Building Sustainable AI Microservices in Heterogeneous Digital Infrastructure Environments Using Hybrid Machine Learning Approaches and Scalable Service Design
Keywords:
AI microservices, hybrid machine learning, sustainable systems, scalable design, heterogeneous environments, service-oriented architectureAbstract
The emergence of microservices as a dominant architectural paradigm has transformed the way software systems are designed, deployed, and scaled. However, integrating artificial intelligence (AI) into microservices presents challenges related to sustainability, interoperability, and scalability, particularly within heterogeneous digital infrastructures. This paper explores a hybrid machine learning approach to enhance AI-driven microservices in varied environments. We propose a design framework that ensures adaptability, energy efficiency, and distributed intelligence. Through scalable service design patterns and hybrid models combining supervised and reinforcement learning, this research addresses the technological and architectural barriers that limited earlier deployments. Practical implications are demonstrated through comparative performance benchmarks and a proposed sustainability-aware architecture for AI microservices.
References
(1) Gannon, D., Barga, R., & Sundaresan, N. (2017). Cloud-native applications. IEEE Internet Computing, 21(3), 62-67. https://doi.org/10.1109/MIC.2017.68
(2) Xu, X., & Buyya, R. (2016). Energy-efficient scheduling of cloud applications using hybrid machine learning. Journal of Systems and Software, 122, 179-191. https://doi.org/10.1016/j.jss.2016.08.015
(3) Pahl, C., & Jamshidi, P. (2016). Microservices: A systematic mapping study. CLOSER, 137-146. https://doi.org/10.5220/0005785501370146
(4) 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
(5) Villamizar, M. et al. (2016). Evaluating the monolithic and the microservice architecture pattern to deploy web applications. SPLASH, 103-104. https://doi.org/10.1145/2989238.2989239
(6) Dustdar, S., & Schreiner, W. (2017). Principles of elastic processes. IEEE Internet Computing, 21(3), 66-71. https://doi.org/10.1109/MIC.2017.68
(7) Fernández-Montes, A. et al. (2017). Power-aware orchestration in heterogeneous clouds. Future Generation Computer Systems, 74, 75-87. https://doi.org/10.1016/j.future.2016.03.010
(8) Di Francesco, P. et al. (2018). Architecting for continuous delivery: On the role of microservices and containers. Journal of Systems and Software, 133, 174-186. https://doi.org/10.1016/j.jss.2017.12.013
(9) Kavis, M. (2014). Architecting the cloud: Design decisions for cloud computing service models. Wiley.
(10) Leite, L. et al. (2016). A systematic mapping study of DevOps. Journal of Systems and Software, 128, 1-16. https://doi.org/10.1016/j.jss.2017.02.061
(11) Medvidovic, N., & Taylor, R. N. (2010). Software architecture: Foundations, theory, and practice. Wiley.
Downloads
Published
Issue
Section
Deprecated: urlencode(): Passing null to parameter #1 ($string) of type string is deprecated in /home/u877385332/domains/ijraics.com/public_html/plugins/generic/pflPlugin/PflPlugin.php on line 216
