Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network performance”

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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Resolving extreme jet substructure

We study the effectiveness of theoretically-motivated high-level jet observables in the extreme context of jets with a large number of hard sub-jets (up to N = 8). Previous studies indicate that high-level observables are powerful, interpretable tools to probe jet substructure for N ≤ 3 hard sub-jets, but that deep neural networks trained on low-level jet constituents match or slightly exceed their performance. We extend this work for up to N = 8 hard sub-jets, using deep particle-flow networks (PFNs) and Transformer based networks to estimate a loose upper bound on the classification performance. A fully-connected neural network operating on a standard set of high-level jet observables, 135 N-subjetiness observables and jet mass, reach classification accuracy of 86.90%, but fall short of the PFN and Transformer models, which reach classification accuracies of 89.19% and 91.27% respectively, suggesting that the constituent networks utilize information not captured by the set of high-level observables. We then identify additional high-level observables which are able to narrow this gap, and utilize LASSO regularization for feature selection to identify and rank the most relevant observables and provide further insights into the learning strategies used by the constituent-based neural networks. The final model contains only 31 high-level observables and is able to match the performance of the PFN and approximate the performance of the Transformer model to within 2%.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions

Neural posterior estimation (NPE), a type of amortized variational inference, is a computationally efficient means of constructing probabilistic catalogs of light sources from astronomical images. To date, NPE has not been used to perform inference in models with spatially varying covariates. However, ground-based astronomical images exhibit spatially varying sky backgrounds and point spread functions (PSFs), and accounting for this variation is essential for constructing accurate catalogs of imaged light sources. In this work, we introduce a novel NPE-based cataloging method that trains an inference network with semisynthetic astronomical images generated using PSFs and backgrounds sampled from the Sloan Digital Sky Survey. In experiments with semisynthetic images, we evaluate the method on key cataloging tasks: light source detection, star/galaxy separation, and flux measurement. A “generalist” inference network—trained with diverse PSFs and backgrounds—performs as well as a “specialist” network even when both are evaluated on the specialist’s particular PSF/background combination. This result suggests that a single NPE network can generalize across spatial variations, eliminating the need for retraining on each observational condition.

astronomy image processing↗
DOE OSTI2023

Cloud Services Enable Efficient AI-Guided Simulation Workflows across Heterogeneous Resources

Applications which fuse machine learning and simulation are rarely best served by a single computing resource. Highly parallel simulation codes are best deployed on super- computers, while AI tasks used to decide which simulations to perform may be best suited to specialized accelerators. Here we present a Function-as-a-Service (FaaS) system for executing complex, distributed computational campaigns that achieves performance parity with conventional workflow systems without the complexities of secure network connections between compute providers. One innovation enabling high performance is a subsystem that directly moves task data between sites, separate from the cloud-hosted FaaS system used to distribute task instructions. We also introduce a flexible scheduling system that allows us access factor of 2 trade offs between the amount of resources required to solve a problem at each compute site. We anticipate that this system will upgrade multi-site applications from demonstration projects to routine practice in computational science.

Ward, Logan↗
DOE OSTI2020

SHARP-Net: Platform for Self-Healing and Attack Resilient PMU Networks

Synchrophasor technology plays a pivotal role in developing the next generation of wide-area monitoring, protection, and control in the smart grid environment. As technology and communications infrastructures evolve, however, so do the attack surfaces in the synchrophasor network that can be exploited by advanced persistent threat (APT) actors to affect power system stability and reliability. In this paper, we propose a novel platform for developing a self-healing and attack-resilient PMU network (SHARP-Net) by instituting a state-of-the-art intrusion detection system (IDS) with an intrusion mitigation system (IMS) and an alert management system (AMS). In particular, the proposed platform detects anomalies during cyberattacks on phasor data concentrators (PDCs) based on the rules defined in the IDS, then the generated alerts are published to the IMS through the AMS. The proposed IMS proceeds to take automated corrective responses to mitigate cyberattacks by reconfiguring the synchrophasor network to isolate the compromised PDCs, and it orchestrates new PDCs to prevent the future propagation of attacks. Further, the IMS restores the system's observability by reconnecting the new PDCs to make the grid attack-resilient. In this work, the SHARP-Net platform is developed by using Python-based libraries, minimega's software-defined network, and virtual machine orchestration. We implement and validate the proposed SHARP-Net architecture by testing a PMU network in the smart grid environment. SHARP-Net showed promising performance in detecting cyberattacks and mitigating them through the network reconfiguration.

computer architecture↗
DOE OSTI2025

PickerXL, A Large Deep Learning Model to Measure Arrival Times from Noisy Seismic Signals

Precisely measuring seismic arrival times is a labor-intensive task but is critical for both earthquake monitoring and subsurface imaging. Recently published deep learning models have demonstrated superior performance compared to traditional automatic approaches for picking arrival times. Although existing deep learning models have shown promising results, further advancements are necessary as their performance is not yet satisfactory especially when applied to new regions and station networks. Increasing model size has led to improved performance in other machine learning applications. Here, we aimed to investigate whether enlarging deep learning models can increase performance on accepted benchmarks. We trained three models of varying sizes, small (1X), medium (4X), and large (16X), using globally distributed local and regional earthquake signals and background noise waveforms from a benchmark dataset, Stanford Earthquake Dataset. Our results indicate that the largest model (PickerXL) outperforms both the smaller models and Seisbench implementation of the PhaseNet model, which has the same number of parameters as our small model. The PickerXL model’s enhanced capacity to extract complex patterns from seismograms contributes to its superior arrival picking abilities compared to the smaller model.

Chai, Chengping [Oak Ridge National Laboratory (OR↗
DOE OSTI2024

Streamlining latent spaces in machine learning using moment pooling

Many machine learning applications involve learning a latent representation of data, which is often high-dimensional and difficult to directly interpret. In this work, we propose “moment pooling,” a natural extension of deep sets networks which drastically decreases the latent space dimensionality of these networks while maintaining or even improving performance. Moment pooling generalizes the summation in deep sets to arbitrary multivariate moments, which enables the model to achieve a much higher effective latent dimensionality for a fixed learned latent space dimension. We demonstrate moment pooling on the collider physics task of quark/gluon jet classification by extending energy flow networks (EFNs) to moment EFNs. We find that moment EFNs with latent dimensions as small as 1 perform similarly to ordinary EFNs with higher latent dimension. This small latent dimension allows for the internal representation to be directly visualized and interpreted, which in turn enables the learned internal jet representation to be extracted in closed form. Published by the American Physical Society 2024

Gambhir, Rikab (ORCID:0000000251080448)↗
DOE OSTI2025

Parallel sorting algorithm classification: is manual instrumentation necessary?

Understanding parallel algorithms is crucial for accelerating scientific simulations on complex, distributed memory, high-performance computers. Modern algorithm classification approaches learn semantics directly from source code to differentiate between algorithms, however, accessing source code is not always possible. We can learn about parallel algorithms from observing their performance, as programs running the same algorithms and using the same hardware should exhibit similar performance characteristics. We present an approach to learn algorithm classes from parallel performance data directly in order to classify algorithms without access to the source code. We extend previous work to enable classifying parallel sorting algorithms using automatic instrumentation instead of requiring manual region annotations in the source code. In this work, we design and demonstrate a study for classification of parallel sorting algorithms using parallel performance data collected from automatic instrumentation, and evaluate the performance of our new methodology on classification. We leverage Caliper to collect the performance data, Thicket for our exploratory data analysis (EDA), and PyTorch and Scikit-learn to evaluate the effectiveness of random forests, support vector machines (SVMs), decision trees, neural networks, and logistic regressions on parallel performance data. Additionally, we study noise in parallel performance data, whether the removal of noise and pre-processing of the data is necessary to accurately classify parallel sorting algorithms, and determine the effectiveness of features created from performance data. In conclusion, we demonstrate classification accuracy for these five different models of up to 97.7% across four different parallel algorithm classes.

Algorithm Classification↗
DOE OSTI2026

Robustness of the smartpixels classifier for different simulated sensor geometries and non-ideal detector conditions

Pixel tracking detectors at upcoming collider experiments will see unprecedented charged-particle densities. Real-time data reduction on the detector will enable higher granularity and faster readout, possibly enabling the use of the pixel detector in high-rate online event selection, such as the ATLAS or CMS first-level trigger systems. This data reduction can be accomplished with a neural network (NN) in the readout chip bonded with the sensor that recognizes and rejects tracks with low transverse momentum (p T ) based on the geometrical shape of the charge deposition (“cluster”). To design viable detectors for deployment, the dependence of the NN as a function of the sensor geometry, external magnetic field, irradiation, and noise must be understood. In this paper, we present first studies of the efficiency and data reduction for planar pixel sensors exploring these parameters. For the CMS HL-LHC sensor geometry, we obtain a signal efficiency of (91.9 ± 0.7)% and a data reduction of (29.7 ± 1.0)%. A smaller sensor pitch in the bending direction improves the p T discrimination, but a larger pitch can be partially compensated with detector thickness. Any accumulated radiation damage also changes the cluster shape, reducing the signal efficiency compared to the baseline by approximately 30–60% in absolute terms, but nearly all of the performance can be recovered through retraining of the network and updating the weights. Finally, the impact of noise was investigated, and retraining the network on noise-injected datasets was found to maintain performance within 6% of the baseline network trained and evaluated on noiseless data. •ASIC-compatible track-momentum classifier is robust in realistic detector conditions.•About 90% signal efficiency and 30% data reduction per layer for CMS HL-LHC geometry.•Single-layer signal efficiency increases for smaller pixel pitch or thicker sensors.•Performance with noise or after radiation damage mostly recovered by retraining.

