TY  - JOUR
T1  - Design of a Storage Service Operation Model for Cloud Service Cost Reduction
AU  - Park, Sun-chul 
AU  - Kim, Young-han 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.10.1568
KW  - Cloud Cost Optimizing
KW  - Cloud Storage Model
KW  - FinOps
KW  - RNN
KW  - LSTM
AB  - As cloud adoption proliferates and operational costs increase, interest in Finance and DevOps(FinOps) for cost management is growing. Existing studies have focused on reducing storage costs through techniques such as remote relocation and compression, but simple optimization is limited as data and inter-dependencies increase. This study proposes a hierarchical storage deployment model that uses the services of a single cloud service provider(CSP) optimized for a 3-tier system consistring of WEB, WAS, and DB components. This model shows 56% annual cost reduction compared to a single model approach. Recurrent Neural Network (RNN)-based Long Short-Term Memory (LSTM) machine learning predicts budget overruns with an error rate of 18%. This study supports cost reduction and effective FinOps in cloud operations.