Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed training”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,171 records · Page 65
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency

Prompt and effective corrective actions in response to unexpected contingencies are crucial for improving power system resilience and preventing cascading blackouts. The optimal load shedding (OLS) accounting for network limits has the potential to address the diverse system-wide impacts of contingency scenarios as compared to traditional local schemes. However, due to the fast cascading propagation of initial contingencies, real-time OLS solutions are challenging to attain in large systems with high computation and communication needs. In this paper, we propose a decentralized design that leverages offline training of a neural network (NN) model for individual load centers to autonomously construct the OLS solutions from locally available measurements. Our learning-for-OLS approach can greatly reduce the computation and communication needs during online emergency responses, thus preventing the cascading propagation of contingencies for enhanced power grid resilience. Numerical studies on both the IEEE 118-bus system and a synthetic Texas 2000-bus system have demonstrated the efficiency and effectiveness of our scalable OLS learning design for timely power system emergency operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications

Deep neural networks have been successfully employed in an extensive variety of research areas, including solving partial differential equations. Despite its significant success, there are some challenges in effectively training DNN, such as avoiding overfitting in over-parameterized DNNs and accelerating the optimization in DNNs with pathological curvature. Here, we propose a Bayesian type sparse deep learning algorithm. The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network. The hierarchical Bayesian mixture will be trained using an adaptive empirical method. That is, one will alternatively sample from the posterior using preconditioned stochastic gradient Langevin Dynamics (PSGLD), and optimize the latent variables via stochastic approximation. The sparsity of the network is achieved while optimizing the hyperparameters with adaptive searching and penalizing. A popular SG-MCMC approach is Stochastic gradient Langevin dynamics (SGLD). However, considering the complex geometry in the model parameter space in nonconvex learning, updating parameters using a universal step size in each component as in SGLD may cause slow mixing. To address this issue, we apply a computationally manageable preconditioner in the updating rule, which provides a step-size parameter to adapt to local geometric properties. Moreover, by smoothly optimizing the hyperparameter in the preconditioning matrix, our proposed algorithm ensures a decreasing bias, which is introduced by ignoring the correction term in the preconditioned SGLD. According to the existing theoretical framework, we show that the proposed algorithm can asymptotically converge to the correct distribution with a controllable bias under mild conditions. Numerical tests are performed on both synthetic regression problems and learning solutions of elliptic PDE, which demonstrate the accuracy and efficiency of the present work.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Bi-Level Adaptive Storage Expansion Strategy for Microgrids Using Deep Reinforcement Learning

Battery energy storage (BES) is a versatile resource for the secure and economic operation of microgrids (MGs). Prevailing stochastic optimization-based approaches for BES expansion planning for MGs are computationally complicated. This work proposes a data-driven bi-level multi-period BES expansion planning framework to determine the siting, sizing, and timing of BES installations. The proposed planning framework unifies deep reinforcement learning (DRL) and linear programming, thereby decoupling the determinations for the integer and continuous decision variables in two time scales, respectively. In the upper level, a rainbow DRL agent with quantile regression is trained to provide dynamic planning policies to accommodate stochastic renewable energy resources (RESs), load, and battery price changes efficiently. Further, the lower level computes the optimal operation of MGs with frequency constraints to hedge the islanding contingency. The two levels communicate with one another by exchanging storage configuration and operating expenses in order to accomplish the shared goal of minimizing investment and operation costs. Comparative case studies on an MG are carried out to demonstrate the superiority of the proposed DRL-based solution to the mixed-integer linear programming counterpart on efficiency, scalability, and adaptability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Emerging Technologies for Privacy Preservation in Energy Systems

This study explores the intersection of digitalization and privacy within the energy sector, focusing on the emerging challenges and opportunities presented by integrating Distributed Energy Resources (DERs) and advanced metering infrastructure. The need for robust digital privacy measures has become crucial as the energy industry evolves towards a more decentralized, digitalized, and decarbonized future. This study delves into four cutting-edge privacy-preserving technologies—Homomorphic Encryption (HE), Secure Multiparty Computation (SMPC), Differential Privacy (DP), and Federated Learning (FL)—each offering unique solutions to safeguard consumer data by increasing digital connectivity and data exchange. Through a detailed examination of these methods, the study explains how each technology operates, its applications within the energy sector, and the specific privacy challenges it addresses. Homomorphic Encryption allows for secure computations on encrypted data, enabling data analysis without compromising privacy. Secure Multiparty Computation enables collaborative data analysis across different entities while protecting the confidentiality of the inputs. Differential Privacy introduces randomness into the assembled data set, preventing the identification of individual records in statistical databases. Lastly, Federated Learning offers a paradigm shift in data analysis, where machine learning models are trained at the edge, minimizing the centralization of sensitive data. The research underscores the significance of implementing these privacy-enhancing technologies to comply with strict data protection regulations, foster consumer trust, and enhance the security of the energy infrastructure. By providing a comprehensive overview of these methodologies and their practical implications for the energy sector, this study aims to contribute to the ongoing discourse on digital privacy, offering insights into how the energy industry can navigate the complexities of data privacy in the digital age.

