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 see...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.展开更多
Let f∈C[-1,1]and R. (r≥1 ) be the reneralized Pal iner polation polynomials satisf ying the conditions Rn, where{xk} are the roots of n-th Jacobi polynomial Pn and are the roots of In this paper,we prove that Rn...Let f∈C[-1,1]and R. (r≥1 ) be the reneralized Pal iner polation polynomials satisf ying the conditions Rn, where{xk} are the roots of n-th Jacobi polynomial Pn and are the roots of In this paper,we prove that Rn holds uniformly on [0,1].展开更多
Key establishment is the basic step for the wireless sensor network （WSN） security. The polynomial based key predistribution scheme of Blom and Blundo et al. has been the basic ingredient for the key establishment f...Key establishment is the basic step for the wireless sensor network （WSN） security. The polynomial based key predistribution scheme of Blom and Blundo et al. has been the basic ingredient for the key establishment for WSNs. It is tempting to use many random and different instances of polynomial based key predistribution scheme for various parts of the WSN to enhance the efficiency of WSN key establishment protocols. This paper indicates that it is not secured in general to use many instances of Blom-Blundo et al. polynomial based key predistribution scheme in a WSN key establishment protocol. Thus the previously constructed group-based type WSN key predistribution schemes using polynomial based key predistribution scheme are insecure. We propose new generalized Bloin-Blundo et al. key predistribution schemes. These new generalized Blom-Blundo et al. key predistribution schemes can be used many times in one WSN key establishment protocol with only a small increase of cost. The application to group-based WSN key predistribution schemes is given.展开更多
This book comprehensively expounds the basic concepts of AIGC(Artificial Intelligence Generated Content),and helps readers deeply understand the application of AIGC in various scenarios through examples and operation ...This book comprehensively expounds the basic concepts of AIGC(Artificial Intelligence Generated Content),and helps readers deeply understand the application of AIGC in various scenarios through examples and operation guides.The book consists of seven chapters,including an overview and fundamentals of generative Al,natural language generation of creative content,image processing and generation,and so on.展开更多
基金supported through Idaho National Laboratory,United States’s Laboratory Directed Research and Development(LDRD)Program Award Number(24A1081-116FP)under Department of Energy Idaho Operations Office contract no.DE-AC07-05ID14517.
文摘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.
基金Supported by the Science Foundation of CSBTB the Natural Science Foundatioin of Zhejiang.
文摘Let f∈C[-1,1]and R. (r≥1 ) be the reneralized Pal iner polation polynomials satisf ying the conditions Rn, where{xk} are the roots of n-th Jacobi polynomial Pn and are the roots of In this paper,we prove that Rn holds uniformly on [0,1].
基金the NSFC Danish National Research Foundation and National Science Foundation of China Joint Grant (No. 11061130539)the National Natural Science Foundation of China (No. 61021004)
文摘Key establishment is the basic step for the wireless sensor network （WSN） security. The polynomial based key predistribution scheme of Blom and Blundo et al. has been the basic ingredient for the key establishment for WSNs. It is tempting to use many random and different instances of polynomial based key predistribution scheme for various parts of the WSN to enhance the efficiency of WSN key establishment protocols. This paper indicates that it is not secured in general to use many instances of Blom-Blundo et al. polynomial based key predistribution scheme in a WSN key establishment protocol. Thus the previously constructed group-based type WSN key predistribution schemes using polynomial based key predistribution scheme are insecure. We propose new generalized Bloin-Blundo et al. key predistribution schemes. These new generalized Blom-Blundo et al. key predistribution schemes can be used many times in one WSN key establishment protocol with only a small increase of cost. The application to group-based WSN key predistribution schemes is given.
文摘This book comprehensively expounds the basic concepts of AIGC(Artificial Intelligence Generated Content),and helps readers deeply understand the application of AIGC in various scenarios through examples and operation guides.The book consists of seven chapters,including an overview and fundamentals of generative Al,natural language generation of creative content,image processing and generation,and so on.
