Search NASA⌕ Search

SEARCH · Search NASA

Results for “High Performance Networking”

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 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

An Efficient Storage-Driven Machine Learning Model for Performance in the Era of Multimodal Scientific Data

Scientific workflows are increasingly relying on machine learning (ML), simulation, and hybrid techniques to predict, understand, and optimize the behavior of complex experiments. High-performance computing has greatly improved researchers’ ability to acquire diverse data modalities in these workflows. Recent studies suggest that the performance of machine learning models can be improved by integrating data from various sources. Unfortunately, these workloads pose unprecedent pressure on the network storage to meet the demands associated with accessing these multimodal data. To mitigate the impact of intensive IO, we propose a solution that utilizes a multi-tier High-Performance Computing (HPC) distributed storage and data processing framework, placing computation where the data resides for better performance. By adopting this project, the scientific community will gain new opportunities to explore multimodal storage-driven possibilities, integrating multiple scientific data sources with advanced streaming frameworks. Additionally, our framework effectively utilizes computing resources and bridges the gaps identified by HPC experts. Our proposed approach tackles scalability and persistence challenges by leveraging native persistency, which has posed difficulties in traditional approaches. Furthermore, we seek to enhance fault-tolerance and load-balance of computations by leveraging real-time streaming in diverse scientific computing environments, thereby propelling advanced scientific computing research into the next generation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

High Performance Solution for Security Constrained Optimal Power Flow

Solving the Alternating Current Optimal Power Flow (ACOPF) problem is key to economically efficient and reliable power networks with a good solution potentially saving utilities tens of billions of dollars annually (according to FERC). The Grid Optimization (GO) Competition set up by ARPA-E saw several promising solutions in Challenge 1. While team GOT-TJU-OPF placed top 10 in Division 3 and 4, this was not a satisfactory performance, and the team has identified specific areas to improve and will be adding more members to round out the necessary skills and expertise needed to be more competitive. The team set out for redemption during GO Challenge 2 with an improved High-Performance Solution for Security Constrained Optimal Power Flow. The (renamed) BSI-GOT-OPF Team ended up finishing top 2 overall in the competition. The algorithms developed have potential impacts for the electric power markets that are enormous. Optimal Power Flow technology can be an enabling technology to achieve energy-efficient power grids while enhancing renewable energy penetration, among others.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2009

Airborne and Ground-Based Measurements Using a High-Performance Raman Lidar: Ground Based - Part 2

The same RASL hardware as described in part I was installed in a ground-based mobile trailer and used in a water vapor lidar intercomparison campaign, hosted at Table Mountain, CA, under the auspices of the Network for the Detection of Atmospheric Composition Change (NDACC). The converted RASL hardware demonstrated high sensitivity to lower stratospheric water vapor indicating that profiling water vapor at those altitudes with sufficient accuracy to monitor climate change is possible. The measurements from Table Mountain also were used to explain the reason, and correct , for sub-optimal airborne aerosol extinction performance during the flight campaign.

Whiteman, David N.↗
DOE OSTI2022

Coal-derived graphene foam and micron-sized silicon composite anodes for lithium-ion batteries

Silicon-based materials demonstrate significant potential as lithium-ion batteries (LIBs) anode, but their expansion and degradation present engineering design challenges for commercial application. In this study, a porous three-dimensional (3D) graphene and micron-sized silicon composite anode (Si@G foam) was synthesized using humic acid (HA) derived from coal as a graphene precursor. In-situ formation of graphene structure through reducing HA was confirmed by Raman spectra. The reduced HA (rHA) shows similar electrical conductivity compared to the commercial conductive carbon. SEM images depict a 3D skeleton of coal-derived graphene, with silicon particles distributed on the 3D graphene foam's internal surface. The Si@G composite-anode displays a good reversible capacity of ~656 mAh/g at a current density of 50 mA/g, as well as a high-rate capability of ~433 mAh/g at a current density of 800 mA/g, and outstanding cycling stability –89.8% capacity retention after 300 cycles, which is significantly higher than that of other foam structures. During lithiation and de-lithiation, the graphene foam serves as a matrix of electrical conductors and a volume expansion support for silicon. This 3D graphene network will be beneficial for developing advanced silicon-based anodes for high-performance LIBs.

25 ENERGY STORAGE↗
DOE OSTI2025

Synthetic-domain computing and neural networks using lithium niobate integrated nonlinear phononics

Analogue computing uses the physical behaviours of devices to provide energy-efficient arithmetic operations. However, scaling up analogue computing platforms by simply increasing the number of devices leads to challenges such as device-to-device variation. Here, in this study, we report scalable analogue computing and neural networks in the synthetic frequency domain using an integrated nonlinear phononic platform on lithium niobate. This synthetic-domain computing is robust to device variations, as vectors and matrices are concurrently encoded at different frequencies within a single device, achieving a high throughput per area. Leveraging inherent nonlinearities, our device-aware neural network can perform a four-class classification task with an accuracy of 98.2%. The nonlinear phononic computing hardware also maintains consistent performance over a wide operational temperature range (characterized up to 192 °C). Our synthetic-domain computing combines single-device parallelism, inherent nonlinearity and environmental stability, and could be of use in edge computing applications in which power efficiency and environmental resilience are crucial.

Ji, Jun [Virginia Polytechnic Inst. and State Univ↗
DOE OSTI2024

Machine learning based unfolding of x-ray spectra from filter stack spectrometer data

We demonstrate the application of neural networks to perform x-ray spectra unfolding from data collected by filter stack spectrometers. A filter stack spectrometer consists of a series of filter-detector pairs, where the detectors behind each filter measure the energy deposition through each layer as photo-stimulated luminescence (PSL). The network is trained on synthetic data, assuming x-rays of energies < 1 MeV and of two different distribution functions (Maxwellian and Gaussian) and the corresponding measured PSL values obtained from five different filter stack spectrometer designs. Predicted unfolds of single distributions are near identical reproductions of the ground truth spectra, with differences in the values lower than 20% at the higher energy end in some cases. The neural network has also demonstrated robustness to experimental measurement errors of < 5% and some capability of performing unfolds for linear combinations of the two distributions without previous training. The network can perform unfolds at rates > 1 Hz, ideal for application to some high-repetition-rate systems.

47 OTHER INSTRUMENTATION↗
DOE OSTI2013

Exploring Hardware Support For Scaling Irregular Applications on Multi-node Multi-core Architectures

With the recent emergence of large-scale knowledge dis- covery, data mining and social network analysis, irregular applications have gained renewed interest. Classic cache-based high-performance architectures do not provide optimal performances with such kind of workloads, mainly due to the very low spatial and temporal locality of the irregular control and memory access patterns. In this paper, we present a multi-node, multi-core, fine-grained multi-threaded shared-memory system architecture specifically designed for the execution of large-scale irregular applications, and built on top of three pillars, that we believe are fundamental to support these workloads. First, we offer transparent hardware support for Partitioned Global Address Space (PGAS) to provide a large globally-shared address space with no software library overhead. Second, we employ multi-threaded multi-core processing nodes to achieve the necessary latency tolerance required by accessing global memory, which potentially resides in a remote node. Finally, we devise hardware support for inter-thread synchronization on the whole global address space. We first model the performances by using an analytical model that takes into account the main architecture and application characteristics. We describe the hardware design of the proposed cus- tom architectural building blocks that provide support for the above- mentioned three pillars. Finally, we present a limited-scale evaluation of the system on a multi-board FPGA prototype with typical irregular kernels and benchmarks. The experimental evaluation demonstrates the architecture performance scalability for different configurations of the whole system.

