Search NASA⌕ Search

SEARCH · Search NASA

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 1,009 records · Page 56

Small Aircraft Transportation System Concept and Technologies

This paper summarizes both the vision and the early public-private collaborative research for the Small Aircraft Transportation System (SATS). The paper outlines an operational definition of SATS, describes how SATS conceptually differs from current air transportation capabilities, introduces four SATS operating capabilities, and explains the relation between the SATS operating capabilities and the potential for expanded air mobility. The SATS technology roadmap encompasses on-demand, widely distributed, point-to-point air mobility, through hired-pilot modes in the nearer-term, and through self-operated user modes in the farther-term. The nearer-term concept is based on aircraft and airspace technologies being developed to make the use of smaller, more widely distributed community reliever and general aviation airports and their runways more useful in more weather conditions, in commercial hired-pilot service modes. The farther-term vision is based on technical concepts that could be developed to simplify or automate many of the operational functions in the aircraft and the airspace for meeting future public transportation needs, in personally operated modes. NASA technology strategies form a roadmap between the nearer-term concept and the farther-term vision. This paper outlines a roadmap for scalable, on-demand, distributed air mobility technologies for vehicle and airspace systems. The audiences for the paper include General Aviation manufacturers, small aircraft transportation service providers, the flight training industry, airport and transportation authorities at the Federal, state and local levels, and organizations involved in planning for future National Airspace System advancements.

Small aircraft transportation system↗

Feature Acquisition with Imbalanced Training Data

This work considers cost-sensitive feature acquisition that attempts to classify a candidate datapoint from incomplete information. In this task, an agent acquires features of the datapoint using one or more costly diagnostic tests, and eventually ascribes a classification label. A cost function describes both the penalties for feature acquisition, as well as misclassification errors. A common solution is a Cost Sensitive Decision Tree (CSDT), a branching sequence of tests with features acquired at interior decision points and class assignment at the leaves. CSDT's can incorporate a wide range of diagnostic tests and can reflect arbitrary cost structures. They are particularly useful for online applications due to their low computational overhead. In this innovation, CSDT's are applied to cost-sensitive feature acquisition where the goal is to recognize very rare or unique phenomena in real time. Example applications from this domain include four areas. In stream processing, one seeks unique events in a real time data stream that is too large to store. In fault protection, a system must adapt quickly to react to anticipated errors by triggering repair activities or follow- up diagnostics. With real-time sensor networks, one seeks to classify unique, new events as they occur. With observational sciences, a new generation of instrumentation seeks unique events through online analysis of large observational datasets. This work presents a solution based on transfer learning principles that permits principled CSDT learning while exploiting any prior knowledge of the designer to correct both between-class and withinclass imbalance. Training examples are adaptively reweighted based on a decomposition of the data attributes. The result is a new, nonparametric representation that matches the anticipated attribute distribution for the target events.

Thompson, David R.↗

Tangible Solutions for Grid Operation Upgrade

Many countries worldwide are setting clean energy targets to decarbonize the energy sector and add higher wind and solar capacities. Given their distributed nature, variable renewable energy (VRE) assets can have unique grid integration considerations, and require grid operation practices to be modernized. When transitioning to higher renewable energy levels, many system operators configure a dedicated renewable energy desk to manage renewable energy resource operation in the system control center. Further, system operation planning is conducted with VRE and load forecasting to enable reliable real-time system operation. NREL has partnered with many system operators in the region to identify appropriate technology and grid modernization solutions. NREL and partners from system operators in the region will present on the challenges and some solutions that have been applied and share best practices such as energy management system upgrades, VRE forecasting framework, grid flexibility improvements, and staff training.

emerging economies↗

DSP Implementation of a Novel Recurrent Neural Network Controller into a TI Solar Microinverter

Single-phase grid-tied inverters are widely used to integrate small-scale renewable energy sources and distributed generations to the utility grid. A novel Recurrent Neural Network (RNN) current controller is introduced to solve the resonant problem associated with LCL based inverters. The well-trained RNN controller was validated through a Texas Instruments (TI) LCL filter based solar microinverter kit that contains a C2000 TI microcontroller. The inverter closed current loop test without the grid connection was conducted in a laboratory setup to verify the RNN contoller functionality. The laboratory waveform results verified that the RNN current controller produced the strong tracking of the measured inverter AC current to its reference value even at a low sampling frequency of 5KHz. The proposed RNN current controller also proved to perform better than the built-in three-pole-three-zero (3P3Z) current controller provided by TI and produce lower values of Total Harmonic Distortion (THD).

digital signal processor↗

A-Train Aerosol Observations Preliminary Comparisons with AeroCom Models and Pathways to Observationally Based All-Sky Estimates

We have developed a technique for combining CALIOP aerosol backscatter, MODIS spectral AOD (aerosol optical depth), and OMI AAOD (absorption aerosol optical depth) retrievals for the purpose of estimating full spectral sets of aerosol radiative properties, and ultimately for calculating the 3-D distribution of direct aerosol radiative forcing. We present results using one year of data collected in 2007 and show comparisons of the aerosol radiative property estimates to collocated AERONET retrievals. Use of the recently released MODIS Collection 6 data for aerosol optical depths derived with the dark target and deep blue algorithms has extended the coverage of the multi-sensor estimates towards higher latitudes. We compare the spatio-temporal distribution of our multi-sensor aerosol retrievals and calculations of seasonal clear-sky aerosol radiative forcing based on the aerosol retrievals to values derived from four models that participated in the latest AeroCom model intercomparison initiative. We find significant inter-model differences, in particular for the aerosol single scattering albedo, which can be evaluated using the multi-sensor A-Train retrievals. We discuss the major challenges that exist in extending our clear-sky results to all-sky conditions. On the basis of comparisons to suborbital measurements, we present some of the limitations of the MODIS and CALIOP retrievals in the presence of adjacent or underlying clouds. Strategies for meeting these challenges are discussed.

Aerosol↗

Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning

Recent alluvial sediments in riverbeds play a significant role in controlling hydrologic exchange flows (HEFs) in river systems. The alluvial layer is usually associated with strong heterogeneity in physical properties (e.g., permeability and hydraulic conductivity), which affects local HEFs and therefore biogeochemical processes. The spatial distribution of these physical properties needs to be determined to inform the numerical models used to reveal the realistic hydro-biogeochemical behaviors. Such information can be obtained based on the intrinsic link between sediment grain-size distribution and hydraulic properties where sediment texture information is available. However, grain-size measurements are usually spatially sparse and do not have adequate coverage and resolution, particularly for a relatively large domain such as the Hanford Reach of the Columbia River. In this paper, we adopted machine learning (ML) approaches for categorizing and mapping the spatial distributions of riverbed substrate grain size and filling in missing areas of substrate data using the ML models along the reach. Such ML models for substrate size mapping were trained at 13,372 locations using measured substrate sizes along with observed and simulated attributes, including bathymetric attributes (e.g., elevation, slope, and aspect ratio) from LIDAR and bathymetric surveys, and hydrodynamic properties (e.g., water depth, velocity, shear stress, and their statistical moments). An ensemble bagging-based ML technique, Random Forest, was adopted to identify the most influential factors as predictors to develop the predictive models with over-fitting issues addressed. The models were evaluated with respect to each individual substrate size class and the lumped group, and then used to generate the final substrate size maps covering all the grid cells in the numerical modeling domain.

54 ENVIRONMENTAL SCIENCES↗

Business Continuity, Cybersecurity, and Backup Control Center: Standards, References, and Recommendations (White Paper)

This Whitepaper provides an overview and synopsis of relevant standards for Control Center, Cyber Security and Continuity of Operations for electric power utilities. It also provides suggestions and recommendations for the outline of a cybersecurity plan and a business continuity plan, and suggests training and certification opportunities for both cybersecurity and business continuity.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We suggest a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118-and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118- and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

alternating direction method of multipliers↗

Visibility-enhanced model-free deep reinforcement learning algorithm for voltage control in realistic distribution systems using smart inverters

Increasing integration of distributed solar photovoltaic (PV) into distribution networks could result in adverse effects on grid operation. Traditional model-based control algorithms require accurate model information that is difficult to acquire and thus are challenging to implement in practice. Here, this paper proposes a surrogate model-enabled grid visibility scheme to empower deep reinforcement learning (DRL) approach for distribution network voltage regulation using PV inverters with minimal system knowledge. In contrast to existing DRL methods, this paper presents and corroborates the adverse impact of missing load information on DRL performance and, based on this finding, proposes a surrogate model methodology to impute load information utilizing observable data. Additionally, a multi-fidelity neural network is utilized to construct the DRL training environment, chosen for its efficient data utilization and enhanced robustness to data uncertainty. The feasibility and effectiveness of the proposed algorithm are assessed by considering DRL testing across varying degrees of observable load information and diverse training environments on a realistic power system.

