Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed computation”

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 1,801 records · Page 100
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Large-Eddy Simulation of Flow Over Boeing Gaussian Bump Using Multiagent Reinforcement Learning Wall Model: Preprint

We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning. The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall at various computational grid points. It utilizes a wall eddy-viscosity formulation as the boundary condition to apply the modeled wall shear stress. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow. To further assess the robustness of the developed wall model, simulations of flow over the Boeing Gaussian bump are conducted at a Reynolds number of 2 x 10^6, based on the free-stream velocity and the bump width. The results of mean skin friction and pressure on the bump surface, as well as the velocity statistics of the flow field, are compared to those obtained from equilibrium wall model (EQWM) simulations and published experimental data sets. The developed wall model is found to successfully capture the acceleration and deceleration of the turbulent boundary layer on the bump surface, providing better predictions of skin friction near the bump peak and exhibiting comparable performance to the EQWM with respect to the wall pressure and velocity field. We also conclude that the subgrid-scale model is crucial to the accurate prediction of the flow field, in particular the prediction of separation.

boundary layer↗
DOE OSTI2024

Investigation of CAD-based Geometry Workflows for Multiphysics Fusion Problems Using OpenMC and MOOSE

Fusion system designs are complex and require intricate and accurate meshes to be properly modeled. In this study, we investigate the use of CAD-based geometry workflows in fusion systems multiphysics problems. A simplified tokamak was introduced and modeled in CAD using a multiphysics coupling of OpenMC Monte Carlo transport and MOOSE heat conduction. The meshed geometry was prepared using direct accelerated geometry Monte Carlo (DAGMC) for particle transport, and a volumetric mesh was also prepared to be used in MOOSE and to tally OpenMC results. Cardinal was used to run OpenMC Monte Carlo particle transport within MOOSE framework. The heat source distribution and tritium production were calculated in OpenMC. The data transfer system was used to transfer heat source and temperature distribution between OpenMC and MOOSE. Two computational studies related to mesh refinement were performed: (1) refining the DAGMC and volumetric meshes used for tallying results and solving heat conduction and (2) only refining the DAGMC particle transport mesh. The refinement of the tally mesh has a much larger effect on the runtime compared to the refinement of the DAGMC particle transport surface mesh.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Modeling of streamflow in a 30 km long reach spanning 5 years using OpenFOAM 5.x

Abstract. Developing accurate and efficient modeling techniques for streamflow at the tens-of-kilometers spatial scale and multi-year temporal scale is critical for evaluating and predicting the impact of climate- and human-induced discharge variations on river hydrodynamics. However, achieving such a goal is challenging because of limited surveys of streambed hydraulic roughness, uncertain boundary condition specifications, and high computational costs. We demonstrate that accurate and efficient three-dimensional (3-D) hydrodynamic modeling of natural rivers at 30 km and 5-year scales is feasible using the following three techniques within OpenFOAM, an open-source computational fluid dynamics platform: (1) generating a distributed hydraulic roughness field for the streambed by integrating water-stage observation data, a rough wall theory, and a local roughness optimization and adjustment strategy; (2) prescribing the boundary condition for the inflow and outflow by integrating precomputed results of a one-dimensional (1-D) hydraulic model with the 3-D model; and (3) reducing computational time using multiple parallel runs constrained by 1-D inflow and outflow boundary conditions. Streamflow modeling for a 30 km long reach in the Columbia River (CR) over 58 months can be achieved in less than 6 d using 1.1 million CPU hours. The mean error between the modeled and the observed water stages for our simulated CR reach ranges from −16 to 9 cm (equivalent to approximately ±7 % relative to the average water depth) at seven locations during most of the years between 2011 and 2019. We can reproduce the velocity distribution measured by the acoustic Doppler current profiler (ADCP). The correlation coefficients of the depth-averaged velocity between the model and ADCP measurements are in the range between 0.71 and 0.83 at 75 % of the survey cross sections. With the validated model, we further show that the relative importance of dynamic pressure versus hydrostatic pressure varies with discharge variations and topography heterogeneity. Given the model's high accuracy and computational efficiency, the model framework provides a generic approach to evaluate and predict the impacts of climate- and human-induced discharge variations on river hydrodynamics at tens-of-kilometers and decadal scales.

