Background

The integration of electric vehicles (EVs) into household energy systems challenges grid stability. Grid operators must balance between dynamic electricity tariffs (as incentives for households) and regulatory measures such as §14a EnWG, which allows curtailment and control of household loads.

Reinforcement learning (RL) offers a promising approach to explore these socio-technical scenarios. Yet, RL environments are often inaccessible to non-experts. From a Management Information Systems (MIS) perspective, there is a research opportunity in designing a layperson-oriented RL tool that supports grid operators in evaluating household charging reactions.

This thesis is framed as a Design Science Research (DSR) study, where the objective is to build and evaluate a rudimentary MVP that provides a usable RL environment for grid operator decision support.

Methodology (DSR Process)

Problem Identification & Objectives

Understand grid operators’ needs in evaluating tariff and §14a scenarios.

Identify barriers for laypersons in applying reinforcement learning.

Design & Development

Construct an RL environment where:

The environment represents households behind a substation.

The action space reflects tariff signals and §14a enforcement options.

Provide a simple user interface so non-experts can define scenarios and observe outcomes.

Demonstration

Apply the MVP in example scenarios to illustrate its use.

Evaluation

Conduct qualitative expert interviews with grid operators and/or energy system specialists.

Assess usability, relevance, and adequacy of the design.

Communication

Document design principles and MIS contributions.

Expected Contribution

Academic: Generates design knowledge on how reinforcement learning tools can be made usable for laypersons, extending DSR in MIS.

Practical: Provides a first MVP for grid operators to explore household charging reactions to dynamic tariffs under regulatory constraints.

Disclaimer 

The Master's thesis is meant for you to show that you are able to work scientifically. Please keep that in mind. We expect you to apply scientific methods and to submit a scientifically sound result. Our role is to provide you with everything you need to succeed at that. We expect that you create a piece of work that is acceptable for a scientific conference, and we aim to submit it to one. A motivated student who works consistently on the thesis throughout the designated period can expect a very good grade. Details on the process and the format that we use to support you in succeeding with your thesis can be found here: https://cloud.uol.de/s/BHCRrqZ5NM4SfTg

Please submit your grade record, a CV, and three sentences explaining why you applied for this topic in any application. We will not respond to requests with incomplete application documents.