An AI-Driven Cloud Computing Framework for Predictive Resource Allocation, Workload Optimization, and Intelligent Service Management
Computer and Decision Making An International Journal · 03.11.2026
DOI: 10.1922/comdem.v3i6s.19039 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 03.11.2026. Verfasst von Dr. Amar Rajendra Mudiraj und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Efficient cloud-resource management is essential for maintaining service performance while controlling workload variability and operational cost. Artificial intelligence offers a predictive approach for improving scaling decisions in multi-cloud environments. This study aimed to assess cloud workload, utilization, and service-performance patterns and to compare machine-learning models for predicting resource-scaling decisions. A quantitative secondary-data design was used with 1,000 multi-cloud observations. Workload, infrastructure, service-performance, and cost variables were analysed. Temporal lag and rolling features were generated, and next-interval scaling decisions were predicted using Logistic Regression, Decision Tree, Random Forest, and XGBoost. Model performance was evaluated using accuracy, macro precision, macro recall, macro F1-score, balanced accuracy, and multiclass ROC-AUC. Resource utilization differed clearly across no-action, scale-up, and scale-down conditions. Scale-up states showed the highest CPU usage, memory usage, and utilization. Throughput was strongly positively associated with utilization, while latency showed strong negative relationships with both throughput and utilization. Random Forest achieved the highest overall accuracy, whereas XGBoost showed the strongest macro-level performance and was selected as the best model. Important predictors included cloud-provider category, lagged CPU usage, latency, disk I/O, and recent workload patterns. AI-driven temporal modelling showed practical potential for short-term cloud-resource prediction and intelligent service management.
Zitieren
APA
Mudiraj, D. A. R., Sidana, D. S., ., P. N., Babu, B. S., Shivane, S. R., & Dutta, S. (2026). An AI-Driven Cloud Computing Framework for Predictive Resource Allocation, Workload Optimization, and Intelligent Service Management. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v3i6s.19039
Vancouver
Mudiraj DAR, Sidana DS, . PN, Babu BS, Shivane SR, Dutta S. An AI-Driven Cloud Computing Framework for Predictive Resource Allocation, Workload Optimization, and Intelligent Service Management. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v3i6s.19039
BibTeX
@article{Mudiraj2026,
author = {Mudiraj, Dr. Amar Rajendra and Sidana, Dr. Sonal and ., P.V. Nageswararao and Babu, Bellam Surendra and Shivane, Santosh Ramdas and Dutta, Subhrajyoti},
title = {An AI-Driven Cloud Computing Framework for Predictive Resource Allocation, Workload Optimization, and Intelligent Service Management},
journal = {Computer and Decision Making An International Journal},
year = {2026},
doi = {10.1922/comdem.v3i6s.19039}
}
EUVIMED