Proactive Elastic Circuit Deconstructor: A Machine Learning-Driven Resiliency Pattern For Microservices

Norton Stanley S A; Shoney Sebastian

doi:10.29284/n2npe876

Authors

Norton Stanley S A Department of Computer Science, CHRIST(Deemed to be University), Hosur Road,Bangalore, 560029, Karnataka, India.
Shoney Sebastian Department of Computer Science, CHRIST(Deemed to be University), Hosur Road,Bangalore, 560029, Karnataka, India.

DOI:

https://doi.org/10.29284/n2npe876

Keywords:

Cloud Computing, Microservices, Cloud Native, Design Patterns, Circuit Breaker, Elastic Circuit Deconstructor, Proactive Resiliency, Zero Downtime, Kubernetes.

Abstract

Adopting cloud-based architecture is essential for scalability and dependability in the changing and highly regulated application environment of today, especially through microservice architecture. Usually providing reactive ways to address issues post-occurrence, traditional resilience patterns that are implemented using libraries like Hystrix, Resilience4j based on error thresholds or timeouts in microservices could cause downtime and performance impacts. Similarly, service meshes like Istio and Linkerd offer L7-aware traffic control at the proxy level, but remain unaware of service functionality or domain-specific failure modes. This work presents a proactive method by including predictive machine learning models into microservice resilience patterns, with particular attention on the Circuit Breaker pattern to improve fault tolerance. This new method forecasts microservices’ abnormalities ahead of time and then switches over to another service with less failure probability. Based on the historic logs we could predict an alternative pre-configured service with least probability of failure and great accuracy using supervised learning methods including Random Forest and Randomised SearchCV. Our tests showed that the predictive models could efficiently forecast and switch to an alternative service, therefore proactively reducing any downtime. Without large system overhauls, the proposed pattern easily connects with current monitoring systems to increase resilience. This work proposes a proactive resilience design pattern for microservices that forecasts service dependability in real-time, ranks services by failure likelihood, and proactively reroutes requests to improve operational reliability, therefore providing robust services with minimal downtime.

References

[1] Gharibvand, V., Kolamroudi, Zeeshan: Cloud based manufacturing: A review of recent developments in architectures, technologies, infrastructures, platforms and associated challenges. The International Journal of Advanced Manufacturing Technology 131, 93–123 (2024) https://doi.org/10.1007/s00170-024-12989-y

[2] Z. Ding, B.F. Y. Xu, Jiang, C.: Microservice extraction based on a comprehensive evaluation of logical independence and performance. IEEE Transactions on Software Engineering 50, 1244–1263 (2024)

[3] Elgheriani, N.S., Ahme, N.D.A.S.: Microservices vs. monolithic architectures [the differential structure between two architectures]. MINAR International Journal of Applied Sciences and Technology 4, 500–514 (2022) https://doi.org/10.47832/ 2717-8234.12.47

[4] Hanada, H., Ishibashi, K.: Hexagon: Generating asynchronous microservices benchmarks for the evaluation of anomaly propagation resistance. In: 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 2436–2441 (2024)

[5] Stanley, N..S..A., Sebastian, S.: A systematic review on the identification and classification of patterns in microservices. In: 2023 4th International Conference for Emerging Technology (INCET), pp. 1–8 (2023)

[6] Stanley, N..S..A., Sebastian, S.: Circuit breaker: A resilience mechanism for cloud native architecture. In: 2023 Global Conference on Information Technologies and

Communications (GCITC), pp. 1–8 (2023)

[7] Lopes, J., Scarfone, K.: Unleashing intelligence: The intersection of cloud computing, ai, and ml. International Journal of Advanced Engineering Technologies and Innovations 1 (2024)

[8] B. Cline, D.H. R. S. Niculescu, Deckel, B.: Predictive maintenance applications for machine learning. In: 2022 Annual Reliability and Maintainability Symposium (RAMS), pp. 1–7 (2017)

[9] J. Nobre, E.J.S.P., Reis, A.: Anomaly detection in microservice-based systems. International Journal of Experimental Research and Review 13, 7891 (2023)

[10] N. Stanley, S., Sebastian, S.: Elastic circuit de-constructor: a pattern to enhance resiliency in microservices, 1–22 (2024)

[11] J. Luo, J.-W.S., Xue., W.: Design and implementation of an efficient multipath for a san environment. International Symposium on Parallel and Distributed Processing and Applications (2005)

[12] Khalil, M.: Storage design and implementation in vsphere 6: A technology deep dive. In: Vmware Press Technology (2017)

[13] Storage, P.: Content Studio, “What is MPIO? (2024). https://www.purestorage. com/knowledge/what-is-mpio.html

[14] Singh, N.D.P.: Cloud-based machine learning: Opportunities and challenges. International Journal of Scientific Research in Computer Science Engineering and Information Technology 10(6), 267–270 (2024)

[15] Hlybovets, A., Paprotskyi, I.: Increasing the fault tolerance in microservice architecture. Cybernetics and Systems Analysis 60 (2024)

[16] A. Colman, Q.B.V. A. V. Uzunov, Chhetri, M.B.: Agent controlled service meshes for resilient, self-adaptive microservice systems. In: IEEE International Conference on Software Services Engineering (SSE), Chicago, IL, USA, 2023 (2023)