58 GEOSCIENCES↗
DOE OSTI2020

Electrical circuit control in power systems

Electrical circuit control techniques in power systems are disclosed herein. In one embodiment, a supervisory computer in the power system can be configured to fit phasor measurement data from phasor measurement units into a Gaussian distribution with a corresponding Gaussian confidence level. When the Gaussian confidence level of the fitted Gaussian distribution is above a Gaussian confidence threshold, the supervisory computer can be configured to perform an ambient analysis on the received phasor measurement data to determine an operating characteristic of the power system. The supervisory computer can then automatically applying at least one electrical circuit control action to the power system in response to the determined operating characteristic.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Productive Programming of Distributed Systems with the SHAD C++ Library

High-performance computing (HPC) is often perceived as a matter of making large-scale systems (e.g., clusters) run as fast as possible, regardless the required programming effort. However, the idea of "bringing HPC to the masses" has recently emerged. Inspired by this vision, we have designed SHAD, the Scalable High-performance Algorithms and Data-structures library. SHAD is open source software, written in C++, for C++ developers. Unlike other HPC libraries for distributed systems, which rely on SPMD models, SHAD adopts a shared-memory programming abstraction, to make C++ programmers feel at home. Underneath, SHAD manages tasking and data-movements, moving the computation where data resides and taking advantage of asynchrony to tolerate network latency. At the bottom of his stack, SHAD can interface with multiple runtime systems: this not only improves developer’s productivity, by hiding the complexity of such software and of the underlying hardware, but also greatly enhance code portability. Thanks to its abstraction layers, SHAD can indeed target different systems, ranging from laptops to HPC clusters, without any need for modifying the user-level code. We have prototyped and open-sourced the implementation of (a subset of) the C++ standard library (STL) targeting multi-node HPC clusters. Our work allows plain STL-based C++ code to scale on HPC systems, with no need for rewriting the code to exploit the complex hardware. SHAD is available under Apache v2 License at https://github.com/pnnl/SHAD. In this paper we overview the design of the SHAD library, depicting its main components: runtime systems abstractions for tasking; parallel and distributed data-structures; STL-compliant interfaces and algorithms.

Castellana, Vito G.↗
DOE OSTI2025

Atomistic Insights into Lithium–Glyme Solvate Ionic Liquids: Effects of Chain Length and Anion Coordination

For this study, mixtures of lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) in diglyme (G2), triglyme (G3) and tetraglyme (G4) at solvate ionic liquid (SIL) concentrations were investigated using classical molecular dynamics (cMD) simulations with a physically motivated force-field specifically developed for modeling these systems. The structural and dynamical properties of the mixtures were computed and analyzed. Lithium solvation shells, radial distribution functions, and X-ray structure factors were studied across the different SIL systems. Translational diffusion and rotational relaxation times were also evaluated, exhibiting similar trends with increasing glyme chain length. The results are consistent with experimental data and in good agreement with previous computational studies on G3 and G4. These findings validate the accuracy of the force field in modeling glyme systems and its use for describing the [Li(G2) 4/3 ][TFSI] mixture. Additionally, the thermal and electrochemical stability of these electrolytes were systematically examined. The thermal stability appears to be governed by cooperative interactions among glyme molecules, while the electrochemical stability is primarily influenced by Li + -anion interactions, which vary significantly with glyme chain length. Overall, the study sheds light on the crucial role of the anion in these glyme-based SILs and offers valuable insights into Li + -glyme systems at SIL concentrations, highlighting their promise as potential Li-ion battery electrolytes.

anions↗
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 OSTI2025

Accelerating Hamiltonian Monte Carlo for Bayesian inference in neural networks and neural operators

Hamiltonian Monte Carlo (HMC) is a powerful and accurate method to sample from the posterior distribution in Bayesian inference. However, HMC techniques are computationally demanding for Bayesian neural networks due to the high dimensionality of the network’s parameter space and the non-convexity of their posterior distributions. Therefore, various approximation techniques, such as variational inference (VI) or stochastic gradient MCMC, are often employed to infer the posterior distribution of the network parameters. Such approximations introduce inaccuracies in the inferred distributions, resulting in unreliable uncertainty estimates. In this work, we propose a hybrid approach that combines inexpensive VI and accurate HMC methods to efficiently and accurately quantify uncertainties in neural networks and neural operators. The proposed approach leverages an initial VI training on the full network. We examine the influence of individual parameters on the prediction uncertainty, which shows that a large proportion of the parameters do not contribute substantially to uncertainty in the network predictions. This information is then used to significantly reduce the dimension of the parameter space, and HMC is performed only for the subset of network parameters that strongly influence prediction uncertainties. This yields a framework for accelerating the full batch HMC for posterior inference in neural networks. We demonstrate the efficiency and accuracy of the proposed framework on deep neural networks and operator networks, showing that inference can be performed for large networks with tens to hundreds of thousands of parameters. Finally, we show that this method can effectively learn surrogates for complex physical systems by modeling the operator that maps from upstream conditions to wall-pressure data on a cone in hypersonic flow.

