Optimizing IT FinOps and Sustainability through Unsupervised Workload Characterization


  • Xi Yang IBM Research
  • Rohan R. Arora IBM Research
  • Saurabh Jha IBM Research
  • Chandra Narayanaswami IBM Research
  • Cheuk Lam IBM Software
  • Jerrold Leichter IBM Software
  • Yu Deng IBM Research
  • Daby M. Sow IBM Research




Data Mining , Pattern recognition , Machine Learning , Track: Emerging Applications


The widespread adoption of public and hybrid clouds, along with elastic resources and various automation tools for dynamic deployment, has accelerated the rapid provisioning of compute resources as needed. Despite these advancements, numerous resources persist unnecessarily due to factors such as poor digital hygiene, risk aversion, or the absence of effective tools, resulting in substantial costs and energy consumption. Existing threshold-based techniques prove inadequate in effectively addressing this challenge. To address this issue, we propose an unsupervised machine learning framework to automatically identify resources that can be de-provisioned completely or summoned on a schedule. Application of this approach to enterprise data has yielded promising initial results, facilitating the segregation of productive workloads with recurring demands from non-productive ones.



How to Cite

Yang, X., Arora, R. R., Jha, S., Narayanaswami, C., Lam, C., Leichter, J., Deng, Y., & Sow, D. M. (2024). Optimizing IT FinOps and Sustainability through Unsupervised Workload Characterization. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 22990-22996. https://doi.org/10.1609/aaai.v38i21.30340