Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network reduction”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Quantifying soil moisture impacts on light use efficiency across biomes

Terrestrial primary productivity and carbon cycle impacts of droughts are commonly quantified using vapour pressure deficit (VPD) data and remotely sensed greenness, without accounting for soil moisture. However, soil moisture limitation is known to strongly affect plant physiology. Here, we investigate light use efficiency, the ratio of gross primary productivity (GPP) to absorbed light. We derive its fractional reduction due to soil moisture (fLUE), separated from VPD and greenness changes, using artificial neural networks trained on eddy covariance data, multiple soil moisture datasets and remotely sensed greenness. This reveals substantial impacts of soil moisture alone that reduce GPP by up to 40% at sites located in sub-humid, semi-arid or arid regions. For sites in relatively moist climates, we find, paradoxically, a muted fLUE response to drying soil, but reduced fLUE under wet conditions. fLUE identifies substantial drought impacts that are not captured when relying solely on VPD and greenness changes and, when seasonally recurring, are missed by traditional, anomaly-based drought indices. Counter to common assumptions, fLUE reductions are largest in drought-deciduous vegetation, including grasslands. Our results highlight the necessity to account for soil moisture limitation in terrestrial primary productivity data products, especially for drought-related assessments.

vapour pressure deficit (VPD)↗
DOE OSTI2019

Vehicle energy consumption estimation using large scale simulations and machine learning methods

Vehicle energy consumption and powertrain operations for future vehicle powertrain technologies are predicted through full-vehicle simulations using Autonomie, a simulation tool developed at Argonne National Laboratory. Over 1 million vehicles, with different powertrain types (conventional and numerous electrified powertrains) and component technologies (advanced engines, batteries, electrical machines, light weighting) are simulated for outputs including vehicle fuel economy and cost. Despite the ability of Autonomic to predict fuel economy given various combination of vehicle inputs, the full-vehicle simulation is very time-consuming. It takes approximately 84 h to simulate for 33,060 vehicles even using distributed computing on a cluster of 128 worker nodes. Moreover, Autonomic is unable to populate a continuous output space through simulation since it only yields outputs with discrete values instead of an input-output relation. This paper proposes a novel large-scale learning and prediction process (LSLPP) via machine learning approaches to answer the need for a continuous space of vehicle fuel economy and a more efficient simulation process. By learning in a supervised fashion to discover structures in data, the machine learning approaches seek to train a model that can explain the data with which we can perform prediction over unseen data. As such, we are able to accomplish analytic continuation on the current discrete space of simulation results. In addition, we present a random sampling -based numerosity reduction algorithm incorporated in LSLPP that reduces simulation runs and improves efficiency of data procurement. We analytically derive a theoretical bound in order to guarantee the effectiveness of our algorithm. We also compare random sampling to stratified sampling and suggest sampling strategies. A user-friendly tool is developed to support the process. Our experimental results confirm that the proposed LSLPP is able to greatly accelerate prediction and analysis of vehicle fuel economy. The output of this study is used by the US government to evaluate the impact of its R&D funding on energy security and CO 2 emission as well as for the setting of Corporate Average Fuel Economy (CAFE) standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

MADE3D™ (Manufacturing and Additive Design of Electric Machines Enabled by Three-Dimensional Printing) [SWR-20-70]

The MADE3D™ software uses advanced neural networks for realizing novel high torque density electric machine designs with desired functional specifications not limited to but including torque, magnetic loading, and mass. This software allows for a reduction in cost of design by using next-generation computational resources including the cloud while still maintaining high accuracy. The design of the neural networks allows for exploration of large design space and possibilities to find more optimal designs and accommodate new manufacturing technologies like 3D printing.

Sethuraman, Latha↗
NASA NTRS1991

Depth-size tradeoffs for neural computation

The tradeoffs between the depth (i.e., the time for parallel computation) and the size (i.e., the number of threshold gates) in neural networks are studied. The authors focus the study on the neural computations of symmetric Boolean functions and some arithmetic functions. It is shown that a significant reduction in the size is possible for symmetric functions and some arithmetic functions, at the expense of a small constant increase in depth. In the process, several neural networks which have the minimum size among all the known constructions have been developed. Results on implementing symmetric functions can be used to improve results about arbitrary Boolean functions. In particular, It is shown that any Boolean function can be computed in a depth-3 neural network with O(2n/2) threshold gates; it is also proven that a minimum number of threshold gates are required.