Cali, Umit↗
DOE OSTI2025

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗
DOE OSTI2023

Radiometric Testing of Germicidal UV Products, Round 1: UV-C Towers and Whole-Room Luminaires (CALiPER Summary Report)

This summary report analyzes the independently tested performance of 13 germicidal ultraviolet (GUV) products purchased between February and July 2022. A companion full report (DOE 2023) provides additional information and discussion of the tested products, test methods, and results. The products were of three different types: • Seven portable, consumer-oriented GUV towers designed to be placed on the floor or a desk of an unoccupied room to disinfect air and surfaces. Five of these products used LED sources and two products had low-pressure mercury (LPM) sources. • One GUV whole-room luminaire designed to be installed on a ceiling to disinfect air when a room is occupied. This product had LED sources. • Five GUV troffer or high-bay style whole-room luminaires designed to be installed in or suspended from a ceiling to disinfect air and surfaces when a room is unoccupied. All five had LPM sources. Product testing covered radiometric and electrical performance for all 13 products as well as photobiological safety evaluation if product documentation included testable claims. Measurement results enable comparison between products and against manufacturer or vendor claims. Testing identified numerous issues related to the accuracy of claimed GUV product performance. Claims were often untestable, contradictory, ambiguous, or used incorrect units and/or terminology. When claims were testable, they often did not match test results. For example, three LED products that claimed to emit UV-C emitted only UV-A. Product claim issues were more common among consumer-oriented tower products, but all product types exhibited problems with accurate performance claims. The UV-C radiant efficiency (calculated as UV-C output power divided by electrical input power) of the products varied widely, even among similar products using the same source technologies. For example, the UV-C radiant efficiency of LPM products varied by greater than a factor of three for the same product type, indicating a large potential energy savings opportunity for products that are better designed for efficiency. LED products had orders-of-magnitude lower UV-C radiant efficiency than LPM products. This study also identified several testing challenges and limitations. Most significant among these is the capability to accurately test and report the performance of larger GUV products. Whereas integrating spheres are used to quickly measure total radiant flux (i.e., output power) and spectral distribution, goniometers are used to measure radiant intensity distribution (from which radiant flux can be calculated). Integrating spheres require a specialized and costly coating to test UV, and the testing laboratory for this round of products had only a 20-inch diameter hemisphere with this capability. The integrating sphere accommodated just 2 of the 10 UV-C emitting products. Goniometer testing had a different size limitation in that mirrors typically used to increase goniometer test distance to the far field reflect little to no UV. As a result, the study evaluated only 6 of 13 products in the far field. Electronic files of UV-C intensity data for the other 7 products, which would typically be imported into design software for designing GUV applications, may not be reliable for predicting irradiance at arbitrary far-field distances (IES 2022a; CIE 2020). Specifiers and buyers of GUV products need accurate performance claims and data to deploy GUV technology safely and effectively. This CALiPER GUV Round 1 report demonstrates the significant education and training manufacturers and vendors still require to accurately test and report the performance of their GUV products. Further industry standards and guidelines may address testing limitations and improve test methods, product performance, and the accuracy of performance claims.

