Internship

Internship: Fast and Robust Security Constrained AC Optimal Power Flow - Track machine learning Locatie Arnhem MCE Contracttype Tijdelijk Salaris € Contractvorm Stage Introductie At TenneT, you will have the opportunity to carry out your graduation research in an environment where you can make a real impact. As a student intern in System Operations & Market Development team, you will work on relevant and current challenges related to AC Optimal Power Flow (OPF) calculations. OPF calculations play an important role in facilitating efficient transport of electric power. In the simplest definition, OPF involves determining operating setpoints for controllable assets in the grid such as generators, shunts and transformers that lead to minimal operational costs while satisfying demand and operational constraints. As the electricity grid is predominantly based on Alternating Current (AC), the underlying physics of the grid is non-linear making the AC-OPF problem non-linear and possibly non-convex. Hence, solving the AC-OPF problem is non-trivial, computationally expensive and prone to divergence. Furthermore, when security constraints are imposed over time, solving the AC-OPF problem can become prohibitively slow. This stimulates the use of approximate methods that compromise on accuracy for speed. The project involves developing a fast and robust calculation framework for solving security constrained AC-OPF problems for the Dutch transmission grid along two tracks - mathematical optimization and machine learning. Jouw rol This graduation project is along the machine learning track where you will: • Review the current literature landscape on solving OPF problems using machine learning. • Train Graph Neural Networks (GNNs) to speed up security constrained AC-OPF calculations. • Build on an internally developed module that trains GNNs for performing AC power flow calculations. • Design a calculation framework that is fast and robust enough to be used close to real-time grid operation. • Investigate convergence problems. You will be supported by the ODINA team, where you will have plenty of room to work independently and collaborate with colleagues. Waar kom je terecht Operate is responsible for the end-to-end operation of the Dutch electricity grid and ensures security of supply, system stability, and market facilitation in the Netherlands and across Europe. Operate makes sure the lights stay on 24 hours a day, 365 days a year. Their goal is to provide our customers tomorrow with the same reliability they enjoy today. Jouw profiel & achtergrond Your profile • Currently enrolled in a master's program in one of the following or a related field: computing sciences, mathematics, machine learning, physics, engineering. • Good programming skills in Python, knowledge of libraries for deep learning is a plus. • Knowledge on power flow analysis or network calculations is helpful, but not a must. • Interest in the energy transition is a big plus. • Curious, eager to learn, and proactively seek contact when needed. • Enjoy working collaboratively and are open to feedback. Arbeidsvoorwaarden What do we offer you? • A monthly gross internship allowance of 500 euros based on a 40-hour work week • Travel and remote working allowance • Hybrid working: we enjoy working together at the office, but working from home is also possible • A laptop provided by TenneT for the duration of your internship The position may gets unpublished earlier, so don't hesitate to apply! Inge Klappers Ervaringen van stagiaires Nils Vorrink • Nils vond zijn stage bij LionLink Als afstudeerder werkte Nils mee aan een uniek offshoreproject. Zijn stage bracht hem dichter bij zijn droombaan. • Eva is trainee ruimtelijke ordening Voor Eva Franke (26) viel alles op z'n plek toen ze bij het spatial planning program van TenneT terechtkwam.. • Elise vond haar plek tussen techniek en strategie Het traineeship liet haar verschillende kanten van TenneT ontdekken. Nu werkt ze aan de energietoekomst van Nederland. Internship: Fast and Robust Security Constrained AC Optimal Power Flow - Track machine learning Arnhem MCE