End-to-end Energy Profiles of Data Analysis Workflows (B06)

• Subject Area: Security and Dependability, Operating-, Communication- and Distributed Systems ; Data Management, Data-Intensive Systems, Computer Science Methods in Business Informatics
• Term: since 2020
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 414984028

The execution of DAWs is driven by specifications of individual steps, their bindings to specific programs, their dependencies, and input data. However, users also have expectations on other properties such as the correctness. To ensure these properties up-front, proactive runtime monitoring of workflow executions is key. In Phase I, we (a) created an efficient monitoring infrastructure for DAWs, and (b) researched novel techniques for processing event streams that adapt automatically to the specific properties of complex and distributed workloads. In phase II, the project will shift its focus from monitoring functional properties to non-functional ones, which are equally important to human productivity. In particular, we will focus on the holistic management of end-to-end energy profiles and climate footprints across the entire hardware-software stack.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1404: FONDA - Foundations of Workflows for Large-Scale Scientific Data Analysis
• Applicant Institution: Humboldt-Universität zu Berlin
• Project Heads: Professor Dr. Matthias Böhm; Professor Dr. Lars Grunske, until 6/2024; Professor Dr. Tilmann Rabl