42 ENGINEERING↗
DOE OSTI2023

Radiometric Testing of Germicidal UV Products, Round 1: UV-C Towers and Whole-Room Luminaires (CALiPER Full Report)

This report analyzes the independently tested performance of 13 germicidal ultraviolet (GUV) products purchased between February and July 2022. The products were of three different types: • Seven portable, consumer-oriented GUV towers designed to be placed on the floor or a desk of an unoccupied room to disinfect air and surfaces. Five of these products used LED sources and two products had low-pressure mercury (LPM) sources. • One GUV whole-room luminaire designed to be installed on a ceiling to disinfect air when a room is occupied. This product had LED sources. • Five GUV troffer or high-bay style whole-room luminaires designed to be installed in or suspended from a ceiling to disinfect air and surfaces when a room is unoccupied. All five had LPM sources. Product testing covered radiometric and electrical performance for all 13 products as well as photobiological safety evaluation if product documentation included testable claims. Measurement results enable comparison between products and against manufacturer or vendor claims. Testing identified numerous issues related to the accuracy of claimed GUV product performance. Claims were often untestable, contradictory, ambiguous, or used incorrect units and/or terminology. When claims were testable, they often did not match test results. For example, three LED products that claimed to emit UV-C emitted only UV-A. Product claim issues were more common among consumer-oriented tower products, but all product types exhibited problems with accurate performance claims. The UV-C radiant efficiency (calculated as UV-C output power divided by electrical input power) of the products varied widely, even among similar products using the same source technologies. For example, the UV-C radiant efficiency of LPM products varied by greater than a factor of three for the same product type, indicating a large potential energy savings opportunity for products that are better designed for efficiency. LED products had orders-of-magnitude lower UV-C radiant efficiency than LPM products. This study also identified several testing challenges and limitations. Most significant among these is the capability to accurately test and report the performance of larger GUV products. Whereas integrating spheres are used to quickly measure total radiant flux (i.e., output power) and spectral distribution, goniometers are used to measure radiant intensity distribution (from which radiant flux can be calculated). Integrating spheres require a specialized and costly coating to test UV, and the testing laboratory for this round of products had only a 20-inch diameter hemisphere with this capability. The integrating sphere accommodated just 2 of the 10 UV-C emitting products. Goniometer testing had a different size limitation in that mirrors typically used to increase goniometer test distance to the far field reflect little to no UV. As a result, the study evaluated only 6 of 13 products in the far field. Electronic files of UV-C intensity data for the other 7 products, which would typically be imported into design software for designing GUV applications, may not be reliable for predicting irradiance at arbitrary far-field distances (IES 2022a; CIE 2020). Specifiers and buyers of GUV products need accurate performance claims and data to deploy GUV technology safely and effectively. This CALiPER GUV Round 1 report demonstrates the significant education and training manufacturers and vendors still require to accurately test and report the performance of their GUV products. Further industry standards and guidelines may address testing limitations and improve test methods, product performance, and the accuracy of performance claims.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

A PSCAD Library Component Featuring a Reduced-Order IBR Model for EMT-Based Fault Studies

This paper presents a fully implemented inverter reduce-order-model (ROM) in an EMT simulation (PSCAD) library component for direct user utilization in protection studies. The developed inverter ROM has the following features: Equivalent to a full IBR inverter model with positive- and negative-sequence current formulation and representation A python script is developed to fully automate this process, including training data generation, ROM parameter training, updating parameters, and model verification and validation. With this PSCAD ROM library component, protection engineers can utilize a trustworthy, accurate ROM for protection studies in an easy-to-use and streamlined manner.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Physics-Based Machine Learning Methods for U-235 Forensics Signatures

Signatures of low-intensity U-235 sources have been recently studied by utilizing a variety of machine learning (ML) classifiers using features derived from gamma spectral measurements collectedunder structured campaigns. Several ML classifiers, such as ensemble of tress and classification trees, revealed misleadingly-optimistic training error due to over-fitting, and furthermore,their performance is not directly relatable to the physical properties due to their data-driven, opaque designs. We present a regression-based ML method that first estimates the inverse distanceto the source and then utilizes a threshold to infer its presence, by representing the background as a source located at an infinite distance. For the inverse distance estimation, we study the ensembleof trees and Gaussian process regression methods, and a hyper parameter auto-tuning and selection method that employs five regression estimators. These methods avoid the over-fittingobserved in several ML classifiers, while providing the classification error nearly comparable to them based on independent test data. Their error is directly related to estimates of the inversephysical distance to source, and the precision of error determines the seperability property that determines the false alarm and missed detection rates. The property of monotonic decrease of thesource strength with increasing detector distance combined with Poisson distribution of measurements is utilized to analytically validate these methods by deriving the generalization equations ofunderlying regression methods.