Siu, Kai-Yeung↗
NASA NTRS2011

The Impact of Traffic Prioritization on Deep Space Network Mission Traffic

A select number of missions supported by NASA's Deep Space Network (DSN) are demanding very high data rates. For example, the Kepler Mission was launched March 7, 2009 and at that time required the highest data rate of any NASA mission, with maximum rates of 4.33 Mb/s being provided via Ka band downlinks. The James Webb Space Telescope will require a maximum 28 Mb/s science downlink data rate also using Ka band links; as of this writing the launch is scheduled for a June 2014 launch. The Lunar Reconnaissance Orbiter, launched June 18, 2009, has demonstrated data rates at 100 Mb/s at lunar-Earth distances using NASA's Near Earth Network (NEN) and K-band. As further advances are made in high data rate space telecommunications, particularly with emerging optical systems, it is expected that large surges in demand on the supporting ground systems will ensue. A performance analysis of the impact of high variance in demand has been conducted using our Multi-mission Advanced Communications Hybrid Environment for Test and Evaluation (MACHETE) simulation tool. A comparison is made regarding the incorporation of Quality of Service (QoS) mechanisms and the resulting ground-to-ground Wide Area Network (WAN) bandwidth necessary to meet latency requirements across different user missions. It is shown that substantial reduction in WAN bandwidth may be realized through QoS techniques when low data rate users with low-latency needs are mixed with high data rate users having delay-tolerant traffic.

prioritization↗
DOE OSTI2015

SMAC: A soft MAC to reduce control overhead and latency in CDMA-based AMI networks

The utilization of state-of-the-art 3G cellular CDMA technologies in a utility owned AMI network results in a large amount of control traffic relative to data traffic, increases the average packet delay and hence are not an appropriate choice for smart grid distribution applications. Like the CDG, we consider a utility owned cellular like CDMA network for smart grid distribution applications and classify the distribution smart grid data as scheduled data and random data. Also, we propose SMAC protocol, which changes its mode of operation based on the type of the data being collected to reduce the data collection latency and control overhead when compared to 3G cellular CDMA2000 MAC. The reduction in the data collection latency and control overhead aids in increasing the number of smart meters served by a base station within the periodic data collection interval, which further reduces the number of base stations needed by a utility or reduces the bandwidth needed to collect data from all the smart meters. The reduction in the number of base stations and/or the reduction in the data transmission bandwidth reduces the CAPital EXpenditure (CAPEX) and OPerational EXpenditure (OPEX) of the AMI network. Finally, the proposed SMAC protocol is analyzed using markov chain, analytical expressions for average throughput and average packet delay are derived, and simulation results are also provided to verify the analysis.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

The Impact of Traffic Prioritization on Deep Space Network Mission Traffic

A select number of missions supported by NASA's Deep Space Network (DSN) are demanding very high data rates. For example, the Kepler Mission was launched March 7, 2009 and at that time required the highest data rate of any NASA mission, with maximum rates of 4.33 Mb/s being provided via Ka band downlinks. The James Webb Space Telescope will require a maximum 28 Mb/s science downlink data rate also using Ka band links; as of this writing the launch is scheduled for a June 2014 launch. The Lunar Reconnaissance Orbiter, launched June 18, 2009, has demonstrated data rates at 100 Mb/s at lunar-Earth distances using NASA's Near Earth Network (NEN) and K-band. As further advances are made in high data rate space telecommunications, particularly with emerging optical systems, it is expected that large surges in demand on the supporting ground systems will ensue. A performance analysis of the impact of high variance in demand has been conducted using our Multi-mission Advanced Communications Hybrid Environment for Test and Evaluation (MACHETE) simulation tool. A comparison is made regarding the incorporation of Quality of Service (QoS) mechanisms and the resulting ground-to-ground Wide Area Network (WAN) bandwidth necessary to meet latency requirements across different user missions. It is shown that substantial reduction in WAN bandwidth may be realized through QoS techniques when low data rate users with low-latency needs are mixed with high data rate users having delay-tolerant traffic.