Bayesian inference↗
DOE OSTI2023

US ATLAS and US CMS HPC and Cloud Blueprint

The Large Hadron Collider (LHC) at CERN houses two general purpose detectors - ATLAS and CMS - which conduct physics programs over multi-year runs to generate increasingly precise and extensive datasets. The efforts of the CMS and ATLAS collaborations lead to the discovery of the Higgs boson, a fundamental particle that gives mass to other particles, representing a monumental achievement in the field of particle physics that was recognized with the awarding of the Nobel Prize in Physics in 2013 to François Englert and Peter Higgs. These collaborations continue to analyze data from the LHC and are preparing for the high luminosity data taking phase at the end of the decade. The computing models of these detectors rely on a distributed processing grid hosted by more than 150 associated universities and laboratories worldwide. However, such new data will require a significant expansion of the existing computing infrastructure. To address this, both collaborations have been working for years on integrating High Performance Computers (HPC) and commercial cloud resources into their infrastructure and continue to assess the potential role of such resources in order to cope with the demands of the new high luminosity era. US ATLAS and US CMS computing management have charged the authors to provide a blueprint document looking at current and possibly future use of HPC and Cloud resources, outlining integration models, possibilities, challenges and costs. The document will address key questions such as the optimal use of resources for the experiments and funding agencies, the main obstacles that need to be overcome for resource adoption, and areas that require more attention.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2017

Precision and Accuracy in PDV and VISAR

This is a technical report discussing our current level of understanding of a wide and varying distribution of uncertainties in velocity results from Photonic Doppler Velocimetry in its application to gas gun experiments. Using propagation of errors methods with statistical averaging of photon number fluctuation in the detected photocurrent and subsequent addition of electronic recording noise, we learn that the velocity uncertainty in VISAR can be written in closed form. For PDV, the non-linear frequency transform and peak fitting methods employed make propagation of errors estimates notoriously more difficult to write down in closed form expect in the limit of constant velocity and low time resolution (large analysis-window width). An alternative method of error propagation in PDV is to use Monte Carlo methods with a simulation of the time domain signal based on results from the spectral domain. A key problem for Monte Carlo estimation for an experiment is a correct estimate of that portion of the time-domain noise associated with the peak-fitting region-of-interesting in the spectral domain. Using short-time Fourier transformation spectral analysis and working with the phase dependent real and imaginary parts allows removal of amplitude-noise cross terms that invariably show up when working with correlation-based methods or FFT power spectra. Estimation of the noise associated with a given spectral region of interest is then possible. At this level of progress, we learn that Monte Carlo trials with random recording noise and initial (uncontrolled) phase yields velocity uncertainties that are not as large as those observed. In a search for additional noise sources, a speckleinterference modulation contribution with off axis rays was investigated, and was found to add a velocity variation beyond that from the recording noise (due to random interference between off axis rays), but in our experiments the speckle modulation precision was not as important as the recording noise precision. But from these investigations we do appreciate that the velocity-uncertainty itself has a wide distribution of values that varies with signal-amplitude modulation (is not a single value). To provide a rough rule of thumb for the velocity uncertainty, we computed the average of the relative standard deviation distributions from 60 recorded traces (with distributions of uncertainties roughly between 0.1 % to 1 % in each trace) and found a mean of the distribution of uncertainties for our experiments is not better than 0.4 % at an analysis window width of 5 ns (although for brief intervals it can be as good as 0.1 %). Further imagination and testing may be needed to reveal other possible hydrodynamics-related sources of velocity error in PDV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2012

