The Vattenfall R&D section for Data Science & AI apply advanced analytics to support the mission of fossil free living within one generation.
Vattenfall own and operate a large portfolio of wind farms and trade power on electricity markets. A significant cost is associated with “imbalance costs”. These are costs the system operator charges on producers if they deviate from their production plan. In certain periods imbalance costs can be very high. Predict the size and magnitude of these imbalance costs in advance, which would enable steps to be taken to minimize costs.
Large imbalance prices are driven by a mixture of predictable and unpredictable factors. Predictable factors include weather conditions, while unpredictable factors include things like power station and cable faults. This project would look at a time series of imbalance prices and use clustering and feature selection methods to distinguish between predictable and unpredictable events. If time allowed, a predictive model could then be tested on the subset of events thought to be predictable.
The goal of this thesis is to develop a technique for classifying power imbalances into weather dependent (potentially predictable) and non-weather dependent events.
Scope of the thesis (30HP)
We would like the student to:
1. Brief literature review
2. Collect power imbalance and weather data for target region
3. Exploratory analysis of data
4. Shortlist of techniques to apply
5. Application of techniques, analysis
6. Write up of results
What else do I need to know?
- This master thesis is done with Vattenfall R&D.
- The location for this work is flexible, but the team is mostly situated at Vattenfall R&D in Solna, Stockholm
You are a computer science or engineering student with knowledge of data science including clustering and feature selection algorithms. You are proficient in Python, and can work collaboratively using jupyter notebooks.
Swedish is not required but we appreciate if you intend on learning it during your thesis.
CV, cover letter, and grades are to be submitted in the application.
The interview process will be ongoing, as soon as relevant applicants are identified.
Deadline for application: 2020-12-06.
Do not hesitate to contact us for any questions: