AI-Driven Dynamic Scaling Frameworks for Resilient Microservices in Cloud-Based E-Commerce Platforms
DOI:
https://doi.org/10.15680/IJCTECE.2025.0802013Keywords:
AI-driven autoscaling, dynamic scaling, microservices, cloud computing, e-commerce platforms, Kubernetes, workload prediction, resilience, resource optimization, fault toleranceAbstract
Microservices play a crucial role in delivering fast, reliable and scalable digital commerce experiences. But the rules-based, manual/automatic resource scaling can lead to over-provisioning resources, failing to meet all combinations of resources demand or simply being too slow to meet demand needs. The proposed research paper proposes an idea of how to create Resilient Microservices for Cloud Based ecommerce Application with AI based Dynamic Scaling Framework. Ensuring the availability and performance of the system is addressed via the framework by means of real-time monitoring, workload prediction, anomaly detection, intelligent allocation of resources and feedback based optimization. Through a machine learning model, the framework understands these characteristics in these historical workloads and uses these to forecast future trends in workload, CPU/memory usage, transaction query latency, traffic volume etc., depending on which services are in use. Based on these predictions, an automatic scaling process which is based on a container orchestration system like Kubernetes can scale up or down by horizontally or vertically scaling the microservices. Also part of the proposed framework are various resilience aspects like service health monitoring, fault detection, load balancing, circuit breaking and self-healing to minimize service downtimes and keep services up and running. The paper highlights the advantages of AI for scaling, including faster response times, optimized cloud resource usage, increased fault tolerance, and reduced costs. When not only is it capturing data over time but also leveraging insights from data to dynamically adjust the scaling, it's an appealing solution for complex and highly trafficked microservices that are considered important for meeting enterprise objectives. This research also contributes to the advocacy of intelligence cloud administration to build up scalable and resilient e-commerce structure which are cost efficien
References
[1] H. Qiu, S. S. Banerjee, S. Jha, Z. T. Kalbarczyk, and R. K. Iyer, “FIRM: An intelligent fine-grained resource management framework for SLO-oriented microservices,” in 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), 2020, pp. 805–825.
[2] V. Subramani, “Dynamic scaling in e-commerce platforms: Microservices for latency, compliance, and resilience,” Computer Fraud and Security, vol. 2024, no. 11, 2024. [Online]. Available: https://computerfraudsecurity.com/index.php/journal/article/view/879
[3] J. Park, B. Choi, C. Lee, and D. Han, “GRAF: A graph neural network based proactive resource allocation framework for SLO-oriented microservices,” in Proceedings of the 17th International Conference on Emerging Networking EXperiments and Technologies, 2021, pp. 154–167.
[4] G. Yu, P. Chen, and Z. Zheng, “Microscaler: Automatic scaling for microservices with an online learning approach,” in 2019 IEEE International Conference on Web Services (ICWS), 2019, pp. 68–75.
[5] B. Choi, J. Park, C. Lee, and D. Han, “pHPA: A proactive autoscaling framework for microservice chain,” in 5th Asia-Pacific Workshop on Networking (APNet 2021), 2021, pp. 65–71.
[6] A. U. Gias, G. Casale, and M. Woodside, “ATOM: Model-driven autoscaling for microservices,” in 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), 2019, pp. 1994–2004.
[7] A. Kwan, J. Wong, H.-A. Jacobsen, and V. Muthusamy, “HyScale: Hybrid and network scaling of dockerized microservices in cloud data centres,” in 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), 2019, pp. 80–90.
[8] A. F. Baarzi and G. Kesidis, “SHOWAR: Right-sizing and efficient scheduling of microservices,” in Proceedings of the ACM Symposium on Cloud Computing, 2021, pp. 427–441.
[9] D. Balla, C. Simon, and M. Maliosz, “Adaptive scaling of Kubernetes pods,” in NOMS 2020—2020 IEEE/IFIP Network Operations and Management Symposium, 2020, pp. 1–5.
[10] B. Liu, R. Buyya, and A. N. Toosi, “A fuzzy-based auto-scaler for web applications in cloud computing environments,” in International Conference on Service-Oriented Computing, Springer, 2018, pp. 797–811.
[11] Y. Al-Dhuraibi, F. Paraiso, N. Djarallah, and P. Merle, “Elasticity in cloud computing: State of the art and research challenges,” IEEE Transactions on Services Computing, vol. 11, no. 2, pp. 430–447, 2017.
