publication/389735586

Ribeiro, J. L., Figueredo, M., & Araujo, A. (2019). A Microservice-Based Topology for ML Deployment. IEEE Latin America Transactions. https://ieeexplore.ieee.org/document/9071708

Sabol, P., & Sincak, P. (2018). AI Bricks: A Microservices-Based Software for Cloud Robotics. IEEE International Conference on Systems and Machines. https://ieeexplore.ieee.org/document/8490532

Salah, T., Zemerly, M. J., & Yeun, C. Y. (2016). The Evolution of Distributed Systems toward Microservices Architecture. IEEE Conference on Innovations in Information Technology, 140–145. https://ieeexplore.ieee.org/document/7856721

Sharma, I. (2018). Semi-Supervised Learning for Scalable AI Models. International Journal of AI and ML, 6(2), 45–55. https://itaimle.com/article/view/168

Thompson, A. (2019). Integrating Automation and AI in Microservices Architectures. IJAI-ML, 8(3), 22–35. https://itaimle.com/article/view/80

Downloads

Published

2021-05-04

How to Cite

Designing Scalable Artificial Intelligence Systems Using Microservices-Based Machine Learning Architectures. (2021). GLOBAL JOURNAL OF MULTIDISCIPLINARY RESEARCH AND DEVELOPMENT, 2(1), 5-10. https://gjmrd.com/index.php/GJMRD/article/view/GJMRD.2.1.002