Internship – End-of-Studies Research Project
Context & Motivation
Modern distributed storage infrastructures are made up of thousands of hard disk drives (HDDs) operating continuously. While compute and network energy costs are increasingly well understood, HDD/SSD power consumption under real-world workloads remains difficult to measure and predict accurately. Understanding and modeling this consumption is critical for:
To date, no robust, interpretable multi-parameter model exists that can accurately estimate disk energy consumption from observable parameters in a production environment. This internship aims to fill that gap.
Your Mission
As part of our R&D team, you will design, build, and validate a multi-parameter model for estimating HDD/SSD power consumption. Your work will include:
1. State of the Art
Review existing literature and open-source projects related to HDD/SSD power modeling, thermal behavior, and energy measurement in storage systems (including tools such as PowerAPI).
2. Physical Modeling
Develop a physics-based multi-parameter model of temperature and power draw, capturing relationships between:
3. Interpretable Machine Learning Model
Design a multi-parameter ML model (e.g., gradient boosting, linear regression with feature engineering) that is both accurate and interpretable — enabling engineers to understand which parameters drive consumption under different workload profiles.
Instrument real drives in a controlled laboratory environment and under
production-representative workloads to collect ground-truth measurements.
