TY - JOUR AU - Zhang, Yuxuan AU - Li, David AU - Zhang, Sophia PY - 2023/03/09 Y2 - 2024/03/28 TI - Cost Optimization - A Recommendation Analysis of Azure Workloads JF - Journal of Student Research JA - J Stud Res VL - 11 IS - 4 SE - DO - 10.47611/jsr.v11i4.1775 UR - https://www.jsr.org/index.php/path/article/view/1775 SP - AB - <p>In a rapidly modernizing world, cloud computing has emerged as an innovative and ground-breaking technology. It is a sector that is experiencing rapid growth, accelerated by the COVID-19 pandemic and remote work environment. Many businesses have started to make the transition from traditional storage systems to the cloud. However, the transition can be opaque and result in an excessive amount of spending on cloud resources. Additionally, these resources are often underutilized, further contributing to cloud waste. This paper seeks to address this problem by designing a comprehensive algorithm based on a detailed analysis of the Microsoft Azure 2019 virtual machine (VM) traces. We first analyzed the cost of approximately 2.7 million VMs and identified that many VMs are under utilized and over consume resources. Then, using a policy-oriented algorithm we constructed a list of VMs that were considered to be "wasteful". Finally, we implemented a recommendation algorithm to sort through this constructed list and recommend lower prices and options for users without interfering with the purpose and function of the VM. Our results show that if all users were to follow our recommendations, the potential cost reduction is over \$1.4 million. We conclude with a discussion of the implications of this research and make recommendations for future studies.</p> ER -