International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI Cloud-Based Cost Optimization System: A Comprehensive Framework for Intelligent Resource Management |
|---|---|
| ABSTRACT | Keeping monthly cloud bills from spiraling out of control is an ongoing headache for engineering teams running workloads on public infrastructure. Launching a virtual server takes less than a minute in a web browser, yet remembering to turn off temporary test boxes, staging environments, or oversized virtual machines once a task wraps up is surprisingly difficult in day-to-day work. In this paper, we present a practical, automated Cloud Cost Optimization and Monitoring System built to track down, evaluate, and shut down idle compute instances before they quietly drain budgets. Instead of counting on rigid capacity plans or waiting around for end-of-month billing alerts, our tool pulls live telemetry straight from cloud-native APIs. Focusing on Amazon Web Services (AWS) Elastic Compute Cloud (EC2), we wrote a Python monitoring service around the Boto3 Software Development Kit (SDK) that checks CPU load, network traffic, and disk activity through AWS CloudWatch. Whenever a virtual machine stays under a chosen activity limit across a rolling time window, our script flags it as an abandoned or “zombie” server, stops it automatically, and sends a message to the operations crew. Because the tool watches real hardware usage rather than fixed clock schedules, developers no longer have to babysit the AWS web console by hand. We walk through the full architecture, cost equations, decision rules, and live experimental runs across ten EC2 instances to demonstrate how a compact Python daemon can enforce everyday FinOps discipline and trim wasted cloud spend. |
| AUTHOR | ABDUL RAHMAN, DARSHAN S, DIPAK SINGH, HITHASHRI T, AND LOKESH K Department of Information Science & Engineering, Raja Rajeswari College of Engineering, Bengaluru, India |
| VOLUME | 189 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1410042 |
| pdf/42_AI Cloud-Based Cost Optimization System A Comprehensive Framework for Intelligent Resource Management.pdf | |
| KEYWORDS | |
| References |
[1] Y. Suthari, N. Krishnan, Z. Thakker, V. Raju, S. Govindarajan, and S. K. Rao Katta, “Cost Optimization Techniques for Efficient Resource Allocation in Cloud Computing Environments,” in 2025 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICOICI), 2025, pp. 793–797. [2] R. Rakavi, K. D. Dharshini, A. S. Jovi, and R. Thenmozhi, “FinOps-based Cloud Cost Optimization Using Billing Analytics and Anomaly Detection in GCP,” in 2026 International Conference on Electronic Systems and Intelligent Computing (ICESIC), 2026, pp. 551–556. [3] P. Vij and A. Mishra, “AI-Driven Resource Optimization in Cloud and Edge Environments for Sustainable Ubiquitous Computing,” in 2025 5th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), 2025, pp. 458–462. [4] B. M. R. L. Ruben, S. J. J. E. D, A. T. T, S. V, and C. M, “AI-Driven Smart Parking System using IoT and Cloud-based Predictive Approach for Urban Mobility Optimization,” in 2025 5th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), 2025, pp. 1154–1159. [5] Amazon Web Services, “Boto3 Documentation – The AWS SDK for Python,” AWS API Reference, 2025. [Online]. Available: https://boto3.amazonaws.com/v1/documentation/api/latest/index.html [6] FinOps Foundation, “FinOps Framework: Cloud Financial Management Best Practices,” 2024. [Online]. Available: https://www.finops.org/framework/ [7] N. Mittal and V. D. Deepthi, “Automated Serverless Cost Monitoring Systems for Enterprise Cloud Environments,” IEEE Transactions on Services Computing, vol. 18, no. 4, pp. 312–325, 2025. [8] S. R. Jena, U. Srilakshmi, and S. M. Rafi, “Intelligent Green Energy Solutions: Optimizing Renewable Energy for Edge Cloud Computing,” in 2025 5th International Conference on Pervasive Computing and Social Networking (ICPCSN), 2025, pp. 112–118. [9] A. Patel and A. Sheth, “AI-Powered Metric Analysis: Safeguarding Cloud Budgets,” in IEEE Cloud Summit, 2025, pp. 45–51. [10] X. Yang and Y. Chen, “Research and Application of Boto3-Based Monitoring Technology for Cloud Waste Prevention,” IEEE Access, vol. 13, pp. 40561–40570, 2025. [11] R. Mehta and S. Kulkarni, “CostGuard: Python-Based Cloud State Detection System for Developer Environments,” IEEE Access, vol. 14, pp. 11200–11215, 2026. [12] A. Verma and K. Srinivas, “SecureCloud: Intelligent Infrastructure Management Using Boto3,” IEEE Transactions on Dependable and Secure Computing, vol. 23, no. 2, pp. 150–162, 2026. [13] H. Kumar and R. Singh, “Intelligent Cloud Resource Provisioning and Cost Optimization Using AWS,” IEEE Access, vol. 14, pp. 88910–88925, 2026. [14] M. Armbrust et al., “A view of cloud computing,” Communications of the ACM, vol. 53, no. 4, pp. 50–58, Apr. 2010. [15] AWS Architecture Center, “AWS Well-Architected Framework: Cost Optimization Pillar,” Amazon Web Services, Whitepaper, 2023. |