Fine-Tuning Pre-trained Large Time Series Models for Prediction of Wind Turbine SCADA Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929609429221376 |
|---|---|
| author | Fan, Yuwei Song, Tao Feng, Chenlong Song, Keyu Liu, Chao Jiang, Dongxiang |
| author_facet | Fan, Yuwei Song, Tao Feng, Chenlong Song, Keyu Liu, Chao Jiang, Dongxiang |
| contents | The remarkable achievements of large models in the fields of natural language processing (NLP) and computer vision (CV) have sparked interest in their application to time series forecasting within industrial contexts. This paper explores the application of a pre-trained large time series model, Timer, which was initially trained on a wide range of time series data from multiple domains, in the prediction of Supervisory Control and Data Acquisition (SCADA) data collected from wind turbines. The model was fine-tuned on SCADA datasets sourced from two wind farms, which exhibited differing characteristics, and its accuracy was subsequently evaluated. Additionally, the impact of data volume was studied to evaluate the few-shot ability of the Timer. Finally, an application study on one-turbine fine-tuning for whole-plant prediction was implemented where both few-shot and cross-turbine generalization capacity is required. The results reveal that the pre-trained large model does not consistently outperform other baseline models in terms of prediction accuracy whenever the data is abundant or not, but demonstrates superior performance in the application study. This result underscores the distinctive advantages of the pre-trained large time series model in facilitating swift deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00403 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Pre-trained Large Time Series Models for Prediction of Wind Turbine SCADA Data Fan, Yuwei Song, Tao Feng, Chenlong Song, Keyu Liu, Chao Jiang, Dongxiang Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science The remarkable achievements of large models in the fields of natural language processing (NLP) and computer vision (CV) have sparked interest in their application to time series forecasting within industrial contexts. This paper explores the application of a pre-trained large time series model, Timer, which was initially trained on a wide range of time series data from multiple domains, in the prediction of Supervisory Control and Data Acquisition (SCADA) data collected from wind turbines. The model was fine-tuned on SCADA datasets sourced from two wind farms, which exhibited differing characteristics, and its accuracy was subsequently evaluated. Additionally, the impact of data volume was studied to evaluate the few-shot ability of the Timer. Finally, an application study on one-turbine fine-tuning for whole-plant prediction was implemented where both few-shot and cross-turbine generalization capacity is required. The results reveal that the pre-trained large model does not consistently outperform other baseline models in terms of prediction accuracy whenever the data is abundant or not, but demonstrates superior performance in the application study. This result underscores the distinctive advantages of the pre-trained large time series model in facilitating swift deployment. |
| title | Fine-Tuning Pre-trained Large Time Series Models for Prediction of Wind Turbine SCADA Data |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2412.00403 |