Machine Learning for Energy Analysis

The Focus Group “Machine Learning for Energy Analysis” comprises as principal investigators Rudolf Diesel Industry Fellow Dr. Sani Nassif  (Radyalis)  and his host Prof. Dr.-Ing. Ulf Schlichtmann (TUM Department of Electrical and Computer Engineering).

Integrated circuits (ICs) are the key enablers for all of the smart devices we use in everyday life. The IC powering a modern smartphone has billions of components and represents the combined effort of hundreds of engineers. A key metric for ICs is energy efficiency, since that determines battery life, and managing energy consumption requires accurate models of energy as a function of usage. Portions of IC design are often acquired from external sources to save on development time, and this makes it more challenging to create energy models for those portions. Our research aims to apply advanced machine learning techniques to improve energy models. We leverage known aspects of these energy models to develop guided machine learning techniques for creating accurate and predictive models. This problem is not specific to smartphones or battery-operated devices; large data centers also consume lots of energy and can also benefit from these ideas.

TUM-IAS funded Doctoral Candidate:
Philipp Fengler, Electronic Design Automation