14 SOLAR ENERGY↗

Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem

Three-dimensional target identification using scattering techniques requires high accuracy solutions and very fast computations for real-time predictions in some critical applications. We first train a deep neural operator (DeepONet) to solve wave propagation problems described by the Helmholtz equation in a domain without scatterers but at different wavenumbers and with a complex absorbing boundary condition. We then design two classes of fast meta-solvers by combining DeepONet with either relaxation methods, such as Jacobi and Gauss-Seidel, or with Krylov methods, such as GMRES and BiCGStab, using the trunk basis of DeepONet as a coarse-scale preconditioner. We leverage the spectral bias of neural networks to account for the lower part of the spectrum in the error distribution while the upper part is handled inexpensively using relaxation methods or fine-scale preconditioners. The meta-solvers are then applied to solve scattering problems with different shape of scatterers, at no extra training cost. We first demonstrate that the resulting meta-solvers are shape-agnostic, fast, and robust, whereas the standard standalone solvers may even fail to converge without the DeepONet. We then apply both classes of meta-solvers to scattering from a submarine, a complex three-dimensional problem. We achieve very fast solutions, especially with the DeepONet-Krylov methods, which require orders of magnitude fewer iterations than any of the standalone solvers.

97 MATHEMATICS AND COMPUTING↗

Transfer learning for probabilistic localization of hidden cracks in concrete structures

Abstract The utility of discriminative supervised learning models built using multiple training-data sources is investigated for hidden crack localization in concrete. Feed-forward neural network (FFNN) is chosen as the model architecture, and transfer learning is used to assimilate the information obtained from different sources (computational physics simulations and laboratory experiments). The labeled training data consists of values of a damage index and the known locations of hidden cracks. The classification models need to learn how the presence of damage (hidden cracks) affects the damage index at different sensors for different test conditions. To this end, diagnostic FFNN models are built by sequentially adding and training new hidden layers to assimilate labeled information from computer models (different model geometries, test conditions, crack lengths, crack locations) and laboratory experiments on a plain cement slab. These transfer learning-based models are then used to localize damage in concrete specimens that reflect real-world conditions (i.e., specimens with steel reinforcement and randomly distributed aggregate). The actual damage state in these specimens is determined by extracting cores and performing petrographic studies on the extracted cores. The damage probability estimated by transfer learning-based models is compared with the petrographic damage rating index (DRI) to identify the most suitable approach to train the diagnostic models. The transfer learning-based diagnostic methodology shows promise and could be used in various structural health monitoring applications, where sufficient labeled data are typically not available from a single data source.

Miele, S.↗

Education and Training Needs in Radiation Oncology in India: Opportunities for Indo–US Collaborations

Purpose: To conduct a survey of radiation oncologists in India, to better understand specific educational needs of radiation oncology in India and define areas of collaboration with US institutions. Methods and Materials: A 20-question survey was distributed to members of the Association of Indian Radiation Oncologists and the Indian Brachytherapy Society between November 2013 and May 2014. Results: We received a total of 132 responses. Over 50% of the physicians treat more than 200 patients per day, use 2-dimensional or 3-dimensional treatment planning techniques, and approximately 50% use image guided techniques. For education needs, most respondents agreed that further education in intensity modulated radiation therapy, image guided radiation therapy, stereotactic radiation therapy, biostatistics, and research methods for medical residents would be useful areas of collaboration with institutions in the United States. Other areas of collaboration include developing a structured training module for nursing, physics training, and developing a second-opinion clinic for difficult cases with faculty in the United States. Conclusion: Various areas of potential collaboration in radiation oncology education were identified through this survey. These include the following: establishing education programs focused on current technology, facilitating exchange programs for trainees in India to the United States, promoting training in research methods, establishing training modules for physicists and oncology nurses, and creating an Indo–US. Tumor Board. It would require collaboration between the Association of Indian Radiation Oncologists and the American Society for Radiation Oncology to develop these educational initiatives.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Application of machine learning for the estimation of electron energy distribution from optical emission spectra

Abstract This paper discusses the use of probabilistic deep neural networks for the prediction of the electron energy probability function in low-temperature non-thermal plasmas. The neural networks are trained using optical emission spectroscopy and Langmuir probe measurements, with the goal of providing a reliable estimate of the electron energy probability function solely from optical emission data. The performance of both non-Bayesian and Bayesian networks is evaluated. It is found that Bayesian models are preferable as they assign a higher level of uncertainty to their prediction especially when the dataset used to train them is small. This work describes one of the many potential applications of machine learning in plasma science and technology.

