Data efficiency assessment of generative adversarial networks in energy applications
This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meani...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | Energy and AI |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546825000333 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850274495725568000 |
|---|---|
| author | Umme Mahbuba Nabila Linyu Lin Xingang Zhao William L. Gurecky Pradeep Ramuhalli Majdi I. Radaideh |
| author_facet | Umme Mahbuba Nabila Linyu Lin Xingang Zhao William L. Gurecky Pradeep Ramuhalli Majdi I. Radaideh |
| author_sort | Umme Mahbuba Nabila |
| collection | DOAJ |
| description | This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performance when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications. |
| format | Article |
| id | doaj-art-e1aefc4818d94311a788419a48c79a1b |
| institution | OA Journals |
| issn | 2666-5468 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy and AI |
| spelling | doaj-art-e1aefc4818d94311a788419a48c79a1b2025-08-20T01:51:08ZengElsevierEnergy and AI2666-54682025-05-012010050110.1016/j.egyai.2025.100501Data efficiency assessment of generative adversarial networks in energy applicationsUmme Mahbuba Nabila0Linyu Lin1Xingang Zhao2William L. Gurecky3Pradeep Ramuhalli4Majdi I. Radaideh5Department of Nuclear Engineering and Radiological Sciences, University of Michigan, Ann Arbor, MI 48109, United States; Corresponding authors.Nuclear Science & Technology Division, Idaho National Laboratory Idaho Falls, ID 83415, United StatesDepartment of Nuclear Engineering, University of Tennessee, Knoxville, TN 37996, United StatesNuclear Energy and Fuel Cycle Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United StatesNuclear Energy and Fuel Cycle Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United StatesDepartment of Nuclear Engineering and Radiological Sciences, University of Michigan, Ann Arbor, MI 48109, United States; Corresponding authors.This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performance when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications.http://www.sciencedirect.com/science/article/pii/S2666546825000333Generative AIGenerative adversarial networksCritical heat fluxData augmentationPower grid energy forecasting |
| spellingShingle | Umme Mahbuba Nabila Linyu Lin Xingang Zhao William L. Gurecky Pradeep Ramuhalli Majdi I. Radaideh Data efficiency assessment of generative adversarial networks in energy applications Energy and AI Generative AI Generative adversarial networks Critical heat flux Data augmentation Power grid energy forecasting |
| title | Data efficiency assessment of generative adversarial networks in energy applications |
| title_full | Data efficiency assessment of generative adversarial networks in energy applications |
| title_fullStr | Data efficiency assessment of generative adversarial networks in energy applications |
| title_full_unstemmed | Data efficiency assessment of generative adversarial networks in energy applications |
| title_short | Data efficiency assessment of generative adversarial networks in energy applications |
| title_sort | data efficiency assessment of generative adversarial networks in energy applications |
| topic | Generative AI Generative adversarial networks Critical heat flux Data augmentation Power grid energy forecasting |
| url | http://www.sciencedirect.com/science/article/pii/S2666546825000333 |
| work_keys_str_mv | AT ummemahbubanabila dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications AT linyulin dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications AT xingangzhao dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications AT williamlgurecky dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications AT pradeepramuhalli dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications AT majdiiradaideh dataefficiencyassessmentofgenerativeadversarialnetworksinenergyapplications |