quality of service↗
DOE OSTI2013

HPNAIDM: The High-Performance Network Anomaly/Intrusion Detection and Mitigation System

Identifying traffic anomalies and attacks rapidly and accurately is critical for large network operators. With the rapid growth of network bandwidth, such as the next generation DOE UltraScience Network, and fast emergence of new attacks/virus/worms, existing network intrusion detection systems (IDS) are insufficient because they: • Are mostly host-based and not scalable to high-performance networks; • Are mostly signature-based and unable to adaptively recognize flow-level unknown attacks; • Cannot differentiate malicious events from the unintentional anomalies. To address these challenges, we proposed and developed a new paradigm called high-performance network anomaly/intrustion detection and mitigation (HPNAIDM) system. The new paradigm is significantly different from existing IDSes with the following features (research thrusts). • Online traffic recording and analysis on high-speed networks; • Online adaptive flow-level anomaly/intrusion detection and mitigation; • Integrated approach for false positive reduction. Our research prototype and evaluation demonstrate that the HPNAIDM system is highly effective and economically feasible. Beyond satisfying the pre-set goals, we even exceed that significantly (see more details in the next section). Overall, our project harvested 23 publications (2 book chapters, 6 journal papers and 15 peer-reviewed conference/workshop papers). Besides, we built a website for technique dissemination, which hosts two system prototype release to the research community. We also filed a patent application and developed strong international and domestic collaborations which span both academia and industry.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Deep multiscale model learning

The objective of this article is to design novel multi-layer neural networks for multiscale simulations of flows taking into account the observed fine data and physical modeling concepts. Our approaches use deep learning techniques combined with local multiscale model reduction methodologies to predict flow dynamics. Using reduced-order model concepts is important for constructing robust deep learning architectures since the reduced-order models provide fewer degrees of freedom. We consider flow dynamics in porous media as multi-layer networks in this work. More precisely, the solution (e.g., pressures and saturation) at the time instant n+1 depends on the solution at the time instant n and input parameters, such as permeability fields, forcing terms, and initial conditions. One can regard the solution as a multi-layer network, where each layer, in general, is a nonlinear forward map and the number of layers relates to the internal time steps. We will rely on rigorous model reduction concepts to define unknowns and connections between layers. It is critical to use reduced-order models for this purpose, which will identify the regions of influence and the appropriate number of variables. Furthermore, due to the lack of available observed fine data, the reduced-order model can provide us sufficient inexpensive data as needed. The designed deep neural network will be trained using both coarse simulation data which is obtained from the reduced-order model and observed fine data. We will present the main ingredients of our approach and numerical examples. Numerical results show that using deep learning with data generated from multiscale models as well as available observed fine data, we can obtain an improved forward map which can better approximate the fine scale model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Electrochemical Reduction of Ag 2 VP 2 O 8 Composite Electrodes Visualized via In situ Energy Dispersive X-ray Diffraction (EDXRD). Unexpected Conductive Additive Effects

In our study, we characterize the deposition of silver metal nanoparticles formed during discharge of Li/Ag 2 VP 2 O 8 cells with composite cathodes containing conductive carbon additive. Using in situ energy dispersive X-ray diffraction (EDXRD) of an intact battery, the location and distribution of silver metal nanoparticles generated upon reduction-displacement deposition within an Ag 2 VP 2 O 8 cathode containing a pre-existing percolation network can be observed for the first time. Our study yielded unexpected results where higher rate initial discharge generated a more effective conductive matrix. This stands in contrast to cells with cathodes with no conductive additive where a low rate initial discharge proved more effective. Our results provide evidence that using conductive additives in conjunction with an in situ reduction-displacement deposition of silver metal provides a path toward the ultimate goal of complete electrical contact and full utilization of all electroactive particles.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Meeting IRA Apprenticeship Requirements

A session at RE+ presented solar industry employers with an introduction to registered apprenticeships and apprenticeship types, and a brief update on Inflation Reduction Act (IRA) apprenticeship requirements for tax credits, followed by an opportunity for structured networking to foster connections with potential partners in the apprenticeship space.

