search

atlarge-research / wta-tools

The tools and scripts used to generate and manage the traces in the Workflow Trace Archive.
Apache License 2.0
7 stars 4 forks source link

Look into process mining #6

Open lfdversluis opened 3 years ago

lfdversluis commented 3 years ago

The article "Measuring data-centre workflows complexity through process mining: the Google cluster case" uses process mining to identify executed workflows in Google's 2011 cluster trace. It might be interesting to apply this (kind of) work to traces to obtain workflows and host these?

lfdversluis commented 3 years ago

https://www.usenix.org/publications/login/fall2020/uta Interesting trace to characterize from SURF

lfdversluis commented 3 years ago

Google's 2019 trace might be interesting to investigate too (although it needs to work with BigQuery, or at least the data extraction part)

lfdversluis commented 3 years ago

https://github.com/Azure/AzurePublicDataset might be interesting to see if we can piece together workflows from azure functions

lfdversluis commented 3 years ago

"Scientific Workflow Mining in Clouds" is another article on process mining to obtain workflows from distributed systems