Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network performance evaluation”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A Resilient Integrated Resource Planning Framework for Transmission Systems: Analysis and Optimization

This article presents a resilient Integrated Resource Planning (IRP) framework designed for transmission systems, with a specific focus on analyzing and optimizing responses to High-Impact Low-Probability (HILP) events. The framework aims to improve the resilience of transmission networks in the face of extreme events by prioritizing the assessment of events with significant consequences. Unlike traditional reliability-based planning methods that average the impact of various outage durations, this work adopts a metric based on the proximity of outage lines to generators to select HILP events. The system’s baseline resilience is evaluated by calculating load curtailment in different parts of the network resulting from HILP outage events. The transmission network is represented as an undirected graph. Graph-theoretic techniques are used to identify islands with or without generators, potentially forming segmented grids or microgrids. This article introduces Expected Load Curtailment (ELC) as a metric to quantify the system’s resilience. The framework allows for the re-evaluation of system resilience by integrating additional generating resources to achieve desired resilience levels. Optimization is performed in the re-evaluation stage to determine the optimal placement of distributed energy resources (DERs) for enhancing resilience, i.e., minimizing ELC. Case studies on the IEEE 24-bus system illustrate the effectiveness of the proposed framework. In the broader context, this resilient IRP framework aligns with energy sustainability goals by promoting robust and resilient transmission networks, as the optimal placement of DERs for resilience enhancement not only strengthens the system’s ability to withstand and recover from disruptions but also contributes to efficient resource utilization, advancing the overarching goal of energy sustainability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Harnessing graph convolutional neural networks for identification of glassy states in metallic glasses

Graph Convolutional Neural Networks (GCNNs) have emerged as powerful tools for analyzing materials. In this study, we employ GCNNs to examine structural characteristics of CuZr metallic glasses (MGs) and identify their states. We use molecular dynamics to simulate the quenching process of CuZr, using cooling rates ranging from 10 9 to 10 15 K/s, to produce six unique glassy states. For each state, we create a dataset comprising 1,800 distinct samples. We evaluate the effectiveness of various GCNNs, including Graph Attention Neural Network (GANN), Graph Sample and AggreGatE (GraphSAGE), Graph Isomorphism Network (GIN), and Relational Graph Convolutional Neural Network (RGCN). GANN and GraphSAGE demonstrate comparable performance, achieving an overall accuracy of 81% in classifying the MG states. Furthermore, these results underscore the potential of GCNNs to detect subtle structural variances in disordered materials and point to broader application of deep learning in the analysis of MGs and other amorphous substances.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management

Abstract Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO $$_2$$ 2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. The heterogeneity typically requires high-fidelity physics-based models to make predictions on CO $$_2$$ 2 fate. Furthermore, characterizing the heterogeneity accurately is fraught with parametric uncertainty. Accounting for both, heterogeneity and uncertainty, makes this a computationally-intensive problem challenging for current reservoir simulators. To tackle this, we use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization at critical reservoir locations. We use DPFEHM framework, which has trustworthy physics based on the standard two-point flux finite volume discretization and is also automatically differentiable like machine learning models. Our physics-informed machine learning framework uses convolutional neural networks to learn an appropriate extraction rate based on the permeability field. We also perform a hyperparameter search to improve the model’s accuracy. Training and testing scenarios are executed to evaluate the feasibility of using physics-informed machine learning to manage reservoir pressures. We constructed and tested a sufficiently accurate simulator that is 400 000 times faster than the underlying physics-based simulator, allowing for near real-time analysis and robust uncertainty quantification.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

A Practical Comparison of Data-Driven Prognostics Methods for Energy Systems

This study explores data-driven prognostics for nuclear power plant (NPP) condensers, focusing on tube fouling. We utilized the Asherah nuclear power plant simulator (ANS) to compare four methods: Random Forest (RF), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory Neural Network (LSTM). By simulating various fouling scenarios in the ANS, we generated data with different degradation rates under transient operations. The models were trained and tested on these data, with performance evaluated visually and numerically including uncertainty assessment. The LSTM model excelled, exhibiting minimal prediction noise and the most accurate remaining useful life estimates across all degradation levels. Its ability to capture long-term dependencies and produce cleaner outputs makes it a strong candidate, although accurate training data across the entire component lifespan are crucial. The RF model emerged as a robust alternative, providing reliable predictions with high confidence. The FCNN and SVR models, while less effective overall, showed potential under specific conditions. FCNN offers a less complex alternative to LSTM and might benefit from larger datasets. SVR excels in precision when the quality of the training data is high. Furthermore, this study highlights the operational benefits of advanced prognostics in the energy sector and emphasizes the need for further research in NPP condenser health management through real-life experiments.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2024

MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training

Scalable data management is essential for processing large scientific dataset on HPC platforms for distributed deep learning. In-memory distributed storage is preferred for its speed, enabling rapid, random, and frequent data access required by stochastic optimizers. Processes use one-sided or collective communication to fetch remote data, with optimal performance depending on (i) dataset characteristics, (ii) training scale, and (iii) interconnection network. Empirical analysis shows collective communication excels with larger mini-batch sizes and/or fewer processes, whereas one-sided communication outperforms at larger scales. We propose MDLoader, a hybrid in-memory data loader for distributed graph neural network training. MDLoader features a model-driven performance estimator that dynamically selects between one-sided and collective communication at the beginning of training using Tree of Parzen Estimators (TPE). Evaluations on NERSC Perlmutter and OLCF Summit show MDLoader outperforms single-backend loaders by up to 2.83 × and predicts the suitable communication method with 96.3% (Perlmutter) and 94.3% (Summit) success rate.

Bae, Jonghyun↗
DOE OSTI2025

Development and Testing of a new Current-Regulated Arc Modulator for the LINAC

In this study, the performance of a current-regulated arc modulator was investigated with a focus on its role in initiating and sustaining plasma discharge within the Magnetron Body of the LINAC system. The analysis centered on how switching components, circuit topology, and feedback loop architecture influence critical factors such as energy efficiency, discharge stability, and long-term plasma containment. Particular attention was given to variations in pulse termination behavior, as observed through oscilloscope traces, which revealed inconsistencies affecting the duty factor and cathode temperature. These fluctuations have downstream effects on the cesium-coated cathode surface, thereby impacting H⁻ ion production and beam reliability. Simulation-based testing in LTspice was used to evaluate noise suppression techniques and arc current regulation schemes, revealing how optimized snubber networks, improved pulse shaping, and feedback stability can mitigate modulator-induced noise. The results identified hardware level parameters that significantly enhance discharge repeatability and improve overall plasma performance under operational conditions.

Campos, Nathan [Unlisted, US; Fermilab]↗
DOE OSTI2025

SineKAN: Kolmogorov-Arnold Networks using sinusoidal activation functions

Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses learnable activation functions on the edges of the computational graph followed by summation on nodes. The learnable edge activation functions in the original implementation are basis spline functions (B-Spline). Here, we present a model in which learnable grids of B-Spline activation functions are replaced by grids of re-weighted sine functions (SineKAN). We evaluate numerical performance of our model on a benchmark vision task. We show that our model can perform better than or comparable to B-Spline KAN models and an alternative KAN implementation based on periodic cosine and sine functions representing a Fourier Series. Further, we show that SineKAN has numerical accuracy that could scale comparably to dense neural networks (DNNs). Compared to the two baseline KAN models, SineKAN achieves a substantial speed increase at all hidden layer sizes, batch sizes, and depths. Current advantage of DNNs due to hardware and software optimizations are discussed along with theoretical scaling. Additionally, properties of SineKAN compared to other KAN implementations and current limitations are also discussed.

Reinhardt, Eric↗
DOE OSTI2022

Evaluation of Optimal Net Load Management in Microgrids Using Hardware-in-the-Loop Simulation: Preprint

This paper presents the performance evaluation of a net load management (NLM) engine that balances load and generation in an isolated community to power a critical facility after a grid interruption event (e.g., lost a large generation unit). The NLM engine is a central dispatch control system that provides high-speed cost-optimal coordination of a set of net loads (combination of generation and deferrable loads) connected to the same electrical network. The NLM algorithm cost-optimally dispatches the grid-following inverters and deferrable loads based on the demanded power and load priorities, and the grid-forming inverters use droop control to form system voltages and share active and reactive power. A controller-hardware-in-the-loop platform is developed to evaluate the control performance of the NLM algorithm. The experimental results indicate that the NLM engine can achieve the targeted system voltage and frequency and balance load and generation to serve the critical facility.

