Optimizing Microservices Performance with Reinforcement Learning: A Case Study in Spring Boot Applications
Main Article Content
Abstract
Microservices architectures have become a popular approach to building scalable, flexible, and maintainable applications. However, optimizing their performance in dynamic environments remains a significant challenge. This paper presents a novel approach to performance optimization in microservices using reinforcement learning (RL). Focusing on Spring Boot applications, we propose an RL-based framework that dynamically adjusts resource allocation, load balancing, and microservice configuration to maximize performance metrics such as response time, throughput, and resource utilization. The reinforcement learning agent learns optimal strategies through interactions with the system, considering real-time performance data and system constraints. A case study demonstrates the practical implementation of the framework in a real-world Spring Boot application, showcasing how the RL model effectively tunes system parameters to improve efficiency and scalability under varying load conditions. Experimental results highlight significant improvements in performance compared to traditional optimization methods, offering a promising solution for automated, intelligent microservices management. This approach empowers organizations to achieve better system responsiveness and resource efficiency with minimal manual intervention.
Article Details
References
Jain, J., Modake, R., Khunger, A., & dnyandev Jagdale, A. CLOUD-NATIVE SECURITY FRAMEWORK: USING MACHINE LEARNING TO IMPLEMENT SELECTIVE MFA IN MODERN BANKING PLATFORMS , 2019.
Van Vlasselaer, V., Eliassi-Rad, T., Akoglu, L., Snoeck, M., & Baesens, B. (2017). GOTCHA! Network-based fraud detection for social security fraud. Management Science, 63(9), 3090–3110.
Pozzolo, A. D., Boracchi, G., Caelen, O., Alippi, C., & Bontempi, G. (2018). Credit card fraud detection: A realistic modeling and a novel learning strategy. IEEE Transactions on Neural Networks and Learning Systems, 29(8), 3784–3797.
Carcillo, F., Dal Pozzolo, A., Le Borgne, Y. A., Caelen, O., Mazzer, Y., & Bontempi, G. (2019). Scarff: A scalable framework for streaming credit card fraud detection with Spark. Information Fusion, 41, 182–194.
Roy, A., Sun, J., Mahoney, W., Alshboul, R., & Prabakar, N. (2018). Deep learning detecting fraud in credit card transactions. In Proceedings of the IEEE International Conference on Big Data (pp. 1846–1855).