Hilverts, Timo (2026) Optimal Electricity Tariff Design under Probabilistic Customer Choice. Master's Thesis / Essay, Applied Mathematics.
|
Text
MasterThesisTimoHilvertss4146158FinalVersion.pdf Download (3MB) | Preview |
Abstract
This thesis develops an optimization-based framework for electricity tariff design with heterogeneous customer segments. The focus lies on determining flat and time-of-use pricing under probabilistic customer choice, modeled through an entropy-regularized logit formulation and evaluated on synthetic data generated using the LoadProfileGenerator (LPG). The resulting nonconvex optimization problem is solved using a High-Resolution Langevin Algorithm, which is derived and implemented in combination with simulated annealing and demonstrates strong performance compared to gradient-based methods. The baseline results show how consumption heterogeneity drives customer segmentation and revenue, while extensions such as fixed tariff components, empirical segment weights, reservation bills and disutilities, consumption shifting, green preferences, and explicit cost structures lead to more realistic and flexible pricing strategies. The framework provides consistent insights into optimal tariff design and highlights the importance of behavioral modeling and algorithmic choice, offering a practical foundation for data-driven pricing decisions in electricity markets.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Peypouquet, J.G. and Grzegorczyk, M.A. |
| Degree programme: | Applied Mathematics |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 30 Apr 2026 14:50 |
| Last Modified: | 30 Apr 2026 14:50 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/37302 |
Actions (login required)
 |
View Item |