droop control↗
DOE OSTI2020

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗
DOE OSTI2021

Geometrical-Based Generative Adversarial Network to Enhance Digital Rock Image Quality

X-ray microcomputed tomography (micro-CT) is a common tool for the study of porous media structures and properties. High-quality micro-CT data are required to accurately capture pore structures. Acquiring high-quality micro-CT data, however, is not always possible, owing to application limitations and experimental constraints. Therefore, we propose a geometrical-based generative adversarial network (GAN) to rapidly restore noisy micro-CT images to their clean counterparts. The training data and related ground-truth (GT) data are scanned for 7 min and 9.5 h, respectively. To evaluate the performance of the geometrical-based GAN, a 6003 voxel image that has never been used for training is reconstructed and compared with the corresponding GT image. Histogram matching and linear normalization are implemented to adjust the histogram of the reconstructed image to that of the GT image. A watershed-based segmentation method is then applied to delineate pore and solid phases. Lastly, we measure the Minkowski functionals and petrophysical properties, including absolute permeability, pore size distribution, drainage capillary pressure-saturation curve, and imbibition relative permeability, to estimate the physical accuracy of the denoised image. The results show that the proposed geometrical-based GAN can accurately restore noisy micro-CT data. By reducing the scanning time from 9.5 h to 7 min, the expenditure of collecting micro-CT can be decreased significantly. This is particularly important for applications where time-lapse images of a dynamic process are required, high-throughput imaging is necessary for real-time data analysis, or where the quantification of large sample volumes is required.

58 GEOSCIENCES↗
DOE OSTI2023

Deep learning for morphological identification of extended radio galaxies using weak labels

Abstract The present work discusses the use of a weakly-supervised deep learning algorithm that reduces the cost of labelling pixel-level masks for complex radio galaxies with multiple components. The algorithm is trained on weak class-level labels of radio galaxies to get class activation maps (CAMs). The CAMs are further refined using an inter-pixel relations network (IRNet) to get instance segmentation masks over radio galaxies and the positions of their infrared hosts. We use data from the Australian Square Kilometre Array Pathfinder (ASKAP) telescope, specifically the Evolutionary Map of the Universe (EMU) Pilot Survey, which covered a sky area of 270 square degrees with an RMS sensitivity of 25–35 $\mu$ Jy beam $^{-1}$ . We demonstrate that weakly-supervised deep learning algorithms can achieve high accuracy in predicting pixel-level information, including masks for the extended radio emission encapsulating all galaxy components and the positions of the infrared host galaxies. We evaluate the performance of our method using mean Average Precision (mAP) across multiple classes at a standard intersection over union (IoU) threshold of 0.5. We show that the model achieves a mAP $_{50}$ of 67.5% and 76.8% for radio masks and infrared host positions, respectively. The network architecture can be found at the following link: https://github.com/Nikhel1/Gal-CAM

Astronomy & Astrophysics↗
DOE OSTI2024

Spectral Data Fusion From Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and X-ray Fluorescence (XRF) Analyzers for Improved Detection of Cerium in a Simulated Dispersal Accident

Here, this work implements a mid-level data fusion methodology on spectral data from handheld X-ray fluorescence and laser-induced breakdown spectroscopy analyzers to quantify plutonium surrogate (CeO 2 ) contamination in soil samples for the first time. Spectral data from each analyzer were used independently to train supervised machine learning regressions to predict Ce concentration. Fused features from both data sets were then used to train the same models, comparing prediction performance by evaluating model precision and sensitivity. Fusing principal component scores from the two sensors yielded an order of magnitude improvement in precision and sensitivity of predictions made with an artificial neural network, compared to predictions made by models trained on independent sensor data. As a result, a boosted ensemble trained on the fused spectral features yielded an ideal predictor with root-mean-squared error on the order of 10 –6 and calculated limit of detection order 10 –5 wt %.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Device Feasibility Analysis of Multi-level FeFETs for Neuromorphic Computing