14 SOLAR ENERGY↗
NASA NTRS1992

Neural network training by integration of adjoint systems of equations forward in time

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically, it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved, but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. The trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Toomarian, Nikzad↗
NASA NTRS1999

Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Toomarian, Nikzad↗
DOE OSTI2022

A differentiable approach to the maximum independent set problem using dataless neural networks

The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approaches generally rely on supervised learning by leveraging datasets of the combinatorial structures of interest drawn from some distribution of problem instances. Reinforcement learning has also been employed to find such structures. Here, in this paper, we propose a different approach in that no data is required for training the neural networks that produce the solution. In this sense, what we present is not a machine learning solution, but rather one that is dependent on neural networks and where backpropagation is applied to a loss function defined by the structure of the neural network architecture as opposed to a training dataset. In particular, we reduce the popular combinatorial optimization problem of finding a maximum independent set to a neural network and employ a dataless training scheme to refine the parameters of the network such that those parameters yield the structure of interest. Additionally, we propose a universal graph reduction procedure to handle large-scale graphs. The reduction exploits community detection for graph partitioning and is applicable to any graph type and/or density. Experimental results on both real and synthetic graphs demonstrate that our proposed method performs on par or outperforms state-of-the-art learning-based methods in terms of the size of the found set without requiring any training data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Load Profile Inpainting for Missing Load Data Restoration and Baseline Estimation

This paper introduces a Generative Adversarial Nets (GAN) based, Load Profile Inpainting Network (Load-PIN) for restoring missing load data segments and estimating the baseline for a demand response event. The inputs are time series load data before and after the inpainting period together with explanatory variables (e.g., weather data). Here, we propose a Generator structure consisting of a coarse network and a fine-tuning network. The coarse network provides an initial estimation of the data segment in the inpainting period. The fine-tuning network consists of self-attention blocks and gated convolution layers for adjusting the initial estimations. Loss functions are specially designed for the fine-tuning and the discriminator networks to enhance both the point-to-point accuracy and realisticness of the results. We test the Load-PIN on three real-world data sets for two applications: patching missing data and deriving baselines of conservation voltage reduction (CVR) events. We benchmark the performance of Load-PIN with five existing deep-learning methods. Our simulation results show that, compared with the state-of-the-art methods, Load-PIN can handle varying-length missing data events and achieve 15-30% accuracy improvement.

14 SOLAR ENERGY↗
NASA NTRS2014

Dynamic Controllability and Dispatchability Relationships

An important issue for temporal planners is the ability to handle temporal uncertainty. Recent papers have addressed the question of how to tell whether a temporal network is Dynamically Controllable, i.e., whether the temporal requirements are feasible in the light of uncertain durations of some processes. We present a fast algorithm for Dynamic Controllability. We also note a correspondence between the reduction steps in the algorithm and the operations involved in converting the projections to dispatchable form. This has implications for the complexity for sparse networks.

controllability↗
DOE OSTI2025

Developing ML/AI Methods for High-Throughput Characterization of Multiple-Sensor Streams of Tokamak Dynamics for High-Speed Control (Final Report)

This project evaluated and developed new mathematical and algorithmic techniques capable of handling (in real-time) the growing amounts of data generated by modern fusion research. While existing numerical linear algebra (NLA) methods provide the backbone to classical data analysis and algorithms, these methods fundamentally do not port to distributed architectures nor do they allow low-latency data reduction for control. Motivated by the needs for modern fusion reactors, this project explored and implemented new numerical methods to characterize plasma dynamics, respond in real-time to discharge evolution, and to process massive-scale data accurately and rapidly more fully. This project links expertise in multiple-sensor diagnostics of tokamak plasma dynamics from Columbia University’s Plasma Physics Laboratory with expertise in massive-scale data reduction and extreme data control algorithms at Columbia University’s Data Science Institute. This interdisciplinary project (i) applied machine learning methods, (ii) implemented a properly-trained neural-network for very fast processing of high-speed plasma videography, and (ii) developed the applied mathematical methods, based on randomized-NLA (rNLA) routines, for data analysis, reduction, and real-time control. The Columbia University High Beta Tokamak-Extended Pulse (HBT-EP) facility provided data to test new algorithms and partnership with Columbia University's Data Sciences Institute evaluated the broader use of new algorithms for many challenging control applications.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