We are seeking motivated students with a passion for AI and energy systems to join the cutting-edge research project ADAPT on electricity market simulations with multi-agent reinforcement learning (RL). Your work will directly contribute to the ASSUME toolbox. 

Background:

The energy transition requires flexible demand to complement intermittent renewable generation. As the share of households with dynamic electricity prices increases and with dynamic network tariffs under discussion, prosumers equipped with PV systems, batteries, electric vehicles, and heat pumps adjust their power consumption based on those price signals. Individually optimized behavior of residential consumers may lead under scenarios with higher adoption to avalanche effects. To investigate future scenarios like this, RL-based demand shifting strategies allow analyzing price-making behavior and enable testing the effect of locational signals like dynamic network tariffs.

Objectives:

In this thesis, your contribution will focus on:

• Reviewing, designing and implementing RL strategies for flexible residential units in low-voltage grids.
• Extending ASSUME to enable simulations of distribution-level mechanisms, supporting investigations of regulatory frameworks such as §14a EnWG or dynamic network tariffs.

Requirements:

• Interest in energy-related topics
• Strong Python coding skills (depending on focus optional)
• Experience with reinforcement learning is a plus

Formalities:

The thesis can be written in German or English. Please apply with a short letter of motivation (max. ½ page), your CV, and a current grade transcript. Work can commence immediately.

Relevant introductory literature:

[1] Harder, Nick, Kim K. Miskiw, Manish Khanra, et al. 2025. “ASSUME: An agent-based simulation framework for exploring electricity market dynamics with reinforcement learning.” SoftwareX 30: 102176. https://doi.org/10.1016/j.softx.2025.102176.