Shekar, Danush [Illinois U., Chicago] (ORCID:00000↗
DOE OSTI2020

ECP Report: Update on Proxy Applications and Vendor Interactions

The ExaLearn miniGAN team (Ellis and Rajamanickam) have released miniGAN, a generative adversarial network(GAN) proxy application, through the ECP proxy application suite. miniGAN is the first machine learning proxy application in the suite (note: the ECP CANDLE project did previously release some benchmarks) and models the performance for training generator and discriminator networks. The GAN's generator and discriminator generate plausible 2D/3D maps and identify fake maps, respectively. miniGAN aims to be a proxy application for related applications in cosmology (CosmoFlow, ExaGAN) and wind energy (ExaWind). miniGAN has been developed so that optimized mathematical kernels (e.g., kernels provided by Kokkos Kernels) can be plugged into to the proxy application to explore potential performance improvements. miniGAN has been released as open source software and is available through the ECP proxy application website (https://proxyapps.exascaleproject.ordecp-proxy-appssuite/) and on GitHub (https://github.com/SandiaMLMiniApps/miniGAN). As part of this release, a generator is provided to generate a data set (series of images) that are inputs to the proxy application.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Quantifying leaf symptoms of sorghum charcoal rot in images of field‐grown plants using deep neural networks

Abstract Charcoal rot of sorghum (CRS) is a significant disease affecting sorghum crops, with limited genetic resistance available. The causative agent, Macrophomina phaseolina (Tassi) Goid, is a highly destructive fungal pathogen that targets over 500 plant species globally, including essential staple crops. Utilizing field image data for precise detection and quantification of CRS could greatly assist in the prompt identification and management of affected fields and thereby reduce yield losses. The objective of this work was to implement various machine learning algorithms to evaluate their ability to accurately detect and quantify CRS in red‐green‐blue images of sorghum plants exhibiting symptoms of infection. EfficientNet‐B3 and a fully convolutional network emerged as the top‐performing models for image classification and segmentation tasks, respectively. Among the classification models evaluated, EfficientNet‐B3 demonstrated superior performance, achieving an accuracy of 86.97%, a recall rate of 0.71, and an F1 score of 0.73. Of the segmentation models tested, FCN proved to be the most effective, exhibiting a validation accuracy of 97.76%, a recall rate of 0.68, and an F1 score of 0.66. As the size of the image patches increased, both models’ validation scores increased linearly, and their inference time decreased exponentially. This trend could be attributed to larger patches containing more information, improving model performance, and fewer patches reducing the computational load, thus decreasing inference time. The models, in addition to being immediately useful for breeders and growers of sorghum, advance the domain of automated plant phenotyping and may serve as a foundation for drone‐based or other automated field phenotyping efforts. Additionally, the models presented herein can be accessed through a web‐based application where users can easily analyze their own images.

Gonzalez, Emmanuel M.↗
DOE OSTI2020

Software Framework for Federated Science Instruments

There is an unprecedented promise of enhanced capabilities for federations of leadership computing systems and experimental science facilities by leveraging software technologies for fast and efficient operations. These federations seek to unify different science instruments, both computing and experimental, to effectively support science users and operators to execute complex workflows. The FedScI project addresses the software challenges associated with the formation and operation of federated environments by leveraging recent advances in containerization of software and softwarization of hardware. We propose a software framework to streamline the federation usage by science users and it’s provisioning and operations by facility providers. A distinguishing element of our work is the support for improved interaction between experimental devices, such as beam-line instruments, and more traditional high-performance computing resources, including compute, network, storage systems. We present guiding principles for the software framework and highlight portions of a current prototype implementation. We describe our science use case involving neutron imaging beam-lines (SNAP/BL-3, Imaging/CG-1D) at the Spallation Neutron Source and High Flux Isotope Reactor facilities at Oak Ridge National Laboratory. Additionally, we detail plans for a more direct instrument interaction within a federated environment, which could enable more advanced workflows with feedback loops to shorten the time to science.