FPGA↗
DOE OSTI2019

Defense strategies and expected capacity of high performance computing infrastructures

We consider high performance computing infrastructures consisting of multiple sites connected over a wide-area network. These sites house heterogeneous computing systems, network elements and local-area connections, and the wide-area network plays a critical, asymmetric role of providing the vital connectivity between them. We model this infrastructure as a recursive system of systems, wherein the basic systems at the finest levels are composed of discrete cyber and physical components. These components may be disabled by cyber and physical disruptions, and their reinforcements protect against them albeit at a cost. We utilize results from a game formulation based on (i) characterizing the disruptions between systems at each level of recursion using aggregate failure correlation functions, and within basic systems using the multiplier functions, and (ii) using utility functions expressed in terms of the number of basic system components attacked and reinforced. At Nash Equilibrium, we derive expressions for the expected capacity of the infrastructure given by the number of computing nodes that are operational and connected to the network.

Rao, Nageswara↗
DOE OSTI2023

Multiverse: Bayesian model selection for neural networks

Multiverse is a code repository for a set of tools for Bayesian model selection for neural networks. The goal of the tools is to provide capabilities for selecting among prior and model specifications for Bayesian neural networks. Multiverse will include tools for creating Bayesian neural networks, evaluating the Bayesian model evidence, and performing inference in Bayesian neural networks. These components are written in Python, a high-level programming language that takes advantage of the Python ecosystem of high-quality open-source packages for machine learning and signal processing.

Klein, Natalie↗
DOE OSTI2015

Rutgers University Subcontract B611610 Final Report

Given an incomplete (i.e., partially-observed) network, which nodes should we actively probe in order to achieve the highest accuracy for a given network feature? For example, consider a cyber-network administrator who observes only a portion of the network at time t and wants to accurately identify the most important (e.g., highest PageRank) nodes in the complete network. She has a limited budget for probing the network. Of all the nodes she has observed, which should she probe in order to most accurately identify the important nodes? We propose a novel and scalable algorithm, MaxOutProbe, and evaluate it w.r.t. four network features (largest connected component, PageRank, core-periphery, and community detection), five network sampling strategies, and seven network datasets from different domains. Across a range of conditions, MaxOutProbe demonstrates consistently high performance relative to several baseline strategies

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

BigData Express: Toward Predictable, Schedulable, and High-Performance Data Transfer [Slides]

BigData Express: a schedulable, predictable, and high-performance data transfer service. A peer-to-peer, scalable, and extensible data transfer model; A visually appealing, easy-to-use web portal; A high-performance data transfer engine; On-demand provisioning of end-to-end network paths with guaranteed QoS; Robust and flexible error handling; CILogon-based security (certificate version); A rich set of REST APIs to support scientific workflows

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

Characterization of throughput on the AXI DMA bus for burst data transfer over Ethernet

cThe Xilinx AXI Direct Memory Access (AXI DMA) module is an efficient solution for medium-speed data transfer in Xilinx SoC FPGAs, supporting data rates greater than 1000 Gbps even in very suboptimal operating modes. It facilitates direct transfer of AXI stream data into processor memory without constant software intervention, which reduces overhead and ensures consistent data logging. By utilizing the FPGA's available memory, large circular buffers (1-5 GiB) are used to buffer data and accommodate network limitations, enabling high-rate data bursts. In this study, we measured the performance of AXI DMA under conditions simulating its lowest practical data transfer speeds. The Arbitrary Length Data Sender was used to transmit AXI stream packets at 32-bit width and 100 MHz frequency, a narrow width and slow speed. Results show that the AXI DMA can transfer up to 3192.76 Mbps with large packet sizes but experiences reduced performance for smaller packets, as low as 2.6 Mbps for 4-byte packets. For Ethernet-limited applications, packet sizes between 8,000 and 16,000 bytes provided optimal transfer speeds of 874 to 1600 Mbps. These findings suggest that the AXI DMA is not the limiting factor in systems where packet sizes exceed 8,000 bytes.