Physics↗

Convolutional Neural Network-Based Protection-Zone Classification of Faults in Distribution Feeders with Photovoltaics.

Fault detection and isolation is critical for reliable operation of distribution systems. The ride-through requirements for the distributed energy resources (DER), mandated by the IEEE 1547-2018 standard, makes it challenging to use undervoltage (UV) conditions for fault detection. In addition, with low fault current contribution from these inverter-based DERs, the time-overcurrent relays are also less effective. Thus motivated, this paper presents a learning-based approach for fault detection and localization. A convolutional neural network (CNN)-based model is proposed which uses local voltage and current waveforms from DER locations and feeder substations, for training a zonal classifier. The classifier can be adopted into any relay-like device for discriminating between faults originating from different protection zones. The performance of the proposed approach was tested on publicly available test feeders with distributed photovoltaics (PVs).

Fault localization, convolutional neural networks,↗

Physics-coupled data-driven design of high-temperature alloys

We present a materials design loop, which streamlines physics-coupled machine learning (ML) surrogate models to discover new alloy chemistries with improved properties. The efficacy is demonstrated by discovering a high-temperature alumina-forming austenitic (AFA) stainless steel with enhanced creep, followed by experimental validation. The ML models have been trained using a well-curated, highly consistent experimental dataset augmented with synthetic microstructural features from a computational thermodynamic approach. We have populated a large number of hypothetical AFA alloys to explore the high-dimensional composition space and have predicted their creep properties by providing the same synthetic input features obtained from the trained ML models. Uncertainties from the ML training were taken as thresholds for truncating predicted results to identify alloys with improved or deteriorated creep. Individual elemental compositions have been determined via probability density distribution analysis from the group of alloys at the top and bottom of the predicted creep values for further virtual and experimental validations. In conclusion, we anticipate that this workflow can be applied to screen desired conditions, such as chemistry and processing parameters, in high-dimensional space through physics-guided data analytics.

Alloy design↗

Tailored Particle Beams From Single-Component Plasmas

Recently, we developed a non-destructive technique to create narrow beams of electrons (or positrons) of adjustable width and brightness from single-component plasmas confined in a Penning-Malmberg trap [Weber et al., Phys. Plasmas 13, 123502 (2008)]. Here, we review highlights of that work and discuss the distributions in energy of the extracted beams. A simple model for beam extraction predicts Gaussian beam profiles, with transverse spatial widths dependent on the number of particles in the beam. A Maxwellian energy distribution is predicted for small beams. The predictions of the theory are confirmed using electron plasmas. Extraction of over 50% of a trapped plasma into a train of nearly identical beams is demonstrated. Finally, the possibility of creating high quality, electrostatic beams by extraction from the confining magnetic field is discussed.

43 PARTICLE ACCELERATORS↗

A REFINED QSO SELECTION METHOD USING DIAGNOSTICS TESTS: 663 QSO CANDIDATES IN THE LARGE MAGELLANIC CLOUD

We present 663 QSO candidates in the Large Magellanic Cloud (LMC) selected using multiple diagnostics. We started with a set of 2566 QSO candidates selected using the methodology presented in our previous work based on time variability of the MACHO LMC light curves. We then obtained additional information for the candidates by crossmatching them with the Spitzer SAGE, the Two Micron All Sky Survey, the Chandra, the XMM, and an LMC UBVI catalog. Using this information, we specified six diagnostic features based on mid-IR colors, photometric redshifts using spectral energy distribution template fitting, and X-ray luminosities in order to further discriminate high-confidence QSO candidates in the absence of spectra information. We then trained a one-class Support Vector Machine model using the diagnostics features of the confirmed 58 MACHO QSOs. We applied the trained model to the original candidates and finally selected 663 high-confidence QSO candidates. Furthermore, we crossmatched these 663 QSO candidates with the newly confirmed 151 QSOs and 275 non-QSOs in the LMC fields. On the basis of the counterpart analysis, we found that the false positive rate is less than 1%.

79 ASTRONOMY AND ASTROPHYSICS↗