Using AI to automatically analyze workload patterns and suggest optimal VM/container sizes, avoiding overprovisioning

Author(s)	Hema Vamsi Nikhil Katakam
Country	United States
Abstract	In cloud computing, organizations often allocate resources conservatively to guarantee application performance under peak load conditions. However, this practice results in persistent over-provisioning, wasted cost, and increased carbon footprint. This paper proposes an AI-driven resource right-sizing framework that leverages workload telemetry, predictive analytics, and feedback-based optimization to automatically determine optimal configurations for virtual machines (VMs) and containers. Using long short-term memory (LSTM) neural networks, the system forecasts resource demand and dynamically recommends suitable compute, memory, and I/O configurations. The proposed model demonstrates substantial cost savings (30–40%) and improved utilization stability without compromising service-level agreements (SLAs).
Keywords	right-sizing, cloud computing, virtual machine sizing, container sizing, workload prediction, machine learning, resource optimization, cost efficiency, autoscaling.
Field	Engineering
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-11-23
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9537
Short DOI	https://doi.org/hbb8gc

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology