Our full conference paper, “Augur: Pre-Execution Energy Prediction for Workflow Tasks in Heterogeneous Clusters” was accepted for publication in the proceedings of the “2026 IEEE International Conference on Cloud Computing (CLOUD), and will be presented in Sydney in July 2026.

In the paper, we proposed Augur, a novel method to predict the energy consumption of scientific workflow tasks prior to execution. By efficiently profiling both the available cluster infrastructure and the workflow at hand, Augur is capable of predicting the overall energy consumption with a median prediction error of 16.3% compared to Ichnos, an energy estimation method that uses fitted power models, and 18.2% compared to Intel RAPL measurements, as observed in our experimental evaluation on public and private cloud infrastructure. Augur outperforms two state-of-the-art methods in predicting both task runtime and total workflow energy, providing a robust foundation for energy-efficient and carbon-aware scientific data analysis.

The pre-print of the paper is available on arXiv, with the results repository also available on GitHub.