ISSN: 2582 - 9734
Saharsh Gera, Dr. Gulshan Kumar
CrossRef DOI URL : https://doi.org/10.31426/ijesti.2024.4.12.5001
The rapid expansion of cloud computing has intensified the need for intelligent and adaptive resource allocation mechanisms capable of handling highly dynamic workloads. Traditional reactive and rule-based strategies often lead to over-provisioning, under-provisioning, SLA violations, and increased operational costs. This study explores the integration of predictive analytics and machine learning techniques for dynamic resource allocation in cloud computing environments. Through time-series forecasting, deep learning models such as LSTM and Transformer, clustering algorithms, and reinforcement learning frameworks, cloud systems can anticipate workload fluctuations and proactively adjust resource provisioning..
2026
28
