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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,063 records · Page 59

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today’s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN) , in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 × pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

Peng, Hongwu↗

DOE OSTI2025

Reinforcement Learning‐Based Adaptation of Grid Following Inverter's Internal Controller to Networked Microgrids' Strengths

The varying topological configurations, generator commitments and dispatches, and dynamic load demand lead to changing system's strengths during the operations of networked microgrids. When the system's strengths significantly change, the fixed control gains at large devices may result in unsatisfactory system performance; this necessitates the tuning of the control gains at large devices to adapt to the changing system's strengths. In this paper, observer-based reinforcement learning (RL) is utilised to automatically tune the proportional-integral (PI) gains of phase lock loop (PLL) controller of grid-following (GFL) inverters to adapt to the changing strengths of microgrids and networked microgrids. The RL agent in this framework augments an observer predicting system's strengths, from which the RL control policy will adjust accordingly to tune the PLL controller's gains towards the system's strengths. Also, to enhance the control performance, the recently introduced Barrier function-based RL framework is leveraged for the design of reward function to prevent the high frequency nadir. An operational 26 kV electric distribution system, which is modelled as networked microgrids, is used to illustrate the need and effectiveness of the proposed RL-tuned control.

frequency response↗

DOE OSTI2024

Enhanced mobility of dislocation network nodes and its effect on dislocation multiplication and strain hardening

Understanding plastic deformation of crystals in terms of the fundamental physics of dislocations has remained a grand challenge in materials science for decades. To overcome this, the Discrete Dislocation Dynamics (DDD) method has been developed, but its lack of atomistic resolution leaves open the possibility that certain key mechanisms may be overlooked. Here, by comparing large-scale Molecular Dynamics (MD) with DDD simulations performed under identical conditions we uncover significant discrepancies in the predicted strength and microstructure evolution in BCC crystals under high-strain rate conditions. These are traced to unexpected behaviors of dislocation network nodes forming at dislocation intersections, that can move in ways not previously anticipated as revealed by MD. Once these newfound freedoms of nodal motion are incorporated, DDD simulations begin to closely match plastic evolution observed in MD. This additional mechanism of motion whereby non-screw dislocations can change their glide plane profoundly affects fundamental processes of dislocation multiplication, recovery and storage that define strength of metals.

36 MATERIALS SCIENCE↗

NASA NTRS1993

Neural self-tuning adaptive control of non-minimum phase system

The motivation of this research came about when a neural network direct adaptive control scheme was applied to control the tip position of a flexible robotic arm. Satisfactory control performance was not attainable due to the inherent non-minimum phase characteristics of the flexible robotic arm tip. Most of the existing neural network control algorithms are based on the direct method and exhibit very high sensitivity, if not unstable, closed-loop behavior. Therefore, a neural self-tuning control (NSTC) algorithm is developed and applied to this problem and showed promising results. Simulation results of the NSTC scheme and the conventional self-tuning (STR) control scheme are used to examine performance factors such as control tracking mean square error, estimation mean square error, transient response, and steady state response.

Ho, Long T.↗

NASA NTRS1993

Adaptive control strategies for flexible robotic arm

The motivation of this research came about when a neural network direct adaptive control scheme was applied to control the tip position of a flexible robotic arm. Satisfactory control performance was not attainable due to the inherent non-minimum phase characteristics of the flexible robotic arm tip. Most of the existing neural network control algorithms are based on the direct method and exhibit very high sensitivity if not unstable closed-loop behavior. Therefore a neural self-tuning control (NSTC) algorithm is developed and applied to this problem and showed promising results. Simulation results of the NSTC scheme and the conventional self-tuning (STR) control scheme are used to examine performance factors such as control tracking mean square error, estimation mean square error, transient response, and steady state response.

Bialasiewicz, Jan T.↗

DOE OSTI2017

Optimizing for Large Planar Fractures in Multistage Horizontal Wells in Enhanced Geothermal Systems Using a Coupled Fluid and Geomechanics Simulator

Enhanced Geothermal Systems (EGS) could potentially use technological advancements in coupled implementation of horizontal drilling and multistage hydraulic fracturing techniques in tight oil and shale gas reservoirs along with improvements in reservoir simulation techniques to design and create EGS reservoirs. In this study, a commercial hydraulic fracture simulation package, Mangrove by Schlumberger, was used in an EGS model with largely distributed pre-existing natural fractures to model fracture propagation during the creation of a complex fracture network. The main goal of this study is to investigate optimum treatment parameters in creating multiple large, planar fractures to hydraulically connect a horizontal injection well and a horizontal production well that are 10,000 ft. deep and spaced 500 ft. apart from each other. A matrix of simulations for this study was carried out to determine the influence of reservoir and treatment parameters on preventing (or aiding) the creation of large planar fractures. The reservoir parameters investigated during the matrix simulations include the in-situ stress state and properties of the natural fracture set such as the primary and secondary fracture orientation, average fracture length, and average fracture spacing. The treatment parameters investigated during the simulations were fluid viscosity, proppant concentration, pump rate, and pump volume. A final simulation with optimized design parameters was performed. The optimized design simulation indicated that high fluid viscosity, high proppant concentration, large pump volume and pump rate tend to minimize the complexity of the created fracture network. Additionally, a reservoir with 'friendly' formation characteristics such as large stress anisotropy, natural fractures set parallel to the maximum horizontal principal stress (SHmax), and large natural fracture spacing also promote the creation of large planar fractures while minimizing fracture complexity.

15 GEOTHERMAL ENERGY↗

DOE OSTI2021

Teaching a neural network to attach and detach electrons from molecules

Abstract Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. Most DNN potentials were parametrized for neutral molecules or closed-shell ions due to architectural limitations. In this work, we propose an improved machine learning framework for simulating open-shell anions and cations. We introduce the AIMNet-NSE (Neural Spin Equilibration) architecture, which can predict molecular energies for an arbitrary combination of molecular charge and spin multiplicity with errors of about 2–3 kcal/mol and spin-charges with error errors ~0.01e for small and medium-sized organic molecules, compared to the reference QM simulations. The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Solving sparse finite element problems on neuromorphic hardware

The finite element method (FEM) is one of the most important and ubiquitous numerical methods for solving partial differential equations (PDEs) on computers for scientific and engineering discovery. Applying the FEM to larger and more detailed scientific models has driven advances in high-performance computing for decades. Here we demonstrate that scalable spiking neuromorphic hardware can directly implement the FEM by constructing a spiking neural network that solves the large, sparse, linear systems of equations at the core of the FEM. We show that for the Poisson equation, a fundamental PDE in science and engineering, our neural circuit achieves meaningful levels of numerical accuracy and close to ideal scaling on modern, inherently parallel and energy-efficient neuromorphic hardware, specifically Intel’s Loihi 2 neuromorphic platform. We illustrate extensions to irregular mesh geometries in both two and three dimensions as well as other PDEs such as linear elasticity. Our spiking neural network is constructed from a recurrent network model of the brain’s motor cortex and, in contrast to black-box deep artificial neural network-based methods for PDEs, directly translates the well-understood and trusted mathematics of the FEM to a natively spiking neuromorphic algorithm.

Applied mathematics↗

DOE OSTI2020

Comparison of machine learning techniques to optimize the analysis of plutonium surrogate material via a portable LIBS device

The utilization of machine learning techniques has become commonplace in the analysis of optical emission spectra. These methods are often limited to variants of principal components analysis (PCA), partial-least squares (PLS), and artificial neural networks (ANNs). A plethora of other techniques exist and are well established in the world of data science, yet are seldom investigated for their use in spectroscopic problems. In this study, machine learning techniques were used to analyze optical emission spectra of laser-induced plasma from ceria pellets doped with silicon in order to predict silicon content. Additionally, a boosted regression ensemble model was created, and its predictive accuracy was compared to that of traditional PCA, PLS, and ANN regression models. Boosted regression tree ensembles yielded fits with R-squared (R2) values as high as 0.964 and mean-squared errors of prediction (MSEPs) as low as 0.074, providing the most accurate predictive model. Neural networks performed with slightly lower R2 values and higher MSEPs compared to the ensemble methods, thus indicating susceptibility to overfitting.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2015

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2016

Evaluation of Topology-Aware Broadcast Algorithms for Dragonfly Networks

Two-tiered direct network topologies such as Dragonflies have been proposed for future post-petascale and exascale machines, since they provide a high-radix, low-diameter, fast interconnection network. Such topologies call for redesigning MPI collective communication algorithms in order to attain the best performance. Yet as increasingly more applications share a machine, it is not clear how these topology-aware algorithms will react to interference with concurrent jobs accessing the same network. In this paper, we study three topology-aware broadcast algorithms, including one designed by ourselves. We evaluate their performance through event-driven simulation for small- and large-sized broadcasts (in terms of both data size and number of processes). We study the effect of different routing mechanisms on the topology-aware collective algorithms, as well as their sensitivity to network contention with other jobs. Our results show that while topology-aware algorithms dramatically reduce link utilization, their advantage in terms of latency is more limited.

