Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909724316794880 |
|---|---|
| author | Beichter, Maximilian Friederich, Nils Pinter, Janik Werling, Dorina Phipps, Kaleb Beichter, Sebastian Neumann, Oliver Mikut, Ralf Hagenmeyer, Veit Heidrich, Benedikt |
| author_facet | Beichter, Maximilian Friederich, Nils Pinter, Janik Werling, Dorina Phipps, Kaleb Beichter, Sebastian Neumann, Oliver Mikut, Ralf Hagenmeyer, Veit Heidrich, Benedikt |
| contents | Time series foundation models provide a universal solution for generating forecasts to support optimization problems in energy systems. Those foundation models are typically trained in a prediction-focused manner to maximize forecast quality. In contrast, decision-focused learning directly improves the resulting value of the forecast in downstream optimization rather than merely maximizing forecasting quality. The practical integration of forecast values into forecasting models is challenging, particularly when addressing complex applications with diverse instances, such as buildings. This becomes even more complicated when instances possess specific characteristics that require instance-specific, tailored predictions to increase the forecast value. To tackle this challenge, we use decision-focused fine-tuning within time series foundation models to offer a scalable and efficient solution for decision-focused learning applied to the dispatchable feeder optimization problem. To obtain more robust predictions for scarce building data, we use Moirai as a state-of-the-art foundation model, which offers robust and generalized results with few-shot parameter-efficient fine-tuning. Comparing the decision-focused fine-tuned Moirai with a state-of-the-art classical prediction-focused fine-tuning Morai, we observe an improvement of 9.45% in average total daily costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01936 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization Beichter, Maximilian Friederich, Nils Pinter, Janik Werling, Dorina Phipps, Kaleb Beichter, Sebastian Neumann, Oliver Mikut, Ralf Hagenmeyer, Veit Heidrich, Benedikt Machine Learning Artificial Intelligence Time series foundation models provide a universal solution for generating forecasts to support optimization problems in energy systems. Those foundation models are typically trained in a prediction-focused manner to maximize forecast quality. In contrast, decision-focused learning directly improves the resulting value of the forecast in downstream optimization rather than merely maximizing forecasting quality. The practical integration of forecast values into forecasting models is challenging, particularly when addressing complex applications with diverse instances, such as buildings. This becomes even more complicated when instances possess specific characteristics that require instance-specific, tailored predictions to increase the forecast value. To tackle this challenge, we use decision-focused fine-tuning within time series foundation models to offer a scalable and efficient solution for decision-focused learning applied to the dispatchable feeder optimization problem. To obtain more robust predictions for scarce building data, we use Moirai as a state-of-the-art foundation model, which offers robust and generalized results with few-shot parameter-efficient fine-tuning. Comparing the decision-focused fine-tuned Moirai with a state-of-the-art classical prediction-focused fine-tuning Morai, we observe an improvement of 9.45% in average total daily costs. |
| title | Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01936 |