Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “DATA NETWORKS”

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 1,369 records · Page 76

Data-Driven Method for Groundwater-Level Mapping and Monitoring-Well Network Optimization at Hanford

This report summarizes the initial results and outcomes of a physics-informed, data-driven groundwater level (GWL) mapping capability for the Hanford Site. GWL mapping at Hanford is typically conducted annually and requires a significant amount of computational and expert resources, and it does not allow assessment of the informational value of specific monitoring wells. The proposed method produces spatially and temporally resolved fields consistent with sparse, irregularly sampled, and nonuniformly distributed well measurements. Implemented successfully, this capability will allow rapid mapping of groundwater levels and provide an opportunity to optimize monitoring activities (both location and sampling frequency) based on data information value evaluation. The approach integrates a diffusion-based generative model – trained on MODFLOW simulation data from the Plateau-to-River (P2R) model – with score-based data assimilation (SDA), allowing observation-conditioned mapping without retraining for each monitoring-network layout.

54 ENVIRONMENTAL SCIENCES↗

The Feasibility of Moving PMU Data in the Future Power Grid

The power grid is a complex network connecting electricity providers with their consumers. With an increasing consumer base requiring more resources and the requirement to integrate significant renewable sources, maintaining the network requires new and innovative management solutions. To manage this complexity and provide precise, real-time views of the grid, Phasor Measurement Units (PMUs) are undergoing widespread deployment. These units provide measurements as often as 60 times per second, with an accurate time identifier attached to each reading, enabling real-time monitoring of the network. However, this new capability generates much more data than the current infrastructure is designed to handle. With the expectation that there will eventually be tens of thousands of PMUs monitoring the transmission lines, the power community is looking towards accumulating multiple terabytes of data per day - several orders of magnitude beyond current data acquisition rates. This has led to questions being raised in the power community about whether or not a significant research effort is required to effectively transfer the volume of information generated by these new data streams. This paper answers that question by comparing a worst-case data generation scenario with several alternative networking protocols and historical trends in protocol advancement. Based on this analysis we are able to conclude that transferring the information between the PMUs and the resulting data repositories is feasible. We recognize that there are issues beyond transferring the data that need to be addressed such as effective access to historical data, data transfer latency, cyber security, and data analysis. There is also an extensive engineering trade-off that the power companies will need to make to decide the best mix of networking protocols for their particular PMU deployments, since that requires significant assumptions about proprietary information including deployment cost, deployment schedules, PMU locations, and available resources.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Using architecture information and real-time resource state to reduce power consumption and communication costs in parallel applications.

As computer systems grow in both size and complexity, the need for applications and run-time systems to adjust to their dynamic environment also grows. The goal of the RAAMP LDRD was to combine static architecture information and real-time system state with algorithms to conserve power, reduce communication costs, and avoid network contention. We devel- oped new data collection and aggregation tools to extract static hardware information (e.g., node/core hierarchy, network routing) as well as real-time performance data (e.g., CPU uti- lization, power consumption, memory bandwidth saturation, percentage of used bandwidth, number of network stalls). We created application interfaces that allowed this data to be used easily by algorithms. Finally, we demonstrated the benefit of integrating system and application information for two use cases. The first used real-time power consumption and memory bandwidth saturation data to throttle concurrency to save power without increasing application execution time. The second used static or real-time network traffic information to reduce or avoid network congestion by remapping MPI tasks to allocated processors. Results from our work are summarized in this report; more details are available in our publications [2, 6, 14, 16, 22, 29, 38, 44, 51, 54].

Brandt, James M.↗

Reconstructing Ly$α$ Fields from Low-resolution Hydrodynamical Simulations with Deep Learning

Hydrodynamical cosmological simulations are a powerful tool for accurately predicting the properties of the intergalactic medium (IGM) and for producing mock skies that can be compared against observational data. However, the need to resolve density fluctuation in the IGM puts a stringent requirement on the resolution of such simulations, which in turn limits the volumes that can be modeled, even on the most powerful supercomputers. In this work, we present a novel modeling method that combines physics-driven simulations with data-driven generative neural networks to produce outputs that are qualitatively and statistically close to the outputs of hydrodynamical simulations employing eight times higher resolution. We show that the Ly$α$ flux field, as well as the underlying hydrodynamic fields, have greatly improved statistical fidelity over a low-resolution simulation. Importantly, the design of our neural network allows for sampling multiple realizations from a given input, enabling us to quantify the model uncertainty. Using test data, we demonstrate that this model uncertainty correlates well with the true error of the Ly$α$ flux prediction. Ultimately, our approach allows for training on small simulation volumes and applying it to much larger ones, opening the door to producing accurate Ly$α$ mock skies in volumes of Hubble size, as will be probed with DESI and future spectroscopic sky surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

Gene network analysis of poplar root transcriptome in response to drought stress identifies a PtaJAZ3PtaRAP2.6-centered hierarchical network

Using time-series transcriptomic data from poplar roots undergoing polyethylene glycol (PEG)-induced drought stress, we built a genetic network model of the involved putative molecular responses. We found that the network resembled a hierarchical structure. The highest hierarchical level in this structure is occupied by 9 genes, which we called superhubs because they were primarily connected to 18 hub genes, which are then connected to 2,934 terminal genes. We were only able to regenerate transgenic plants overexpressing two of the superhubs, suggesting that the majority of the superhubs might interfere with the regeneration process and did not allow recovery of transgenic plants. The two superhubs encode proteins with closest homology to JAZ3 and RAP2.6 genes of Arabidopsis and were consequently named PtaJAZ3 and PtaRAP2.6. PtaJAZ3 and PtaRAP2.6 overexpressing transgenic lines showed a significant increase in both root elongation and lateral root proliferation and these responses were specific for the drought stress conditions and were highly correlated with the levels of overexpression of the transgenes. Several lines of evidence suggest of regulatory interactions between the two superhubs. Both superhubs were significantly induced by methyl jasmonate (MeJA). Because jasmonate signaling involves ubiquitin-mediated proteasome degradation, treatment with proteasome inhibitor abolished the MeJA induction for both genes. PtaRAP2.6 was upregulated in PtaJAZ3 transgenics but PtaJAZ3 expression was not affected in the PtaRAP2.6 overexpressors. The discovery of the two genes and further future insights into the associated mechanisms can lead to improved understanding and novel approaches to regulate root architecture in relation to drought stress.

59 BASIC BIOLOGICAL SCIENCES↗

Constructing a Network Fundamental Diagram: Synthetic Origin–Destination Approach

The Network Fundamental Diagram (NFD) is significantly used in traffic monitoring and control. One obstacle to a wider application of NFDs in network control is the difficulty of obtaining data from all vehicles traveling in the network to construct an accurate NFD. One solution is to estimate the NFD using data from only a fraction of vehicles (i.e., probe vehicles), where the probe vehicle market penetration rate (MPR) needs to be estimated. A previous study conducted by the authors demonstrated that a distance or time weighted harmonic mean was needed to estimate the flow- and density-based MPRs, respectively using a pairing k-mean clustering approach. This paper introduces another approach that utilizes probe vehicle and observed link volume data to estimate the MPR. A heuristic model is proposed to identify the optimum locations from which to collect link traffic volume data for use in the MPR estimation. The estimated MPR can then be used to construct the NFD. Results show that these models can accurately estimate the NFD with limited probe vehicle and link traffic volume data. Accordingly, the models can be used in the field to estimate the NFD using readily available loop detector and probe vehicle data. The ideal locations for traffic volume data collection can also be proactively chosen to generate optimum estimation results. Since the models proposed here show no significant gains with an increased magnitude of collected data after a certain threshold, they will be helpful, particularly when large-scale data collection is not affordable or realistic.

42 ENGINEERING↗

CONSTRUCTING A NETWORK FUNDAMENTAL DIAGRAM: A SYNTHETIC ORIGIN-DESTINATION APPROACH

The Network Fundamental Diagram (NFD) is increasingly used in traffic monitoring and control. One obstacle to a wider application of NFDs in network control is the difficulty of obtaining data from all vehicles traveling in the network to construct an accurate NFD. One solution is to estimate the NFD using data from only a fraction of vehicles (i.e., probe vehicles), where the probe vehicle market penetration rate (MPR) needs to be estimated. A previous study conducted by the authors demonstrated that a distance or time weighted harmonic mean was needed to estimate the flow- and density-based MPRs, respectively using a pairing k-mean clustering approach. This paper proposes another approach that utilizes probe vehicle and observed link volume data to estimate the MPR. A heuristic model is proposed to identify the optimum locations from which to collect link traffic volume data for use in the MPR estimation. The estimated MPR can then be used to construct the NFD. Results show that these models can accurately estimate the NFD with limited probe vehicle and link traffic volume data. Accordingly, the models can be used in the field to estimate the NFD using readily available loop detector and probe vehicle data. The ideal locations for traffic volume data collection can also be proactively chosen to generate optimum estimation results. Since the models proposed here show no significant gains with an increased magnitude of collected data after a certain threshold, they will be helpful, particularly when large-scale data collection is not affordable or realistic.

Spatial Analysis, Market Penetration Rate, NFD, Sy↗

Evaluating performance of different generative adversarial networks for large-scale building power demand prediction

We report as an unsupervised-learning data-driven model, Generative Adversarial Networks (GANs) have recently attracted a lot of attention for various applications. There is potential to apply GANs for large-scale building power demand prediction, which is needed for power grid operation. However, there are many GAN variations and it is unclear which GAN is suitable for this application. To answer this question, this paper identifies five promising GANs (Original GAN, cGAN, SGAN, InfoGAN, and ACGAN) and evaluates their performance for predicting building power demand at a large scale. Physics-based building energy models are developed to generate training and reference data. A new evaluation indicator that combines accuracy and reproducibility is proposed to evaluate the performance of different GANs in predicting building power demand. The results show that SGAN and InfoGAN are not suitable because they cannot control the number of generated building samples for different building types. The prediction performance among the Original GAN, cGAN, and ACGAN can vary depending on training sample sizes and number of building types. If the training sample size is sufficiently large, Original GAN and cGAN can predict building power demand more accurately than ACGAN with the same number of samples. If training samples are limited, Original GAN provides better accuracy than cGAN and ACGAN. When the number of building types increase, the prediction accuracy increases for cGAN, decreases for ACGAN, and remains the same for Original GAN. As a result, cGAN and Original GAN are recommended for large-scale building power demand prediction.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Integrated, Coordinated, Open, and Networked (ICON) Science to Advance the Geosciences: Introduction and Synthesis of a Special Collection of Commentary Articles

Abstract The sciences struggle to integrate across disciplines, coordinate across data generation and modeling activities, produce connected open data, and build strong networks to engage stakeholders within and beyond the scientific community. The American Geophysical Union (AGU) is divided into 25 sections intended to encompass the breadth of the geosciences. Here, we introduce a special collection of commentary articles spanning 19 AGU sections on challenges and opportunities associated with the use of ICON science principles. These principles focus on research intentionally designed to be Integrated, Coordinated, Open, and Networked (ICON) with the goal of maximizing mutual benefit (among stakeholders) and cross‐system transferability of science outcomes. This article (a) summarizes the ICON principles; (b) discusses the crowdsourced approach to creating the collection; (c) explores insights from across the articles; and (d) proposes steps forward. There were common themes among the commentary articles, including broad agreement that the benefits of using ICON principles outweigh the costs, but that using ICON principles has important risks that need to be understood and mitigated. It was also clear that the ICON principles are not monolithic or static, but should instead be considered a heuristic tool that can and should be modified to meet changing needs. As a whole, the collection is intended as a resource for scientists pursuing ICON science and represents an important inflection point in which the geosciences community has come together to offer insights into ICON principles as a unified approach for improving how science is done across the geosciences and beyond.

Goldman, A. E.↗

Development of Predictive Models for Advanced Reactor Autonomous Control

Advanced reactor designs including microreactors and small modular reactors will contribute to the clean production of cheap energy, and autonomous control for advanced reactors is an appealing option for reducing cost. However, there is a lack of industry experience applying autonomous control for advanced nuclear reactors. To accelerate the development and industry acceptance of autonomous control software for nuclear reactors, we aim to demonstrate autonomous control of the Purdue University research reactor (PUR-1) using INL-developed model predictive control (MPC) methods. To prepare for this demonstration, data-driven predictive models based on process data collected from PUR-1 have been developed and integrated with MPC and used to control a physics-based model of PUR-1. A data-driven dynamics model and a gated recurrent unit (GRU) network were both trained on process data from PUR-1. The dynamics model was shown to effectively control the reactor model with MPC when provided reactivity as a control variable but failed to control the model through the control rod positions. The GRU network produced more accurate predictions than the dynamics model when evaluated on operational data, and future work will include the evaluation of the GRU network in the controller.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

Suppressing simulation bias in multi-modal data using transfer learning

Abstract Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is multi-dimensional. Simulations, however, often suffer from an inherent bias. Estimation of this bias may be poorly constrained not only because of data sparsity, but also because traditional predictive models fit only one type of observed outputs, such as scalars or images, instead of all available output data modalities, which might have been acquired and simulated at great cost. To break this limitation and open up the path for multi-modal calibration, we propose to combine a novel, transfer learning technique for suppressing the bias with recent developments in deep learning, which allow building predictive models with multi-modal outputs. First, we train an initial neural network model on simulated data to learn important correlations between different output modalities and between simulation inputs and outputs. Then, the model is partially retrained, or transfer learned, to fit the experiments; a method that has never been implemented in this type of architecture. Using fewer than 10 inertial confinement fusion experiments for training, transfer learning systematically improves the simulation predictions while a simple output calibration, which we design as a baseline, makes the predictions worse. We also offer extensive cross-validation with real and carefully designed synthetic data. The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Image-driven discriminative and generative machine learning algorithms for establishing microstructure–processing relationships

We investigate methods of microstructure representation for the purpose of predicting processing condition from microstructure image data. A binary alloy that is currently under development as a nuclear fuel was studied for the purpose of developing an improved machine learning approach to image recognition, characterization, and building predictive capabilities linking microstructure to processing conditions. Here, we test different microstructure representations and evaluate model performance based on classification accuracy. A classification accuracy of 95.8% was achieved fordistinguishing between micrographs corresponding to ten different thermo-mechanical material processing conditions.We find that our newly developed microstructure representation describes image data well, and the traditional approachof utilizing area fractions of different phases is insufficient for distinguishing between multiple classes using a relativelysmall, imbalanced original data set of 272 images. To explore the applicability of generative methods for supplementing such limited data sets, generative adversarial networks were trained to generate artificial microstructure images. Two different generative networks were trained and tested to assess performance. Challenges and best practices associated with applying machine learning to limited microstructure image data sets is also discussed. Our work has implications for quantitative microstructure analysis, and development of microstructure-processing relationships in limited data sets typical of metallurgical process design studies.

36 MATERIALS SCIENCE↗

Device and method for constructing and displaying high quality images from imaging data by transforming a data structure utilizing machine learning techniques

Constructing a computer image from raw imaging data or encoded imaging data by transforming a first data structure in which the raw imaging data or the encoded imaging data is stored into a second data structure storing reorganized imaging data. The raw imaging data or the encoded imaging data is received, stored in the first data structure. The computer reorganizes the raw imaging data or the encoded imaging data into the reorganized data and stores the reorganized data in the second data structure, which is a multi-dimensional array having subarrays containing local information needed by a convolutional neural network for processing the reorganized data. Other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data. The computer also processes the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed.

