International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Artificial Intelligence-Enabled Resource Allocation Strategies in Cloud Environments |
|---|---|
| ABSTRACT | Cloud computing has revolutionized the way computing resources are consumed by enabling dynamic, on-demand resource provisioning. However, with increasing demand, heterogeneity of workloads, and stringent Quality of Service (QoS) requirements, efficient resource allocation remains a critical challenge. Artificial Intelligence (AI) technologies, particularly machine learning (ML), deep learning (DL), and reinforcement learning (RL), have emerged as promising solutions for addressing the complexity and dynamism in cloud environments. This paper explores AI-enabled strategies for resource allocation in cloud computing, focusing on how intelligent algorithms can improve system performance, reduce operational costs, and ensure SLA compliance. We present a comprehensive review of recent advancements in AI-driven resource allocation, including predictive models for demand forecasting, intelligent scheduling, dynamic provisioning, and workload balancing. The paper also classifies existing approaches based on AI techniques and evaluates their effectiveness across various performance metrics such as latency, energy efficiency, and throughput. Through a simulated environment using popular datasets and cloud simulators, we demonstrate the superiority of reinforcement learning-based allocation mechanisms over traditional heuristic approaches. Results show significant improvements in resource utilization and response times under fluctuating workloads. The study concludes that AI techniques provide scalable, adaptive, and context-aware solutions to the resource allocation problem. However, challenges remain in terms of model interpretability, generalization across platforms, and real-time implementation. Future research should focus on hybrid AI models, federated learning, and ethical AI to build more transparent and efficient cloud systems. |
| AUTHOR | JOHN AGUNWAMBA PAULINUS |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311077 |
| pdf/77_Artificial Intelligence-Enabled Resource Allocation Strategies in Cloud Environments.pdf | |
| KEYWORDS |