As an emerging non-volatile memory device technology, Ferroelectric Field-Effect Transistors (FeFETs) can enable low-power, adaptive intelligent system design. However, device dimension and operating voltage dependent reliability issues of scaled FeFETs can ultimately lead to degraded performance in solving machine learning tasks. In this article, detailed experimental characterization of FeFET devices of different dimensions have been carried out to explicitly evaluate the non-ideal behavior in device conductance programming properties like number of programming states, cycle-to-cycle (C2C) variations, device-to-device (D2D) variations, and state retention. A hardware-aware software simulation approach has been adopted to capture the adversarial effects of the non-idealities on recognition accuracy through algorithm-level performance assessment by including them in NeuroSim, a popular neural network hardware simulator, to execute a neural network model considering all other hardware constraints. With the added non-idealities, significant accuracy degradation has been observed compared to the ideal scenarios where D2D variations play the most critical role. Thereafter, feasibility of a variation-aware training method has been evaluated to tackle the accuracy drop.

42 ENGINEERING↗
DOE OSTI2024

Scaling neural simulations in STACS

Abstract As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on Simulation Tool for Asynchronous Cortical Streams (STACS), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown to be effective tools for solving both forward and inverse problems of partial differential equations (PDEs). PINNs embed the PDEs into the loss of the neural network using automatic differentiation, and this PDE loss is evaluated at a set of scattered spatio-temporal points (called residual points). The location and distribution of these residual points are highly important to the performance of PINNs. However, in the existing studies on PINNs, only a few simple residual point sampling methods have mainly been used. Here, we present a comprehensive study of two categories of sampling for PINNs: non-adaptive uniform sampling and adaptive nonuniform sampling. We consider six uniform sampling methods, including (1) equispaced uniform grid, (2) uniformly random sampling, (3) Latin hypercube sampling, (4) Halton sequence, (5) Hammersley sequence, and (6) Sobol sequence. We also consider a resampling strategy for uniform sampling. To improve the sampling efficiency and the accuracy of PINNs, we propose two new residual-based adaptive sampling methods: residual-based adaptive distribution (RAD) and residual-based adaptive refinement with distribution (RAR-D), which dynamically improve the distribution of residual points based on the PDE residuals during training. Hence, we have considered a total of 10 different sampling methods, including six non-adaptive uniform sampling, uniform sampling with resampling, two proposed adaptive sampling, and an existing adaptive sampling. We extensively tested the performance of these sampling methods for four forward problems and two inverse problems in many setups. Our numerical results presented in this study are summarized from more than 6000 simulations of PINNs. Here, we show that the proposed adaptive sampling methods of RAD and RAR-D significantly improve the accuracy of PINNs with fewer residual points for both forward and inverse problems. Furthermore, the results obtained in this study can also be used as a practical guideline in choosing sampling methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Neural Architecture Search Benchmarks: Insights and Survey

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

An a priori evaluation of a principal component and artificial neural network based combustion model in diesel engine conditions

A principal component analysis (PCA) and artificial neural network (ANN) based chemistry tabulation approach is presented. ANNs are used to map the thermochemical state onto a low-dimensional manifold consisting of five control variables that have been identified using PCA. Three canonical configurations are considered to train the PCA-ANN model: a series of homogeneous reactors, a nonpremixed flamelet, and a two-dimensional lifted flame. The performance of the model in predicting the thermochemical manifold of a spatially-developing turbulent jet flame in diesel engine thermochemical conditions is a priori evaluated using direct numerical simulation (DNS) data. The PCA-ANN approach is compared with a conventional tabulation approach (tabulation using ad hoc defined control variables and linear interpolation). The PCA-ANN model provides higher accuracy and requires several orders of magnitude less memory. Here, these observations indicate that the PCA-ANN model is superior for chemistry tabulation, especially for modelling complex chemistries that present multiple combustion modes as observed in diesel combustion. The performance of the PCA-ANN model is then compared to the optimal estimator, i.e. the conditional mean from the DNS. The results indicate that the PCA-ANN model gives high prediction accuracy, comparable to the optimal estimator, especially for major species and the thermophysical properties. Higher errors are observed for the minor species and reaction rate predictions when compared to the optimal estimator. It is shown that the prediction of minor species and reaction rates can be improved by using training data that exhibits a variation of parameters as observed in the turbulent flame. The output of the ANN is analysed to assess mass conservation. It is observed that the ANN incurs a mean absolute error of 0.05% in mass conservation. Furthermore, it is demonstrated that this error can be reduced by modifying the cost function of the ANN to penalise for deviation from mass conservation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