Home / Current Issue / Paper 1722726
AI-Driven Capacity Forecasting and Resource Optimization in Enterprise Cloud Infrastructure in Saudi Arabia
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
Abstract
Enterprise cloud environments generate continuous streams of utilization data, yet many organizations still plan capacity through static thresholds, periodic reports, and reactive expansion. This review examines how artificial intelligence (AI) can convert infrastructure telemetry into forward-looking capacity forecasts and resource decisions for enterprise cloud platforms, with specific attention to Saudi Arabia. A structured review of recent peer-reviewed literature (2020-2025) and official Saudi digital-transformation sources was undertaken, covering workload prediction, deep learning, reinforcement learning, autoscaling, resource allocation, energy efficiency, and AIOps. The literature indicates that recurrent, attention-based, hybrid, and uncertainty-aware forecasting models can improve anticipation of CPU, memory, storage, and workload demand, while reinforcement-learning approaches can translate predictions into scaling, placement, and scheduling actions. However, accuracy alone is insufficient: useful enterprise systems require data quality controls, application context, explainability, service-level safeguards, and human-governed automation. For Saudi organizations, these capabilities align with Cloud First and Vision 2030 objectives by supporting resilient digital services, efficient infrastructure investment, and scalable modernization. The review proposes a layered implementation framework combining observability, predictive models, policy engines, and controlled automation, and identifies research priorities for multi-resource forecasting, uncertainty quantification, cross-domain transfer, and sovereign-cloud operations.
Keywords
artificial intelligence; capacity forecasting; cloud computing; resource optimization; AIOps; autoscaling; Saudi Arabia; Vision 2030
How to cite this paper
@article{1722726,
author = {Muneer Shaik},
title = {AI-Driven Capacity Forecasting and Resource Optimization in Enterprise Cloud Infrastructure in Saudi Arabia},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {3704-3713},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1722726.pdf},
abstract = {Enterprise cloud environments generate continuous streams of utilization data, yet many organizations still plan capacity through static thresholds, periodic reports, and reactive expansion. This review examines how artificial intelligence (AI) can convert infrastructure telemetry into forward-looking capacity forecasts and resource decisions for enterprise cloud platforms, with specific attention to Saudi Arabia. A structured review of recent peer-reviewed literature (2020-2025) and official Saudi digital-transformation sources was undertaken, covering workload prediction, deep learning, reinforcement learning, autoscaling, resource allocation, energy efficiency, and AIOps. The literature indicates that recurrent, attention-based, hybrid, and uncertainty-aware forecasting models can improve anticipation of CPU, memory, storage, and workload demand, while reinforcement-learning approaches can translate predictions into scaling, placement, and scheduling actions. However, accuracy alone is insufficient: useful enterprise systems require data quality controls, application context, explainability, service-level safeguards, and human-governed automation. For Saudi organizations, these capabilities align with Cloud First and Vision 2030 objectives by supporting resilient digital services, efficient infrastructure investment, and scalable modernization. The review proposes a layered implementation framework combining observability, predictive models, policy engines, and controlled automation, and identifies research priorities for multi-resource forecasting, uncertainty quantification, cross-domain transfer, and sovereign-cloud operations.},
keywords = {artificial intelligence; capacity forecasting; cloud computing; resource optimization; AIOps; autoscaling; Saudi Arabia; Vision 2030},
month = {August},
}