Skip to content

Autonomous Cloud & FinOps

Workload-aware optimization, learned control, warehouse sizing, and operational safeguards for cloud data warehouses and data infrastructure.

Can cloud data infrastructure continuously balance performance and cost?

This research treats cloud configuration as a continuous systems problem. Telemetry informs models and control decisions while performance objectives, cost constraints, real-time feedback, and protective backoff remain explicit.

Methods and questions

  • workload modeling
  • learned control
  • automated tuning
  • performance and cost optimization

Projects

Publications

Making Data Clouds Smarter at Keebo: Automated Warehouse Optimization using Data Learning

Barzan Mozafari, Radu Alexandru Burcuta, Alan Cabrera, Andrei Constantin, Derek Francis, David Grömling, Alekh Jindal, Maciej Konkolowicz, Valentin Marian Spac, Yongjoo Park, Russell Razo Carranzo, Nicholas Richardson, Abhishek Roy, Aayushi Srivastava, Isha Tarte, Brian Westphal, Chi Zhang

SIGMOD Demo 2023 · ACM SIGMOD International Conference on Management of Data — Demonstration

Paper ↗Project ↗
Cite
@inproceedings{8ede012b-09b5-4196-bc20-95033ee64807,
  title = {Making Data Clouds Smarter at Keebo: Automated Warehouse Optimization using Data Learning},
  author = {Barzan Mozafari and Radu Alexandru Burcuta and Alan Cabrera and Andrei Constantin and Derek Francis and David Grömling and Alekh Jindal and Maciej Konkolowicz and Valentin Marian Spac and Yongjoo Park and Russell Razo Carranzo and Nicholas Richardson and Abhishek Roy and Aayushi Srivastava and Isha Tarte and Brian Westphal and Chi Zhang},
  booktitle = {ACM SIGMOD International Conference on Management of Data — Demonstration},
  year = {2023},
  doi = {10.1145/3555041.3589681}
}