[17] M. Panahandeh, M.H. A. Hamou-Lhadj, Miller, J.: Serviceanomaly: An anomaly detection approach in microservices using distributed traces and profiling metrics. Journal of Systems and Software 209 (2023)

[18] D. Noetzold, V.R.Q.L. A. G. D. M. Rossetto, Costa, H.J.D.M.: Enhancing infrastructure observability: Machine learning for proactive monitoring and anomaly detection. Journal of Internet Services and Applications 15 (2024)

[19] Akta¸s, K., Kilinc, H.H.: Interaction prediction and anomaly detection in a microservices-based telecommunication platform. In: ICSSP ’24: International

Conference on Software and Systems Processes, pp. 56–65 (2024)

[20] K. Yamnual, P.P., Achalakul, T.: Failure detection through monitoring of the scientific distributed system. In: 2017 International Conference on Applied System Innovation (ICASI), pp. 568–571 (2017)

[21] D. K. Yadav, A.K., Yadav, N.: Predicting machine failure using machine learning and deep learning algorithms. Sustainable Manufacturing and Service Economics 3, 100029 (2024)

[22] W. Marfo, D.K.T., Moore, S.V.: Tcondition monitoring and anomaly detection in cyber-physical systems. In: 2022 17th Annual System of Systems Engineering Conference (SOSE) (2022)

[23] Al., T.E.: Intelligent proactive fault tolerance at the edge through resource usage prediction. ITU Journal on Future and Evolving Technologies (3), 761–778 (2023)

[24] Asmawi, T.N.T., Ismail, A., Shen, J.: Cloud failure prediction based on traditional machine learning and deep learning. Journal of Cloud Computing Advances Systems and Applications 11(1) (2022)

[25] T, A.T.N., Ismail, A., Shen, J.: A proactive approach to fault tolerance using predictive machine learning models in distributed systems. International Journal of Experimental Research and Review 44, 208–220 (2024)

[26] M. Raeiszadeh, R.H.G.J.E. A. Ebrahimzadeh, F. Mini, R.: Asynchronous realtime federated learning for anomaly detection in microservice cloud applications. IEEE Transactions on Machine Learning in Communications and Networking (2025)

[27] Haroon, S.Z.A.H.M.A.A..A.T. M.: A proactive approach to fault tolerance using predictive machine learning models in distributed systems. International Journal of Experimental Research and Review (2024)

[28] Akta¸s, K., Kilinc, H.H.: Interaction prediction and anomaly detection in a microservices-based telecommunication platform. International Conference on Software and Systems Processes (ICSSP ’24) (2024)

[29] Kalaskar, .T.S. C.: Fault tolerance of cloud infrastructure with machine learning. Cybernetics and Information Technologies (2023)

[30] Gururaj: Fault tolerance of network routers using machine learning techniques (2023)

[31] Theodoropoulos: Intelligent proactive fault tolerance at the edge through resource usage prediction. ITU Journal on Future and Evolving Technologies (2022)

[32] Asmawi: Cloud failure prediction based on traditional machine learning and deep learning. Research Square (2022)

[33] Chakrabarty: Flight arrival delay prediction using gradient boosting classifier. In Advances in intelligent systems and computing (2018)

[34] K. Yamnual, P.P., Achalakul, T.: Failure detection through monitoring of the scientific distributed system. International Conference on Applied System Innovation (ICASI) (2017)

[35] al., R.R.: Instantops: A joint approach to system failure prediction and root cause identification in microserivces cloud-native applications. ICPE ’24: Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering (2024)

[36] A. Ampatzoglou, S.C., Stamelos, I.: Research state of the art on gof design patterns: A mapping study. Journal of Systems and Software, vol. 86, no. 7 (2013)

[37] Fowler, M.: Patterns of Enterprise Application Architecture., (2002)

[38] Punithavathy, E., Priya, N.: Auto retry circuit breaker for enhanced performance in microservice applications. International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, vol. 14, no. 2 (2024)

[39] F. Meng, L.J., Thottan, M.: Model-based reinforcement learning for service mesh fault resiliency in a web application-level. arXiv (Cornell University) (2021)

[40] C. Meiklejohn, C.C.M.R. L. Stark, Miller, H.: Method overloading the circuit. In: SoCC ’22: Proceedings of the 13th Symposium on Cloud Computing (2022)

[41] M. R. S. Sedghpour, B.S.C.K. D. Garlan, Tordsson, J.: Breaking the vicious circle: Self-adaptive microservice circuit breaking and retry. In: 2023 IEEE International Conference on Cloud Engineering (IC2E), Boston, MA, USA (2023)

[42] Kephart, J.O., Chess, D.M.: The vision of autonomic computing. Computer, vol. 36, no. 1 (2003)

[43] Salehie, M., Tahvildari, L.: Self-adaptive software. ACM Transactions on Autonomous and Adaptive Systems (2009)

[44] Tan, R., Li, Z.: Maad: A distributed anomaly detection architecture for microservices systems. In: 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2024)

[45] al., M.J.: An anomaly detection algorithm for microservice architecture based on robust principal component analysis. IEEE Access, vol. 8 (2020)

[46] al., Y.G.: An open-source benchmark suite for microservices and their hardwaresoftware implications for cloud edge systems. In: Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (2019)

[47] Scikit-learn: Cross-validation: evaluating estimator performance. https:// scikit-learn.org/1.5/modules/cross validation.html