The DTU CEE Summer School 2019 “Data-Driven Analytics and Optimization for Energy Systems” was organized by the ELMA group from June 16 to June 21, 2019, and sponsored by by EES-UETP, Mosek ApS and RTE France.

With 60 participants (from universities and enterprises, and from all over the world) and 8 world-renowned lecturers, this event was again larger than the previously organized school. The summer school focused in particular on optimal power flow, distributionally robust optimization, convex relaxations, data-driven methods, machine learning and their applications to power systems. Students received tutorials on the application and interpretation of these techniques, by means of hands-on exercises. In addition, students were asked to disseminate their research to other students through poster presentations and peer review. The overall evaluation from 55 participants was as follows: excellent: 45.4%, good: 47.3%, fair: 7.3%, poor: 0%.

Presentation slides – link to videos:
Jalal Kazempour | Introduction |
Munther Dahleh | A Marketplace for Data – Learning Linear Systems |
Dolores Romero Morales | The Opportunities and Challenges of Mathematical Optimization for Data Science |
Johanna Mathieu | Data‐Driven Distributionally Robust Optimization – Codes |
Andrea Simonetto | Data‐Driven Optimization in Power Systems – Hands-on Exercises |
Saverio Bolognani | Data‐Driven Control in Power Distribution Grids |
Pierre Pinson | Statistical and Machine Learning for Forecasting – Part 2 – Part 3 |
Spyros Chatzivasileiadis | Data‐Driven Methods for Power System Security Assessment – Exercises – Codes – Database |
Jalal Kazempour | Distributed Optimization – Part 2 – Part 3 – Part 4 – Exercises |
Michal Adamaszek | Mosek |
Reading Material
Johanna Mathieu – Paper 1, Paper 2
Saverio Bolognani – Paper
Munther Dahleh – Paper 1, Paper 2, Lecture Video
Jalal Kazempour – Notes 1, Notes 2, Notes 3
Pierre Pinson – Book Chapter
Spyros Chatzivasileiadis – Paper 1, Paper 2, Paper 3, Paper 4, Paper 5, Paper 6, Tutorial
Andrea Simonetto – Paper