43 PARTICLE ACCELERATORS↗
NASA NTRS1989

Transputer finite element solver

In January 1987, SPARTA received a Phase I SBIR award from the NASA Lewis Research Center to investigate the feasibility of a finite element solver implemented on multiple VLSI processors. The transputer was chosen as the processor for the feasibility study since it combined low cost with high performance and was specifically designed to directly link with other transputers to form networks of multiple processors. A brief description of transputers, a summary of the SBIR feasibility study, and a discussion of issues concerning a large scale transputer based finite element solver (TBFES) and the performance levels which can be expected are discussed.

Source record↗
NASA NTRS2019

Deep Learning Emulation of Atmospheric Correction for Geostationary Sensors

New generation geostationary satellites make reflectance observations available at a continental scale with unprecedented spatiotemporal resolution and spectral range. Generating Earth monitoring products from these observations requires retrieval of the basic parameter, surface reflectance (SR), by atmospheric correction (AC). Algorithms for atmospheric correction, including Multi-Angle Implementation of Atmospheric Correction (MAIAC), are adapted for each sensor and are too computationally complex to be run in real time, relying instead on look-up tables with precomputed values. Machine learning methods, including convolutional neural networks, have demonstrated performance in learning complex, nonlinear mappings and extracting insight from high-dimensional remote sensing data. In this work, we present a deep learning emulator of MAIAC to retrieve both SR and cloud products. Using this adaptation of deep learning-based emulation to remote sensing, we demonstrate stable SR retrieval over a variety of land covers and viewing conditions and accurate cloud detection. Further, a comparison of computation time suggests emulation as a compelling alternative for expensive physical simulation, especially for applications benefited by near-real time data, such as agricultural management and disaster response.

Duffy, Kate↗
NASA NTRS2018

Towards Explainability of UAV-Based Convolutional Neural Networks for Object Classification

f autonomous systems using trust and trustworthiness is the focus of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR), a new NASA Convergent Aeronautical Solutions (CAS) Project. One critical research element of ATTRACTOR is explainability of the decision-making across relevant subsystems of an autonomous system. The ability to explain why an autonomous system makes a decision is needed to establish a basis of trustworthiness to safely complete a mission. Convolutional Neural Networks (CNNs) are popular visual object classifiers that have achieved high levels of classification performances without clear insight into the mechanisms of the internal layers and features. To explore the explainability of the internal components of CNNs, we reviewed three feature visualization methods in a layer-by-layer approach using aviation related images as inputs. Our approach to this is to analyze the key components of a classification event in order to generate component labels for features of the classified image at different layers of depths. For example, an airplane has wings, engines, and landing gear. These could possibly be identified somewhere in the hidden layers from the classification and these descriptive labels could be provided to a human or machine teammate while conducting a shared mission and to engender trust. Each descriptive feature may also be decomposed to a combination of primitives such as shapes and lines. We expect that knowing the combination of shapes and parts that create a classification will enable trust in the system and insight into creating better structures for the CNN.

Dolph, Chester V.↗
NASA NTRSDate not supplied

The International Space Station, Optical Communications, and Delay Tolerant Networking: Towards A Solar System Internet Architecture

