Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.12129 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909293457965056 |
|---|---|
| author | Zhang, Zecheng |
| author_facet | Zhang, Zecheng |
| contents | Grid startup, an integral component of the power system, holds strategic importance for ensuring the reliability and efficiency of the electrical grid. However, current methodologies for in-depth analysis and precise prediction of grid startup scenarios are inadequate. To address these challenges, we propose a novel method based on the Transformer-LSTM-PSO model. This model uniquely combines the Transformer's self-attention mechanism, LSTM's temporal modeling capabilities, and the parameter tuning features of the particle swarm optimization algorithm. It is designed to more effectively capture the complex temporal relationships in grid startup schemes. Our experiments demonstrate significant improvements, with our model achieving lower RMSE and MAE values across multiple datasets compared to existing benchmarks, particularly in the NYISO Electric Market dataset where the RMSE was reduced by approximately 15% and the MAE by 20% compared to conventional models. Our main contribution is the development of a Transformer-LSTM-PSO model that significantly enhances the accuracy and efficiency of smart grid startup predictions. The application of the Transformer-LSTM-PSO model represents a significant advancement in smart grid predictive analytics, concurrently fostering the development of more reliable and intelligent grid management systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12129 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Analysis of Time Series Data for Smart Grid Startup Strategies: A Transformer-LSTM-PSO Model Approach Zhang, Zecheng Machine Learning Artificial Intelligence Systems and Control Grid startup, an integral component of the power system, holds strategic importance for ensuring the reliability and efficiency of the electrical grid. However, current methodologies for in-depth analysis and precise prediction of grid startup scenarios are inadequate. To address these challenges, we propose a novel method based on the Transformer-LSTM-PSO model. This model uniquely combines the Transformer's self-attention mechanism, LSTM's temporal modeling capabilities, and the parameter tuning features of the particle swarm optimization algorithm. It is designed to more effectively capture the complex temporal relationships in grid startup schemes. Our experiments demonstrate significant improvements, with our model achieving lower RMSE and MAE values across multiple datasets compared to existing benchmarks, particularly in the NYISO Electric Market dataset where the RMSE was reduced by approximately 15% and the MAE by 20% compared to conventional models. Our main contribution is the development of a Transformer-LSTM-PSO model that significantly enhances the accuracy and efficiency of smart grid startup predictions. The application of the Transformer-LSTM-PSO model represents a significant advancement in smart grid predictive analytics, concurrently fostering the development of more reliable and intelligent grid management systems. |
| title | Deep Analysis of Time Series Data for Smart Grid Startup Strategies: A Transformer-LSTM-PSO Model Approach |
| topic | Machine Learning Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2408.12129 |