System Architecture and Model Implementation for AI-Driven Resource Management in Large-Scale Distributed Operating Environments
Article Sidebar
Main Article Content
Abstract
This study presents an integrated AI-driven resource management framework designed to optimize performance, adaptability, and energy efficiency across cloud, edge, and hybrid distributed computing environments. The research evaluates the framework through three progressive simulation scenarios, each reflecting increasing levels of infrastructural complexity and workload heterogeneity. In Scenario 1, conducted within a large-scale cloud data center, the AI-based model demonstrated substantial improvements in throughput, response time, and energy consumption through its scalable and self-adaptive scheduling mechanisms. The system’s dynamic optimization capabilities provided a strong foundation for extending the methodology to decentralized environments. Scenario 2 examined the framework’s behavior within an edge computing cluster characterized by heterogeneous nodes, latency-sensitive applications, and continuous IoT data streams. The results confirmed the model’s ability to deliver low-latency, energy-efficient task scheduling and high service reliability by leveraging predictive analytics and real-time decision learning. In Scenario 3, a hybrid cloud–edge architecture was simulated to evaluate the end-to-end adaptability of the proposed system. The hybrid results revealed that the fusion of deep learning–based workload prediction, reinforcement learning control, and evolutionary optimization achieved superior performance over traditional heuristics. The framework consistently maintained low latency, high throughput, optimal resource utilization, and energy-aware operation across multi-tier infrastructures. Together, these findings establish the proposed AI-driven architecture as a robust and intelligent solution for next-generation distributed operating environments, enabling autonomous, sustainable, and scalable resource management across diverse computational ecosystems.
Article Details
References
Barroso, L. A., & Hölzle, U. (2013). The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines (2nd ed.). Morgan & Claypool.
Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A. F., & Buyya, R. (2011). CloudSim: A toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and Experience, 41(1), 23–50.
Chiang, M., & Zhang, T. (2016). Fog and IoT: An overview of research opportunities. IEEE Internet of Things Journal, 3(6), 854–864.
Fox, A., Griffith, R., Joseph, A. D., Katz, R., Konwinski, A., Lee, G., Patterson, D., Rabkin, A., & Stoica, I. (2009). Above the Clouds: A Berkeley View of Cloud Computing (Tech. Rep. UCB/EECS-2009-28). University of California, Berkeley.
Gulati, A., Shanmuganathan, G., Holler, A., Ahmad, I., & Waldspurger, C. A. (2012). Cloud-scale resource management: Challenges and techniques. In Proceedings of the USENIX HotCloud Workshop.
Hindle, A., Barr, E. T., Gabel, M., Su, Z., & Devanbu, P. (2012). On the naturalness of software. In Proceedings of the 34th International Conference on Software Engineering (ICSE) (pp. 837–847). IEEE.
Islam, S., Lee, K., Fazio, M., & Suliman, A. (2012). A survey on green computing: Tools, approaches, and trends. International Journal of Computer Applications, 9(12), 1–12.
Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016). Resource management with deep reinforcement learning. In Proceedings of the 15th ACM Workshop on Hot Topics in Networks (HotNets) (pp. 50–56).
Morabito, R., Cozzolino, V., Ding, A. Y., Beijar, N., & Ott, J. (2018). Consolidate IoT edge computing with lightweight virtualization. IEEE Network, 32(1), 102–111.
Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39.
Xu, X., Liu, Q., Zhang, Z., Dai, F., Wu, Y., & Wu, J. (2020). A deep reinforcement learning–based framework for resource management in hybrid cloud–edge environments. IEEE Transactions on Cloud Computing, 8(4), 1238–1251.