Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186997,
        author = {Atharva V. Aher and Akshada B. Dinde and Amit S. Chaudhary and Vaishnavi V. Darekar},
        title = {An AI-Powered Predictive Cloud Resource Manager Using Prometheus-Based Workload Telemetry},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4216-4221},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186997},
        abstract = {With the introduction of cloud computing, there has been an intense revolution in the digital infrastructure space by offering the on-demand and scalable computing resources. Conventional fixed or deterministic resource allocation policies, on the other hand, often lead to either over-allocation or under-utilization and thus trigger a decrease in performance or unnecessary expenditures.
This paper presents a framework based on AI-powered Cloud Resource Allocator and Manager, also known as the proposed framework, that uses the models of Machine Learning (ML) and Artificial Intelligence (AI) to predict workload fluctuations, identify anomalies, and automatically coordinate the decisions on cloud scaling.
The framework uses time-series forecasting models, including Long Short-Term Memory (LSTM) [1] and eXtreme Gradient Boosting (XGBoost) [2] models with the support of anomaly refinement methods to achieve an effective balance between costs and performance [3].
Assessment based on simulated Amazon Web Services (AWS) EC2 and Prometheus monitoring datasets indicate that the proposed model can be used to effect efficient adaptive scaling, better mitigation of anomalies, and better cost utilisation [4].
Empirical evidence suggests that the AI-based cloud resource management can significantly increase elasticity, reliability, and cost-effectiveness compared to the traditional allocation methods. [5],[6].},
        keywords = {Artificial Intelligence, Cloud Computing, Machine Learning, Predictive Scaling, Resource Optimization, Anomaly Detection.},
        month = {November},
        }