Dorier, Matthieu↗

DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗

DOE OSTI2026

Energy–Performance Trade-offs in Privacy-Preserving Federated Learning on SmartNIC-Enabled HPC Systems

Federated learning (FL) is increasingly deployed on accelerator-rich high-performance computing (HPC) systems, yet the system-level energy cost of privacy-aware FL remains poorly understood, particularly across heterogeneous networking and server-placement options. We present a measurement-driven study of energy–performance trade-offs for FL on GH200-class nodes across three deployment configurations: CPU-Ethernet, CPU-InfiniBand (RDMA-capable), and a DPU-hosted FL server over InfiniBand using a BlueField-3 SmartNIC/DPU. Using NVIDIA FLARE (NVFLARE), we align node-level power telemetry with per-round timing extracted from NVFLARE logs to quantify time-to-solution (TTS), energy-to-solution (ETS), energy-delay product (EDP), and synchronization behavior for three transformer models (ALBERT, DistilBERT, BERT), trained with and without differential privacy (DP). We find that interconnect choice is the dominant driver of runtime and energy: host-managed InfiniBand consistently reduces communication overhead versus Ethernet, yielding lower TTS/ETS/EDP. In contrast, in our NVFLARE deployment, placing the FL server on the DPU does not consistently match CPU-InfiniBand performance and can be slower—especially for larger models—highlighting that server placement alone is not sufficient to guarantee end-to-end gains. Finally, under our fixed-round protocol, DP increases per-round cost and runtime variance; ETS increases largely in proportion to TTS because average node power remains relatively stable across configurations.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗

DOE OSTI2017

Roles and Responsibilities for Distribution Grids: DER Sensing and Communication Networks

Traditional distribution grids require sensing and communications for grid operations. In many cases the communications networks are owned by the Distribution Operator (DO); in some cases, carrier services such as leased telephone land lines or cellular services are used. In recent years, wireless mesh field area networks and optical fiber have become viable options for distribution. Fiber in particular has improved in cost to the point where its high performance (large bandwidth, low latency, and low packet loss) has become practical for distribution systems where geographic circumstances permit. As grid modernization proceeds, utilities find a need to improve or upgrade distribution communications; this represents a significant investment and it is natural that both utilities and regulators would seek both to future-proof and minimize their costs. Given the development and rising penetration of smart grid edge devices such as Distributed Energy Resources (DER) that have local sensing and intelligence and can communicate via the internet or other non-utility communications channels to cloud-based services, the idea of using such devices for grid sensing and communications to support grid operations has emerged as a potential means to avoid utility investment. To a great extent, however, these DER and communication channels will be owned and operated not by the DO but by end-use customers, aggregators and other third parties pursuing their own energy needs and business models. The question of whether such devices and systems can effectively substitute for DO grid modernization investment can be assessed and resolved using grid architecture methods and by considering the appropriate roles and responsibilities of the entities and systems involved in distribution grid operations. This approach reveals that there are several compelling reasons to dismiss the idea of eliminating DO owned and operated sensing and communication entirely and relying on DER-based sensing and third party communications.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

5G Energy FRAME: The Design and Implementation of Data, Model, and Use Case (Year 2 Report)

This report summarizes the Year 2 work of Pacific Northwest National Laboratory’s (PNNL’s) 5G Fabricated Resource and Asset Management Encompassment for energy infrastructure (Energy FRAME) project funded by the Department of Energy Office of Science’s Advanced Scientific Computing Research (ASCR) Program. In this report, newest 5G equipment testing results are presented, along with two 5G-enabled AI/ML examples for grid applications; in addition, the work flow of grid edge, cloud, and High Performance Computing (HPC) platform is introduced, to support and interface the cross-domain simulation for power system transmission, distribution, and communication networks. Last but not least, the outlook for Year 3 work and the overarching impact of 5G Energy FRAME work to a multitude of stakeholders are provided. Additional 5G performance data now is shared through the publicly available weblink, https://www.pnnl.gov/projects/5g-energy-frame/publications

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS1988

Measurement of the properties of lossy materials inside a finite conducting cylinder

A computer code was developed to automatically perform swept frequency reflection and transmission measurements using a HP5510B Network Analyzer and computer. This software is used in conjunction with a modified high temperature test rig to obtain reflection measurements from a flat material sample. The software allows data processing to eliminate measurement errors and to obtain a reflection coefficient in the frequency or time domain. A description of the program is presented.

Caldecott, R.↗

NASA NTRS1993

LANL High-Performance Data System (HPDS)

The Los Alamos High-Performance Data System (HPDS) is being developed to meet the very large data storage and data handling requirements of a high-performance computing environment. The HPDS will consist of fast, large-capacity storage devices that are directly connected to a high-speed network and managed by software distributed in workstations. The HPDS model, the HPDS implementation approach, and experiences with a prototype disk array storage system are presented.

Collins, M. William↗

DOE OSTI2014

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to the needs of a processing algorithm.

97 MATHEMATICS AND COMPUTING↗