EUVIMEDEUVIMED entdecken
Crossref

Optimizing Resource Allocation in Cloud Computing Using Machine Learning Techniques

Subhrajyoti Chakraborty, Shameemul Haque

International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)

DOI: 10.25258/ijddt.16.44s.84 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von Subhrajyoti Chakraborty und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud computing has become a major way of providing scalable, on-demand, and distributed computing resources to enterprises, research institutions and public-sector institutions. Cloud infrastructure's rapid growth has brought many challenges in managing resources resulting from many variables such as variable workloads, heterogeneous virtualized environments and dynamic user demands. Classical approaches to resource provisioning and heuristic scheduling methods can result in suboptimal resource utilization, higher operational costs, contention for resources, growing latency and excessive energy consumption. Machine learning techniques provide a computational model that can be used for workload analysis, workload prediction and adaptive resource management in real-time. The research discussed in this paper centers on the effectiveness of machine learning-based optimization models in allocation of resources in cloud environment. Supervised learning, reinforcement learning and deep learning methods have been compared in the context of virtual machine allocation, task scheduling, energy optimisation, load balancing for clouds. An experimental framework was created for comparison with the simulated cloud workloads created in CloudSim and the analytical tools created in Python. Performance indicators used were the resource utilization, task completion time, throughput, energy consumption, SLA violation rate and computational overhead. Experimental results revealed that energy efficiency of reinforcement learning based allocation is 28% more efficient than conventional heuristic methods and 93.4% is the resource utilization efficiency. The accuracy of workload prediction using the deep neural network models was 95.2%, alleviating over-provisioning and under-utilization. The study demonstrates the benefits of adaptive cloud management, reducing operational costs and service reliability, with the use of machine learning for optimising cloud management application. The study offers an integrated analytical solution for intelligent cloud orchestration and helps support future evolution of autonomous cloud infrastructure management

Zitieren

APA

Chakraborty, S., & Haque, S. (2026). Optimizing Resource Allocation in Cloud Computing Using Machine Learning Techniques. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.84

Vancouver

Chakraborty S, Haque S. Optimizing Resource Allocation in Cloud Computing Using Machine Learning Techniques. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.84

BibTeX
@article{Chakraborty2026,
  author = {Chakraborty, Subhrajyoti and Haque, Shameemul},
  title = {Optimizing Resource Allocation in Cloud Computing Using Machine Learning Techniques},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {44s},
  doi = {10.25258/ijddt.16.44s.84}
}
Kostenlos starten →