Rao, Nageswara↗
DOE OSTI2024

PDF DECODER ANALYSIS CODE

SF-24-038"PDFdecoder", as a new application to explore parametrizations of parton distribution functions (PDFs) of the proton or other hadrons. The PDFs are fundamental quantities in particle physics which are necessary inputs to precise theoretical predictions for experiments at the Large Hadron Collider (LHC) and other facilities. As such, understanding how the PDFs are parametrized and associated uncertainties is a pressing need. The specific problem PDFdecoder confronts is the need of having a tractable and interpretably machine-learning (ML) framework to parametrize the PDFs and their uncertainties so as to understand how a given preferred parametrization is obtained. This problem has not been significantly addressed in the current literature. While other groups have used ML-based approaches to parametrize PDFs in the form of feed-forward neural networks, the question of tractability has not been explored in a PDF context. Our solution makes significant progress in this problem by using an array of encoder-decoder (essentially, autoencoder) architectures with varying constraints to the intermediate latent spaces based on interpretable physics. As a consequence, the trained models can be used as generative networks to produce interpretable predictions for the PDFs in a way that can be refined and studied further.

Hobbs, Timothy↗
DOE OSTI2026

Evaluation of a Reduced-Order Model for IBR Fault Response Representation via OEM Blackbox Models

This paper presents a fully implemented inverter reduced-order-model (ROM) in an EMT simulation (PSCAD) library component for direct user utilization in protection studies. The developed inverter ROM has the following features: Equivalent to a full inverter-based resource (IBR) inverter model with positive- and negative-sequence current formulation and representation. A Python script is developed to fully automate this process, including training data generation, ROM parameter training, updating parameters, and model verification and validation. The ROM is validated using both IEEE 2800-compliant and non-compliant OEM modes in a real-world system, building confidence of its usability by protection engineers.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

The GGCMI Phase 2 emulators: global gridded crop model responses to changes in CO 2 , temperature, water, and nitrogen (version 1.0)

Statistical emulation allows combining advantageous features of statistical and process-based crop models for understanding the effects of future climate changes on crop yields. We describe here the development of emulators for nine process-based crop models and five crops using output from the Global Gridded Model Intercomparison Project (GGCMI) Phase 2. The GGCMI Phase 2 experiment is designed with the explicit goal of producing a structured training dataset for emulator development that samples across four dimensions relevant to crop yields: atmospheric carbon dioxide (CO2) concentrations, temperature, water supply, and nitrogen inputs (CTWN). Simulations are run under two different adaptation assumptions: that growing seasons shorten in warmer climates, and that cultivar choice allows growing seasons to remain fixed. The dataset allows emulating the climatological-mean yield response of all models with a simple polynomial in mean growing-season values. Climatological-mean yields are a central metric in climate change impact analysis; we show here that they can be captured without relying on interannual variations. In general, emulation errors are negligible relative to differences across crop models or even across climate model scenarios; errors become significant only in some marginal lands where crops are not currently grown. We demonstrate that the resulting GGCMI emulators can reproduce yields under realistic future climate simulations, even though the GGCMI Phase 2 dataset is constructed with uniform CTWN offsets, suggesting that the effects of changes in temperature and precipitation distributions are small relative to those of changing means. The resulting emulators therefore capture relevant crop model responses in a lightweight, computationally tractable form, providing a tool that can facilitate model comparison, diagnosis of interacting factors affecting yields, and integrated assessment of climate impacts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Physics-Based Machine Learning Methods for U-235 Forensics Signatures

Signatures of low-intensity U-235 sources have been recently studied by utilizing a variety of machine learning (ML) classifiers using features derived from gamma spectral measurements collected under structured campaigns. Several ML classifiers, such as ensemble of tress and classification trees, revealed misleadingly-optimistic training error due to over-fitting, and furthermore, their performance is not directly relatable to the physical properties due to their data-driven, opaque designs. We present a regression-based ML method that first estimates the inverse distance to the source and then utilizes a threshold to infer its presence, by representing the background as a source located at an infinite distance. For the inverse distance estimation, we study the ensemble of trees and Gaussian process regression methods, and a hyper parameter auto-tuning and selection method that employs five regression estimators. These methods avoid the over-fitting observed in several ML classifiers, while providing the classification error nearly comparable to them based on independent test data. Their error is directly related to estimates of the inverse physical distance to source, and the precision of error determines the seperability property that determines the false alarm and missed detection rates. The property of monotonic decrease of the source strength with increasing detector distance combined with Poisson distribution of measurements is utilized to analytically validate these methods by deriving the generalization equations of underlying regression methods.

