Thesis subject
Data-driven discovery of manipulations in electricity markets (MSc)
Europe's energy sector is going through unprecedented transformations represented by the increasing share of variable Renewable Energy Sources (vRES), such as wind and solar power plants, and electrification. Indeed, the world of energy as we used to know it will not ever be the same again. However, the integration of vRES is accompanied with technical and economic challenges due to their intermittency, non-dispatchability and unpredictability. Electricity markets are essential instruments to guarantee the balance between energy supply and demand in a technical feasible and economically efficient manner. In electricity markets, trading by market participants takes place in multi-settlement markets, allowing to trade energy products with different temporal granularities. This is needed to satisfy diverse stakeholders requirements and accommodate the uncertainty in electricity consumption and vRES generation, which is likely to increase in response to climate policies.
Short description
Despite the importance of electricity markets and the significance of the challenges they are facing, the trading behaviour of their market participants is poorly understood. The objective of this thesis project is focused on using data-driven techniques to achieve two main goals: i) analyse and understand the trading behaviour of participants in electricity markets, such as trading patterns of different market participants, electricity prices development, market correlation with external events, and ii) identify market manipulations and anomalies that can hinder market efficiency. A comprehensive data-driven understanding of participants’ trading behaviour and the different types of market manipulations in electricity markets will play a key role in improving the functionality of electricity markets under the energy transition.
This project will focus on the Dutch electricity market. Students doing their MSc thesis on this topic will have the opportunity to be in contact with leading scientists and research institutes of energy markets, data science and AI as part of an international research project. Being part of this project would also provide the opportunity of a research stay at one of the EU leading institute in electricity markets.
Objectives
- Review articles and white papers on market manipulations in electricity markets.
- Distinguish between different manipulations in electricity markets and identify what spatio-temporal data and AI models are needed to identify/discover each.
- Build a data-driven model, supported by Artificial Intelligence (AI), to discover one type of market manipulations.
Tasks
The work in this MSc thesis entails:
- To collect full-text articles or PDFs from primary studies and literature reviews or white papers on market manipulations in electricity markets.
- To assess the challenges and data-driven solutions available in the literature for discovering different types of market manipulations in electricity markets.
- To develop and implement a data-driven AI model for identifying one type of market manipulations.
- To evaluate the effectiveness of the model in the Dutch electricity market using actual data.
Literature:
- Bichler, M., Buhl, H. U., Knörr, J., Maldonado, F., Schott, P., Waldherr, S., & Weibelzahl, M. (2022). Electricity Markets in a Time of Change: A Call to Arms for Business Research. Schmalenbach Journal of Business Research, 74(1), 77–102. https://doi.org/10.1007/s41471-021-00126-4
- Valitov, Niyaz, and Andreas Maier. "Asymmetric information in the German intraday electricity market." Energy Economics 89 (2020): 104785. https://doi.org/10.1016/j.eneco.2020.104785
- ACER Guidance Note 1/2018. On The Application of Article 5 of Remit on The Prohibition of Market Manipulation. 1–23. Link
- ACER Guidance Note 1/2019. On The Application of Article 5 of Remit on The Prohibition of Market Manipulation. 1–21. Link
Requirements:
- Courses: Programming in Python (INF-22306), Big Data (INF-33806), Statistics (MAT), or Machine Learning (FTE-35306)
- Required skills/knowledge: basic data analytics/statistics/ machine learning and willingness to learn new data-driven tools, interest about electricity markets and sustainable energy transition
Key words: Data Analytics, Machine Learning, Statistics, Sustainable Energy Transition, Electricity Markets, Solar Photovoltaics
Contact person(s)
Tarek Alskaif (tarek.alskaif@wur.nl)