Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.08082 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914110399053824 |
|---|---|
| author | Cai, Yuting Liu, Shaohuai Tian, Chao Xie, Le |
| author_facet | Cai, Yuting Liu, Shaohuai Tian, Chao Xie, Le |
| contents | Generative artificial intelligence (AI) models in smart grids have advanced significantly in recent years due to their ability to generate large amounts of synthetic data, which would otherwise be difficult to obtain in the real world due to confidentiality constraints. A key challenge in utilizing such synthetic data is how to assess the data quality produced from such generative models. Traditional Euclidean distance-based metrics only reflect pair-wise relations between two individual samples, and could fail in evaluating quality differences between groups of synthetic datasets. In this work, we propose a novel metric based on the Fréchet Distance (FD) estimated between two datasets in a learned feature space. The proposed method evaluates the quality of generation from a distributional perspective. Empirical results demonstrate the superiority of the proposed metric across timescales and models, enhancing the reliability of data-driven decision-making in smart grid operations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fréchet Power-Scenario Distance: A Metric for Evaluating Generative AI Models across Multiple Time-Scales in Smart Grids Cai, Yuting Liu, Shaohuai Tian, Chao Xie, Le Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Signal Processing Generative artificial intelligence (AI) models in smart grids have advanced significantly in recent years due to their ability to generate large amounts of synthetic data, which would otherwise be difficult to obtain in the real world due to confidentiality constraints. A key challenge in utilizing such synthetic data is how to assess the data quality produced from such generative models. Traditional Euclidean distance-based metrics only reflect pair-wise relations between two individual samples, and could fail in evaluating quality differences between groups of synthetic datasets. In this work, we propose a novel metric based on the Fréchet Distance (FD) estimated between two datasets in a learned feature space. The proposed method evaluates the quality of generation from a distributional perspective. Empirical results demonstrate the superiority of the proposed metric across timescales and models, enhancing the reliability of data-driven decision-making in smart grid operations. |
| title | Fréchet Power-Scenario Distance: A Metric for Evaluating Generative AI Models across Multiple Time-Scales in Smart Grids |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Signal Processing |
| url | https://arxiv.org/abs/2505.08082 |