SpotLake AWS Spot Instance Dataset (2025 Sample)

Description

SpotLake is a spot instance dataset archive service operated by the DDPS Lab at Hanyang University. This dataset is a one-year sample of its AWS data: every 10-minute snapshot of 2025. For each instance type and Availability Zone on the AWS spot market, a snapshot records the Spot Placement Score, the Spot Instance Advisor interruption frequency band, the spot price, the on-demand price, and the resulting savings. All values come from public AWS APIs and data, and the collection method is documented. It supports research on spot availability, pricing dynamics, and capacity-aware scheduling.

Update Frequency

Not updated. Static sample covering calendar year 2025.

License

Creative Commons Attribution 4.0 International (CC BY 4.0)

Documentation

https://github.com/ddps-lab/spotlake-open-data

Managed By

DDPS Lab, Hanyang University

See all datasets managed by DDPS Lab, Hanyang University.

Contact

spotlake@hanyang.ac.kr

How to Cite

SpotLake AWS Spot Instance Dataset (2025 Sample) was accessed on DATE from https://registry.opendata.aws/spotlake. S. Lee, J. Hwang, and K. Lee, "SpotLake: Diverse Spot Instance Dataset Archive Service," IEEE International Symposium on Workload Characterization (IISWC), 2022. https://doi.org/10.1109/IISWC55918.2022.00029

Usage Examples

Tutorials

• Get To Know A Dataset: SpotLake AWS Spot Instance Dataset (2025 Sample) by DDPS Lab, Hanyang University
  
  Amazon S3

Tools & Applications

• SpotLake web service by DDPS Lab, Hanyang University
  

Publications

• Making Cloud Spot Instance Interruption Events Visible by Kim K., Lee K.
  
• Multi-Node Spot Instances Availability Score Collection System by Cheon S., Kim K., Kim K., Song M., Lee K.
  
• Public Spot Instance Dataset Archive Service by Kim K., Park S., Hwang J., Lee H., Kang S., Lee K.
  
• SpotLake: Diverse Spot Instance Dataset Archive Service by Lee S., Hwang J., Lee K.