A METHOD FOR COUPLING DYNAMICAL AND COLLISIONAL EVOLUTION OF DUST IN CIRCUMSTELLAR DISKS: THE EFFECT OF A DEAD ZONE

Dust is a major component of protoplanetary and debris disks as it is the main observable signature of planetary formation. However, since dust dynamics are size-dependent (because of gas drag or radiation pressure) any attempt to understand the full dynamical evolution of circumstellar dusty disks that neglect the coupling of collisional evolution with dynamical evolution is thwarted because of the feedback between these two processes. Here, a new hybrid Lagrangian/Eulerian code is presented that overcomes some of these difficulties. The particles representing 'dust clouds' are tracked individually in a Lagrangian way. This system is then mapped on an Eulerian spatial grid, inside the cells of which the local collisional evolutions are computed. Finally, the system is remapped back in a collection of discrete Lagrangian particles, keeping their number constant. An application example of dust growth in a turbulent protoplanetary disk at 1 AU is presented. First, the growth of dust is considered in the absence of a dead zone and the vertical distribution of dust is self-consistently computed. It is found that the mass is rapidly dominated by particles about a fraction of a millimeter in size. Then the same case with an embedded dead zone is investigated and it is found that coagulation is much more efficient and produces, in a short timescale, 1-10 cm dust pebbles that dominate the mass. These pebbles may then be accumulated into embryo-sized objects inside large-scale turbulent structures as shown recently.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

DER Cybersecurity R&D

The National Renewable Energy Laboratory (NREL) conducted more than 30 assessments for utilities across the United States with a cybersecurity assessment tool based on the U.S. Department of Energy (DOE) Cybersecurity Capability Maturity Model (C2M2) and the National Institute of Standards and Technology (NIST) Cybersecurity Framework (CSF) and focused on business process. With funding from the DOE Office of Renewable Energy and Energy Efficiency Federal Energy Management Program, NREL modified the current cyber governance assessment tool to include an assessment process specifically for distributed energy resources (DERs). The Distributed Energy Resources Cybersecurity Framework (DER-CF) was developed to help federal agencies mitigate gaps in their cybersecurity posture for distributed energy systems.

cybersecurity valuation↗
DOE OSTI2024

Digital Twin + AI: Control Room of the Future

A digital twin enhances power grid control room operations by providing real-time monitoring, predictive insights, simulation capabilities, remote control, training opportunities, data integration, and decision support. This technology empowers control room operators to effectively manage the grid, optimize performance, and ensure reliable and efficient energy distribution.

control room of the future↗
DOE OSTI2013

Demonstration of Data Center Energy Use Prediction Software

This report documents a demonstration of a software modeling tool from Romonet that was used to predict energy use and forecast energy use improvements in an operating data center. The demonstration was conducted in a conventional data center with a 15,500 square foot raised floor and an IT equipment load of 332 kilowatts. It was cooled using traditional computer room air handlers and a compressor-based chilled water system. The data center also utilized an uninterruptible power supply system for power conditioning and backup. Electrical energy monitoring was available at a number of locations within the data center. The software modeling tool predicted the energy use of the data center's cooling and electrical power distribution systems, as well as electrical energy use and heat removal for the site. The actual energy used by the computer equipment was recorded from power distribution devices located at each computer equipment row. The model simulated the total energy use in the data center and supporting infrastructure and predicted energy use at energy-consuming points throughout the power distribution system. The initial predicted power levels were compared to actual meter readings and were found to be within approximately 10 percent at a particular measurement point, resulting in a site overall variance of 4.7 percent. Some variances were investigated, and more accurate information was entered into the model. In this case the overall variance was reduced to approximately 1.2 percent. The model was then used to predict energy use for various modification opportunities to the data center in successive iterations. These included increasing the IT equipment load, adding computer room air handler fan speed controls, and adding a water-side economizer. The demonstration showed that the software can be used to simulate data center energy use and create a model that is useful for investigating energy efficiency design changes.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

On the calculation of parton distributions from Lattice QCD

A new method for calculating parton distribution functions from lattice QCD is implemented and studied. Lattice QCD calculable matrix elements with space-like separated fields have an analogous operator product expansion to experimental scattering cross sections and thus these matrix elements are known as “Good Lattice Cross Sections”. Using the colinear factorization approach, a Good Lattice Cross Section can be factorized to the short distance matching kernels that are computed in perturbation theory and the non-perturbative parton distribution functions. As a result, using the perturbative matching kernels and the non-perturbatively computed matrix elements, one can obtain the parton distribution functions. The nucleon and pion matrix elements are determined on a set of 2+1 flavors of clover improved quarks with heavier than physical pion mass. The determination of the parton distributions from Good Lattice Cross Sections constitutes an ill-posed inverse problem. Methods for accurate determination of parton distributions from the Good Lattice Cross Sections are studied. With the calculation of several Good Lattice Cross Sections, the determination of the parton distributions can be improved with a simultaneous analysis, similar to the global parton distribution fits to experimental cross sections.

Karpie, Joseph↗
DOE OSTI2023

A Sparse Distributed Gigascale Resolution Material Point Method

In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

97 MATHEMATICS AND COMPUTING↗

Refine your search to explore more results.