Naughton III, Thomas↗
DOE OSTI2023

Deep Reinforcement Learning Based Smart Water Heater Control for Reducing Electricity Consumption and Carbon Emission

Water heating is the third largest electricity consumer in U.S. households, after space heating and cooling. Thus, water heaters represent a significant potential for reducing electricity consumption and associated CO2 emissions of residential buildings. To this end, this study proposes a model-free deep reinforcement learning (RL) approach that aims to minimize the electricity consumption and the CO2 emissions of a heat pump water heater without affecting user comfort. In this approach, a set of RL agents focusing on either electricity saving or emission reduction, with different look ahead periods, were trained using the deep Q-networks (DQN) algorithm and their performance was tested on different hot water usage and Marginal Operating Emissions Rate (MOER) profiles. The testing results showed that the RL agents that focus on electricity saving can save electricity in the range of 12–22% by operating the water heater with maximum heat pump efficiency and minimum electric element utilization. On the other hand, the RL agents that focus on emission reduction reduced emissions in the range of 18–37% by making use of the variable MOER values. These RL agents used the heat pump and/or an element when the MOER values are low due to the availability of renewable energy sources (e.g., solar and wind) and mostly avoided the periods of carbon-intensive periods. Overall, these results showed that the proposed RL approach can help minimize the electricity consumption and the CO2 emissions of a heat pump water heater without having any prior knowledge about the device.

Amasyali, Kadir↗
DOE OSTI2024

Agent-based simulations of shared automated vehicle operations: reflecting travel-party size, season and day-of-week demand variations

Here, this paper explores the effects of day of week and season of year demand variations for shared rides, along with realistic travel party sizes, on shared autonomous vehicle (SAV) services across the Austin, Texas region. Using the agent-based POLARIS program, synthetic person-trips that reflect travel-party size (from one to four persons) and demand variations over days and months, as evident in the National Household Travel Survey data were simulated in each scenario over a 24 h travel day. Results show that realistic party sizes can bring considerable changes to SAV fleet performance, including up to 8.5% higher service rates (number of requests accepted within 15 min), 5 min shorter journey times (wait time + travel time), 28% higher vehicle occupancies on weekends, and roughly 4% lower empty fleet VMT. Weekend travel is most impacted by season of year, with weekday travel patterns looking more uniform (thanks to work and school trips). Various performance metrics for the Austin network, like total and empty VMT, change by up to 30% when considering realistic variations in party size and time of year. This paper underscores the value of recognizing day-to-day and month-to-month variations in travel demand, and the importance of agent-based model equations to reflect travel-party size. Such realism can help quantify SAV seat occupancies more accurately, highlighting the importance of shared mobility. However, it also creates demand and supply issues for operators that now need more information on party size to manage dynamic ride-sharing, or those that may wish to shift their fleet vehicles to other regions for special events to protect profits while offering reasonable wait times to customers throughout the year.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Optimizing dynamic wireless charging for electric buses: A data-driven approach to infrastructure planning

The network configuration significantly impacts the performance of dynamic wireless charging (DWC) technology for electric buses. Here, this study presents a novel approach to planning charging infrastructure for public transit using data-driven nonconvex mixed-integer optimization. Integrating DWC and charging station technologies reveals a trade-off between enroute and stationary charging times. Our framework optimizes bus frequency settings and transmitter coil arrangements to minimize operational and infrastructure costs. A case study in Chattanooga, Tennessee, demonstrates the method's effectiveness in mitigating range anxiety and reducing charging expenses. This research implies that integrating DWC technology into public transit systems can enhance the feasibility and cost-effectiveness of electric bus operations, promoting sustainable urban mobility.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2021

Topology optimization of additively manufactured fluidic components free of internal support structures

This report integrates projection-based approaches for implementing overhang constraints with fluid topology optimization to design additively manufactured fluidic components that do not require internal support structures. Internal support structures are challenging, potentially impossible to remove in complex fluid networks, yet would degrade fluidic performance if left within the part. This presents a major challenge in coupling topology optimization with additive manufacturing in the design of fluid components. The proposed approach leverages past work in overhang constraints for solid mechanics, including projection formulations and adjoint sensitivity analysis, and considers incompressible Navier–Stokes equations for laminar fluid flow. The approach is demonstrated on 2D and 3D fluid topology optimization problems to minimize pressure drop and constrain mass flow rates in pipes and manifolds. Resulting designs are crisp, logical, satisfy performance constraints, and satisfy overhang constraints, eliminating the need for internal support structures.

