Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Performance”

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 379 records · Page 21

Genetic algorithm based task reordering to improve the performance of batch scheduled massively parallel scientific applications

The growth in size of networked high performance computers along with novel accelerator-based node architectures has further emphasized the importance of communication efficiency in high performance computing. The world's largest high performance computers are usually operated as shared user facilities due to the costs of acquisition and operation. Applications are scheduled for execution in a shared environment and are placed on nodes that are not necessarily contiguous on the interconnect. Furthermore, the placement of tasks on the nodes allocated by the scheduler is sub-optimal, leading to performance loss and variability. Here, we investigate the impact of task placement on the performance of two massively parallel application codes on the Titan supercomputer, a turbulent combustion flow solver (S3D) and a molecular dynamics code (LAMMPS). Benchmark studies show a significant deviation from ideal weak scaling and variability in performance. The inter-task communication distance was determined to be one of the significant contributors to the performance degradation and variability. A genetic algorithm-based parallel optimization technique was used to optimize the task ordering. This technique provides an improved placement of the tasks on the nodes, taking into account the application's communication topology and the system interconnect topology. As a result, application benchmarks after task reordering through genetic algorithm show a significant improvement in performance and reduction in variability, therefore enabling the applications to achieve better time to solution and scalability on Titan during production.

97 MATHEMATICS AND COMPUTING↗

Randomized methods to characterize large-scale vortical flow networks

We demonstrate the effective use of randomized methods for linear algebra to perform network-based analysis of complex vortical flows. Network theoretic approaches can reveal the connectivity structures among a set of vortical elements and analyze their collective dynamics. These approaches have recently been generalized to analyze high-dimensional turbulent flows, for which network computations can become prohibitively expensive. In this work, we propose efficient methods to approximate network quantities, such as the leading eigendecomposition of the adjacency matrix, using randomized methods. Specifically, we use the Nyström method to approximate the leading eigenvalues and eigenvectors, achieving significant computational savings and reduced memory requirements. The effectiveness of the proposed technique is demonstrated on two high-dimensional flow fields: two-dimensional flow past an airfoil and two-dimensional turbulence. We find that quasi-uniform column sampling outperforms uniform column sampling, while both feature the same computational complexity.

97 MATHEMATICS AND COMPUTING↗

Performance Evaluation of Distributed Energy Resource Management Algorithm in Large Distribution Networks

This paper presents performance evaluation of hierarchical optimization and control for distributed energy resource management system (DERMS) in large distribution networks via an advanced hardware-in-the-loop (HIL) platform. The HIL platform provides realistic testing in a laboratory environment, including the accurate modeling of a full-scale distribution system of 11,000 nodes, the DERMS software controller, and 90 power hardware photovoltaics (PVs) and battery inverters. The applied DERMS algorithm is designed based on a realtime optimal power flow algorithm and implemented with acceleration design that performs fast dispatch of simulated PVs and real physical hardware DER devices every 4 seconds.

DERMS↗

Performance Evaluation of Distributed Energy Resource Management Algorithm in Large Distribution Networks

This paper presents performance evaluation of hierarchical optimization and control for distributed energy resource management system (DERMS) in large distribution networks via an advanced hardware-in-the-loop (HIL) platform. The HIL platform provides realistic testing in a laboratory envi-ronment, including the accurate modeling of a full-scale dis-tribution system of 11,000 nodes, the DERMS software con-troller, and 90 power hardware photovoltaics (PVs) and bat-tery inverters. The applied DERMS algorithm is designed based on a real-time optimal power flow algorithm and im-plemented with acceleration design that performs fast dis-patch of simulated PVs and real physical hardware DER devices every 4 seconds.

distributed energy management system (DERMS)↗

Implementation and Investigation of a Weather- and Jam Density-tuned Network Perimeter Controller

This paper implements and evaluates the performance of a network fundamental diagram (NFD) proportional-integral perimeter controller (PC) using base tuned parameters (clear weather conditions and a base jam density of 160 veh/km/lane). The parameters were then re-tuned separately for different weather conditions and jam density values (reflecting different percentage of trucks), resulting in two new control methods: a weather-tuned perimeter controller (WTPC) and a jam density-tuned perimeter controller (JTPC). The WTPC was shown to outperform the no control strategy and the PC for different weather conditions. Specifically, the WTPC decreased the congestion inside the protected network (PN) and improved the overall performance of the full network (FN) by decreasing the average vehicle travel time, decreasing the vehicle total delay, increasing the average vehicle speed and decreasing the average vehicle fuel consumption. Alternatively, the JTPC was shown to perform similar to the PC for jam densities higher than the base-case jam density used in the PC (in our case 160 veh/km/lane). However, the JTPC outperformed the PC for smaller jam densities given that these smaller jam densities result in queues spilling back faster to upstream traffic signals. The results demonstrate the need to tune the controller to the actual jam density especially when the jam density decreases (e.g. trucks are introduced to the network). http://pubsindex.trb.org/