Korbin, John P.↗

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗

Advanced Performance Modeling with Combined Passive and Active Monitoring

To improve the efficiency of resource utilization and scheduling of scientific data transfers on high-speed networks, the "Advanced Performance Modeling with combined passive and active monitoring" (APM) project investigates and models a general-purpose, reusable and expandable network performance estimation framework. The predictive estimation model and the framework will be helpful in optimizing the performance and utilization of networks as well as sharing resources with predictable performance for scientific collaborations, especially in data intensive applications. Our prediction model utilizes historical network performance information from various network activity logs as well as live streaming measurements from network peering devices. Historical network performance information is used without putting extra load on the resources by active measurement collection. Performance measurements collected by active probing is used judiciously for improving the accuracy of predictions.

97 MATHEMATICS AND COMPUTING↗

App2Net: Moving App Functions to Network & a Case Study on Low-latency Feedback

Recent advances in programmable networks enable custom processing of data at hundreds of gigabits per second. These advances can boost the performance of many distributed applications. Yet the high-level languages used by application developers are different from the data plane programming languages (such as P4 and NPL) used by network equipment. This language barrier slows innovation. Our hourglass-shaped architectural solution aims to lower this language barrier. This enables the application developer community to leverage programmable networks for achieving better performance. In this paper we propose a JSON-based intermediate representation to bridge the gap between applications and in-network computing. We demonstrate an instance of the solution in the context of a low-latency feedback application that enables SQL-based data filtering in a P4-based programmable environment. We also present a prototype compiler to convert an intermediate representation in JSON to P4 source.

Sankaran, Ganesh↗

Data Driven Online Learning of Power System Dynamics

With the advancement of sensing and communication in power networks, high-frequency real-time data from a power network can be used as a resource to develop better monitoring capabilities. In this work, a systematic approach based on data-driven operator theoretic methods involving Koopman operator is proposed for the online identification of power system dynamics. In particular, a new algorithm is provided, which unlike any previously existing algorithms, updates the Koopman operator iteratively as new data points are acquired. The proposed algorithm has three advantages: a) allows for real-time monitoring of the power system dynamics b) linear power system dynamics (this linear system is usually in a higher dimensional feature space and is not same as linearization of the underlying nonlinear dynamics) and c) computationally fast and less intensive when compared to the popular Extended Dynamic Mode Decomposition (EDMD) algorithm. The efficiency of the proposed algorithm is illustrated on an IEEE 9 bus system using synthetic data from the nonlinear model and on IEEE 39 bus system using synthetic data from the linearized model.

Sinha, Subhrajit↗

A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence

In the present study, we investigate different data-driven parameterizations for large eddy simulation of two-dimensional turbulence in the a priori settings. These models utilize resolved flow field variables on the coarser grid to estimate the subgrid-scale stresses. We use data-driven closure models based on localized learning that employs a multilayer feedforward artificial neural network with point-to-point mapping and neighboring stencil data mapping, and convolutional neural network fed by data snapshots of the whole domain. The performance of these data-driven closure models is measured through a probability density function and is compared with the dynamic Smagorinksy model (DSM). The quantitative performance is evaluated using the cross-correlation coefficient between the true and predicted stresses. We analyze different frameworks in terms of the amount of training data, selection of input and output features, their characteristics in modeling with accuracy, and training and deployment computational time. We also demonstrate computational gain that can be achieved using the intelligent eddy viscosity model that learns eddy viscosity computed by the DSM instead of subgrid-scale stresses. Here, we detail the hyperparameters optimization of these models using the grid search algorithm.

42 ENGINEERING↗