42 ENGINEERING↗
DOE OSTI2021

The Corrected Distortion model for Lagrangian spray simulation of transcritical fuel injection

In this work, we present a detailed implementation and validation of the droplet modeling framework proposed by Dahms and Oefelein (2016) into the engine commercial CFD software CONVERGE using the User Defined Function (UDF) interface. The model accounts for the nonlinear deformation and oscillation experienced by liquid spray droplet injected into high pressure and temperature. Lagrangian spray simulations of Engine Combustion Network (ECN) Spray A are performed. Model validation against standard experimental measurements of liquid velocity, vapor mixture fraction is conducted. To perform more rigorous model validation, new experimental measurements based on Diffused Back Illumination (DBI) are introduced. The new measurements are processed for Projected Liquid Volume (PLV), which offers as close as possible one-to-one model validation for liquid penetration while offering new insights into the spray physics. Comparison with a One-D model based on adiabatic mixing theory by Siebers (1999) and Desantes et al. (2007) are also conducted. Through these model validation exercises, it is shown that the new framework improves liquid-phase penetration predictions, following a tendency for enhanced evaporation, compared to the standard approach for both Reynolds Average Navier Stokes (RANS) and Large Eddy Simulation (LES). Additionally, at the liquid length, maximum mixture fraction values predicted by the new approach are in good agreement those of an adiabatic mixing model. Qualitative analysis of the spray behaviors during the early stage of the injection process reveals that the proposed framework predicts significant increase in droplet evaporation rate with lower drop drag compared to the current standard approach.

42 ENGINEERING↗
DOE OSTI2023

Computational study of the ECN spray C via one-way coupling of internal nozzle flow and ensuing spray

Here, in this study, computational fluid dynamics simulations of the Engine Combustion Network Spray C injector were performed to investigate the effect of the internal nozzle flow on the development of the ensuing spray in automotive fuel injectors. A set of simulation best practices was first developed to achieve an accurate representation of the internal nozzle flow. Detailed, spatiotemporally defined information was extracted at the injector’s orifice exit and stored in maps that were subsequently employed to initialize a Lagrangian spray by means of a static, one-way coupling (OWC) approach. To highlight the impact of the in-nozzle flow on the spray, the OWC approach was compared with the conventional rate-of-injection (ROI) approach, for which the spray parcels are commonly initialized using a blob injection model. The results indicated that, using the ROI approach, considerable evaporation was observed within the plume in the near-nozzle region. On the other hand, the OWC approach showed evidence of evaporation farther downstream and at the plume periphery. The different behavior observed with the two approaches was mostly due to substantial differences in fuel mass distribution. The liquid fuel concentration predicted by the OWC approach matched well with X-ray tomography measurements of projected fuel mass per unit volume, in terms of both magnitude and distribution. In contrast, an unphysical distribution of fuel mass characterized by an extremely low liquid concentration was predicted by the ROI approach. In the far-field, the effect of the in-nozzle flow was found to be weaker as the spray penetrated and interacted with the ambient gas. In this region, the OWC and ROI approaches provided similar predictions of vapor penetration, spray morphology, and mixing-related characteristics.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

Search for pair-production of vector-like quarks in pp collision events at s = 13 TeV with at least one leptonically decaying Z boson and a third-generation quark with the ATLAS detector

Herein a search for the pair-production of vector-like quarks optimized for decays into a Z boson and a third-generation Standard Model quark is presented, using the full Run 2 dataset corresponding to 139fb –1 of pp collisions at $\sqrt{s}$ = 13TeV, collected in 2015–2018 with the ATLAS detector at the Large Hadron Collider. The targeted final state is characterized by the presence of a Z boson with high transverse momentum, reconstructed from a pair of same-flavour leptons with opposite-sign charges, as well as by the presence of b-tagged jets and high-transverse-momentum large-radius jets reconstructed from calibrated smaller-radius jets. Events with exactly two or at least three leptons are used, which are further categorized by the presence of boosted W, Z, and Higgs bosons and top quarks. The categorization is performed using a neural-network-based boosted object tagger to enhance the sensitivity to signal relative to the background. No significant excess above the background expectation is observed and exclusion limits at 95% confidence level are set on the masses of the vector-like partners T and B of the top and bottom quarks, respectively. The limits depend on the branching ratio configurations and, in the case of 100% branching ratio for T→Zt and 100% branching ratio for B→Zb, this search sets the most stringent limits to date, allowing m T >1.60TeV and m B >1.42TeV, respectively.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