42 ENGINEERING↗

Effect of Networking Density on the Patterning Performance of Molecular Layer Deposited Alucone Electron Beam/EUV Resists

One of the main barriers to continued device scaling in the era of extreme ultraviolet (EUV) lithography is the need for improved photoresist chemistries to address challenges such as poor EUV sensitivity, inadequate etch resistance, and pattern collapse. Metal-organic photoresists are a promising class of materials that can address many of these challenges, and among them, resists deposited via hybrid molecular layer deposition (MLD) have attracted interest for their unique advantages in thickness control, chemical homogeneity, and compatibility with vacuum processing. However, despite many successful demonstrations of patterning, little is known about how the molecular design of hybrid MLD resists affects their lithographic performance. In this work, we study the effect of the network structure, a common feature among all hybrid MLD resists, via a series of aluminum alkoxide ("alucone") negative tone resists with varying networking density. Their patterning mechanism is investigated via electron beam lithography (EBL)─a common proxy for EUV─and compared to their EUV-induced reactions studied via flood exposure and in situ characterization. In conclusion, we show that the resist with the least networking density demonstrates the best sensitivity and resolution, with the ability to resolve dense line/space gratings as small as 14 nm half pitch via EBL.

electron beam lithography↗

Training toward significance with the decorrelated event classifier transformer neural network

Experimental particle physics uses machine learning for many tasks, where one application is to classify signal and background events. This classification can be used to bin an analysis region to enhance the expected significance for a mass resonance search. In natural language processing, one of the leading neural network architectures is the transformer. In this work, an event classifier transformer is proposed to bin an analysis region, in which the network is trained with special techniques. The techniques developed here can enhance the significance and reduce the correlation between the network’s output and the reconstructed mass. It is found that this trained network can perform better than boosted decision trees and feed-forward networks. Published by the American Physical Society 2024

Astronomy & Astrophysics↗

Situational Awareness of Network System Roles (SANSR)

In a large enterprise it is difficult for cyber security analysts to know what services and roles every machine on the network is performing (e.g., file server, domain name server, email server). Using network flow data, already collected by most enterprises, we developed a proof-of-concept tool that discovers the roles of a system using both clustering and categorization techniques. The tool's role information would allow cyber analysts to detect consequential changes in the network, initiate incident response plans, and optimize their security posture. The results of this proof-of-concept tool proved to be quite accurate on three real data sets. We will present the algorithms used in the tool, describe the results of preliminary testing, provide visualizations of the results, and discuss areas for future work. Without this kind of situational awareness, cyber analysts cannot quickly diagnose an attack or prioritize remedial actions.

cyber security↗

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗

Auto-deconvolution and molecular networking of gas chromatography–mass spectrometry data

We engineered a machine learning approach, MSHub, to enable auto-deconvolution of gas chromatography–mass spectrometry (GC–MS) data. We then designed workflows to enable the community to store, process, share, annotate, compare and perform molecular networking of GC–MS data within the Global Natural Product Social (GNPS) Molecular Networking analysis platform. MSHub/GNPS performs auto-deconvolution of compound fragmentation patterns via unsupervised non-negative matrix factorization and quantifies the reproducibility of fragmentation patterns across samples.

47 OTHER INSTRUMENTATION↗

Understanding the Impact of Interconnect Failures on System Operation

Hardware failures are inevitable on large high performance computing systems. Faults or performance degradations in the high-speed network can reduce the entire system s performance. Since the introduction of the Gemini interconnect, Cray systems have become resilient to many networking faults that were fatal in their previous generation systems. These new network reliability and resiliency features have enabled higher uptimes on Cray systems by allowing them to continue running with reduced network performance. Oak Ridge National Laboratory has developed a set of user-level diagnostics that stresses the high-speed network and searches for components that are not performing as expected. Nearest-neighbor bandwidth tests check every network chip and network link in the system. Additionally, performance counters stored on the network ASIC s memory mapped registers (MMRs) are used to better understand the state of the network. Applications have also been characterized under various suboptimal network conditions to better understand what impact network problems have on user codes.

Cray↗

GASNet-EX Performance Improvements Due to Specialization for the Cray Aries Network

This document is a deliverable for milestone STPM17-6 of the Exascale Computing Project, delivered by WBS 2.3.1.14. It reports on the improvements in performance observed on Cray XC-series systems due to enhancements made to the GASNet-EX software. These enhancements, known as “specializations”, primarily consist of replacing network-independent implementations of several recently added features with implementations tailored to the Cray Aries network. Performance gains from specialization include (1) Negotiated-Payload Active Messages improve bandwidth of a ping-pong test by up to 14%, (2) Immediate Operations reduce running time of a synthetic benchmark by up to 93%, (3) non-bulk RMA Put bandwidth is increased by up to 32%, (4) Remote Atomic performance is 70% faster than the reference on a point-to-point test and allows a hot-spot test to scale robustly, and (5) non-contiguous RMA interfaces see up to 8.6x speedups for an intra-node benchmark and 26% for inter-node. These improvements are available in the GASNet-EX 2018.3.0 release.

