Intelligent Cost Optimization in Cloud Migration Using Machine Learning

Cloud migration gives organizations scalable computing without large upfront hardware investment, but it can also raise operational expenditure when resources are over-provisioned, workloads are poorly estimated, or pricing models are chosen carelessly. Existing practice often relies on static thresholds, manual capacity planning and periodic cost reviews, which struggle with workloads that change quickly or behave non-linearly. Earlier research has studied workload prediction, autoscaling, virtual-machine consolidation and cost-aware provisioning, but these topics are usually examined separately, and an accurate forecast does not by itself prove that cloud spending falls. To address this issue, this paper proposes a machine-learning framework that connects workload forecasting with a constrained decision layer. Telemetry such as CPU, memory, request rate, latency, storage activity, network traffic, instance count and billing data is used to predict future demand. A transparent Safe Cost Optimization Score (SCOS) then ranks candidate actions such as resizing, scaling, consolidation, scheduling, pricing-plan changes and decommissioning, while hard limits on latency, availability and operational risk keep recommendations safe. This research does not present new experimental findings. The studies discussed are described qualitatively from their published scope, and the proposed SCOS framework is a new concept that requires further testing and validation. The overall analysis suggests that forecasting accuracy is only one input to a good cost decision; cost, performance, reliability and governance must be evaluated together. The main contribution is a practical, reproducible framework for evaluating and improving cloud-cost decisions during and after migration. Rather than minimizing expenditure alone, the approach aims to deliver financially beneficial, explainable and operationally safe resource decisions.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24372110
Primary Topic
Cloud Computing and Resource Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Intelligent Cost Optimization in Cloud Migration Using Machine Learning

Prashant Chordiya, Pratik Jadhav, Vedant Chaudhari, Rohan Katkar et al.
Zenodo (CERN European Organization for Nuclear Research)
Cloud Computing and Resource Management
article

Intelligent Cost Optimization in Cloud Migration Using Machine Learning

Prashant Chordiya, Pratik Jadhav, Vedant Chaudhari, Rohan Katkar, Karan Bhongale
article en

Abstract

Cloud migration gives organizations scalable computing without large upfront hardware investment, but it can also raise operational expenditure when resources are over-provisioned, workloads are poorly estimated, or pricing models are chosen carelessly. Existing practice often relies on static thresholds, manual capacity planning and periodic cost reviews, which struggle with workloads that change quickly or behave non-linearly. Earlier research has studied workload prediction, autoscaling, virtual-machine consolidation and cost-aware provisioning, but these topics are usually examined separately, and an accurate forecast does not by itself prove that cloud spending falls. To address this issue, this paper proposes a machine-learning framework that connects workload forecasting with a constrained decision layer. Telemetry such as CPU, memory, request rate, latency, storage activity, network traffic, instance count and billing data is used to predict future demand. A transparent Safe Cost Optimization Score (SCOS) then ranks candidate actions such as resizing, scaling, consolidation, scheduling, pricing-plan changes and decommissioning, while hard limits on latency, availability and operational risk keep recommendations safe. This research does not present new experimental findings. The studies discussed are described qualitatively from their published scope, and the proposed SCOS framework is a new concept that requires further testing and validation. The overall analysis suggests that forecasting accuracy is only one input to a good cost decision; cost, performance, reliability and governance must be evaluated together. The main contribution is a practical, reproducible framework for evaluating and improving cloud-cost decisions during and after migration. Rather than minimizing expenditure alone, the approach aims to deliver financially beneficial, explainable and operationally safe resource decisions.

Zenodo (CERN European Organization for Nuclear Research)
Cloud Computing and Resource Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon