Cloud Cost Optimization and Forecasting Using Machine Learning
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Cloud computing offers scalable and flexible infrastructure, but inefficient resource utilization often results in excessive and unpredictable operational costs. Organizations frequently over-provision resources or fail to identify idle services, leading to significant financial waste. This project presents a Cloud Cost Optimization and Forecasting System using machine learning techniques to analyze cloud usage data and reduce unnecessary expenditure. The proposed system uses a Random Forest regression model to predict future cloud costs based on CPU utilization, memory usage, storage, and network activity. Time-series forecasting techniques are applied to analyze cost trends, while resources are classified into optimized, underutilized, and idle categories. Actionable optimization recommendations such as downsizing, scheduling, and termination of idle resources are generated. An interactive dashboard visualizes cost insights, optimization potential, and savings. The system improves cost efficiency, supports proactive decision-making, and promotes sustainable cloud resource utilization
Fields of Study & Subjects
Cloud Computing and Resource Management
Energy Efficiency in Computing
Software System Performance and Reliability
Publication details
- Journal / source
- International Journal of Advanced Research in Science Communication and Technology
- Pages
- 298–298
- Publication date
- 30 March 2026
- Language
- EN