As Delay Tolerant Networking (DTN) matures as a software product its use cases have extended to infrastructural and architectural studies, bringing DTN closer to a widespread, operational technology. While it is known that a DTN can be configured, given complete information about a system of nodes, to provision a system with a complete network capability, what remains is to tackle practical considerations such as scalability, networking best practices, and how to establish service providers. In this paper, we document progress towards a scalable DTN architecture that was tested across multiple organizational and project boundaries; our approach was tested across nodes flying on the International Space Station (ISS) connected to a ground network. The network consists of four main network areas: the ISS, the White Sands Complex (WSC), the Mission Cloud Platform (MCP), and NASA’s Huntsville Operations Support Center (HOSC). The connections on the ground (WSC, MCP, and HOSC) are straightforward technically, but represent administrative and non-technical challenges that had to be overcome. The connection from the ISS to WSC was realized through a hybrid optical/RF means. In particular, NASA’s Integrated Laser Communications Relay Demonstration (LCRD) can form a relay from lowEarth-orbit (LEO) to the Earth, and was used in conjunction with the LCRD LEO User Modem and Amplifier Terminal (ILLUMA-T) on the ISS to form a link to one of three geographically diverse ground stations. A major goal was to achieve communications while keeping the ISS nodes unaware of ground station choices and scheduling. These disparate links were networked using High-rate DTN (HDTN), which enabled the desired architecture. The network architecture, tests, HDTN performance metrics, and general observations made are all discussed in detail, including a discussion on the successful utilization of the DTN security standard known as DTN Bundle Protocol Security (BPSec). We conclude with suggestions for next steps, and in particular focus on extending this architecture to the Near Space Network (NSN) and the upcoming LunaNet.

Alan Hylton↗
DOE OSTI2024

Toward digital design at the exascale: An overview of project ICECap

High performance computing has entered the Exascale Age. Capable of performing over 1018 floating point operations per second, exascale computers, such as El Capitan, the National Nuclear Security Administration's first, have the potential to revolutionize the detailed in-depth study of highly complex science and engineering systems. However, in addition to these kind of whole machine “hero” simulations, exascale systems could also enable new paradigms in digital design by making petascale hero runs routine. Currently, untenable problems in complex system design, optimization, model exploration, and scientific discovery could all become possible. Motivated by the challenge of uncovering the next generation of robust high-yield inertial confinement fusion (ICF) designs, project ICECap (Inertial Confinement on El Capitan) attempts to integrate multiple advances in machine learning (ML), scientific workflows, high performance computing, GPU-acceleration, and numerical optimization to prototype such a future. Built on a general framework, ICECap is exploring how these technologies could broadly accelerate scientific discovery on El Capitan. In addition to our requirements, system-level design, and challenges, we describe some of the key technologies in ICECap, including ML replacements for multiphysics packages, tools for human-machine teaming, and algorithms for multifidelity design optimization under uncertainty. As a test of our prototype pre-El Capitan system, we advance the state-of-the art for ICF hohlraum design by demonstrating the optimization of a 17-parameter National Ignition Facility experiment and show that our ML-assisted workflow makes design choices that are consistent with physics intuition, but in an automated, efficient, and mathematically rigorous fashion.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Layer-by-Layer Organic Solar Cells Enabled by 1,3,4-Selenadiazole-Containing Crystalline Small Molecule with Double-Fibril Network Morphology

A double-fibril network of the photoactive layer morphology is recognized as an ideal structure facilitating exciton diffusion and charge carrier transport for high-performance organic solar cells (OSCs). However, in the layer-by-layer processed OSCs (LbL-OSCs), polymer donors and small molecule acceptors (SMAs) are separately deposited, and it is challenging to realize a fibril network of pure SMAs with the absence of tight interchain entanglement as polymers. Here, in this work, crystalline small molecule donors (SMDs), named TDZ-3TR and SeDZ-3TR, were designed and introduced into the L8-BO acceptor solution, forcing the phase separation and molecular fibrilization. SeDZ-3TR showed higher crystallinity and lower miscibility with L8-BO acceptor than TDZ-3TR, enabling more driving force to favor the phase separation and better molecular fibrilization of L8-BO. On the other hand, two donor polymers of PM6 and D18 with different fibril widths and lengths were put together to optimize the fibril network of the donor layer. The simultaneously optimization of the acceptor and donor layers resulted in a more ideal double-fibril network of the photoactive layer and an impressive power conversion efficiency (PCE) of 19.38 % in LbL-OSCs.

36 MATERIALS SCIENCE↗