Work

Intelligent Cost Optimization in Cloud Migration Using Machine Learning

Year: 2026
Type: article
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.
Language: English
Open Access status: green
OpenAlex ID: W7236855397
FWCI:
Cites:
Cited by:
Related to: 10