Rao, Nageswara↗
DOE OSTI2026

Digital Twin User Guide for Chelan County Public Utility District

This user manual offers a comprehensive guide for developing a Digital twin (DT) of a Kaplan turbine at Chelan County Public Utility District (Chelan PUD) using neural networks. As variable renewable generation expands, hydropower units must operate with optimal efficiency and stability. For Kaplan machines, this flexibility is achieved through coordinated control of guide vane (wicket gates) opening and runner blade pitch, which amplifies the plant’s inherent nonlinear behavior and challenges traditional physics-only modeling. The efficiency of the Kaplan turbine varies with different combinations of the guide vans (wicket gate) opening and the blade angle. Each guide van opening and blade angle has a corresponding highest efficiency point, forming a cam relationship that represents the optimal combination.The discharge of a hydraulic turbine is controlled by the opening angle of the guide vans. Therefore, for each value of head, there is a certain guide van opening and blade angle that corresponds to the highest efficiency. For a given head, different combinations of the guide van opening and blade angle have different efficiencies. Therefore, coordinate cam curves are used to describe the relationship between the wicket gate opening and blade angle with different water head. To address these challenges, the manual details a data-driven modeling and learning workflow centered on structured neural networks. The approach is designed to forecast critical operational variables—discharge flow, net head, penstock (or scroll-case) pressure, and generator electrical outputs—by leveraging real-time inputs such as the generator power control setpoint, exciter field current and field voltage, together with hydromechanical commands (e.g., gate position and, when available, runner blade-pitch angle). The neural models are trained and validated on operational data from a Kaplan unit operated by Chelan PUD, demonstrating that the structured NN architecture can learn the coupled gate–blade–electrical dynamics. The result is a robust DT that improves situational awareness and supports data-informed decision-making for Chelan PUD’s Kaplan turbine operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings

The U.S. power grid is transforming to become smarter, cleaner, and more effi- cient. This is leading to the addition of significant distributed variable renew- able generation. Due to the variable nature of renewable generation, the short- and long-term supply-demand imbalances are less predictable, and conventional approaches to mitigating the imbalance will not be efficient or cost-effective. To address this challenge, transactive control technologies have been proposed which balance energy generation and consumption with market activity and in- frastructural limitations. Transactive control requires the ability of individual end-use loads to express flexibility as a function of a transactive signal (e.g., price). Empirical gray- and black-box models have been widely used to express flexibility, and although these approaches are generally easy to construct and simple to use, they do not capture the non-linear behavior that some end-use loads represent . Machine learning approaches have been proposed to address this limitation. Although deep learning approaches for forecasting end-use loads have been explored, certain aspects of the application of deep models to load forecasting are not well understood. These aspects include how much training data is required, and how models should be structured and trained. To that end, this work explores how to approach applying deep recurrent neural networks to short-term electrical load forecasting with a case study of four commercial office buildings. We identify data requirements for training accurate models of whole building electricity use conditioned on outdoor temperature, provide insight into model hyperparameter sensitivity, and demonstrate how readily models can be generalized to unseen buildings.

Skomski, Elliott↗
DOE OSTI2023

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Towards a Workforce Roadmap for Distributed Wind: Phase 1 - Identifying Needs and Barriers

Despite recent policy, research efforts, and resources available for utility-scale and offshore wind workforce development, the distributed wind (DW) industry has yet to make similar advances to address its workforce challenges. This report initiates the phased development of a DW workforce roadmap to provide a foundation for roadmap development. Phase 1, contained in this report, uses desk-based research on clean energy workforce approaches and a DW interested-party survey to discuss needs and barriers hindering the workforce from expanding. Findings are summarized into goals and solutions for Phase 2 of roadmap development, which identifies actors responsible for implementing solutions identified in Phase 1. Phase 1 results suggest that the sector's small size and limited growth motivate the short-term need for skilled workers or candidates with well-rounded and multifaceted abilities. Long-term expansion plans must diversify positions while capitalizing on existing utility-scale wind and offshore workforce efforts, as well as other renewable sector best practices where possible. The findings in this report can advance workforce development in the DW sector by aligning interested industry parties around common goals to address challenges. Training providers, installers, operators, manufacturers, federal agencies, national laboratories, academic partners, and labor unions can utilize the findings to help promote sustainable growth of the DW sector.

17 WIND ENERGY↗
DOE OSTI2025

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 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.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