97 MATHEMATICS AND COMPUTING↗

Performance Study of Hybrid DS/FFH Spread-Spectrum Systems in the Presence of Frequency-Selective Fading and Multiple-Access Interference

Hybrid spread-spectrum (HSS) systems have recently received considerable interest in commercial, Smart Grid, and military communication systems because they accommodate high data rates with high link integrity, even in the presence of significant multipath effects and interfering signals. A highly useful form of this modulation scheme is the specific code-related combination of standard direct-sequence spread spectrum (DSSS) with fast frequency-hopping (FFH) spread spectrum, denoted hybrid DS/FFH, wherein multiple frequency hops occur within a single data-bit time. In this paper we perform a simulation-based study of the DS/FFH performance as compared to the existing standard DSSS and FHSS wireless networks. The performance metrics are bit-error probability and multiple-access capability. The parameter space of DS/FFH, including the DS spreading rate, frequency hopping rate, carrier frequencies, and numbers of users, is explored to show its performance under frequency-selective Rayleigh fading environments and multiuser interference. Direct digital synthesizers to achieve fast hopping speeds are also considered in our study.

99 GENERAL AND MISCELLANEOUS↗

Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment

We present a simulation-based study using deep convolutional neural networks (DCNNs) to identify neutrino interaction vertices in the MINERvA passive targets region, and illustrate the application of domain adversarial neural networks (DANNs) in this context. DANNs are designed to be trained in one domain (simulated data) but tested in a second domain (physics data) and utilize unlabeled data from the second domain so that during training only features which are unable to discriminate between the domains are promoted. MINERvA is a neutrino-nucleus scattering experiment using the NuMI beamline at Fermilab. A-dependent cross sections are an important part of the physics program, and these measurements require vertex finding in complicated events. To illustrate the impact of the DANN we used a modified set of simulation in place of physics data during the training of the DANN and then used the label of the modified simulation during the evaluation of the DANN. In conclusion, we find that deep learning based methods offer significant advantages over our prior track-based reconstruction for the task of vertex finding, and that DANNs are able to improve the performance of deep networks by leveraging available unlabeled data and by mitigating network performance degradation rooted in biases in the physics models used for training.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Unsupervised learning for identifying events in active target experiments

This article presents novel applications of unsupervised machine learning methods to the problem of event separation in an active target detector, the Active-Target Time Projection Chamber (AT-TPC). The overarching goal is to group similar events in the early stages of the data analysis, thereby improving efficiency by limiting the computationally expensive processing of unnecessary events. The application of unsupervised clustering algorithms to the analysis of two-dimensional projections of particle tracks from a resonant proton scattering experiment on 46 Ar is introduced. We explore the performance of autoencoder neural networks and a pre-trained VGG16 Simonyan and Zisserman (2015) convolutional neural network. We study clustering performance on both data from a simulated 46 Ar experiment, and real events from the AT-TPC detector. We find that a -means algorithm applied to simulated data in the VGG16 latent space forms almost perfect clusters. Additionally, the VGG16+-means approach finds high purity clusters of proton events for real experimental data. Here, we also explore the application of clustering the latent space of autoencoder neural networks for event separation. While these networks show strong performance, they suffer from high variability in their results.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Evaluating generative networks using Gaussian mixtures of image features

We develop a measure for evaluating the performance of generative networks given two sets of images. A popular performance measure currently used to do this is the Fréchet Inception Distance (FID). However, FID assumes that images featurized using the penultimate layer of Inception follow a Gaussian distribution. This assumption allows FID to be easily computed, since FID uses the 2-Wasserstein distance of two Gaussian distributions fitted to the featurized images. However, we show that Inception features of the ImageNet dataset are not Gaussian; in particular, each marginal is not Gaussian. To remedy this problem, we model the featurized images using Gaussian mixture models (GMMs) and compute the 2-Wasserstein distance restricted to GMMs. We define a performance measure, which we call WaM, on two sets of images by using inception (or another classifier) to featurize the images, estimate two GMMs, and use the restricted 2-Wasserstein distance to compare the GMMs. We experimentally show the advantages of WaM over FID, including how FID is more sensitive than WaM to image perturbations. By modelling the non-Gaussian features obtained from inception as GMMs and using a GMM metric, we can more accurately evaluate generative network performance.

machine learning, genrative adversarial networks↗

Phoebus: Network Middleware for Next-Generation Network Computing

The Phoebus project investigated algorithms, protocols, and middleware infrastructure to improve end-to-end performance in high speed, dynamic networks. The Phoebus system essentially serves as an adaptation point for networks with disparate capabilities or provisioning. This adaptation can take a variety of forms including acting as a provisioning agent across multiple signaling domains, providing transport protocol adaptation points, and mapping between distributed resource reservation paradigms and the optical network control plane. We have successfully developed the system and demonstrated benefits. The Phoebus system was deployed in Internet2 and in ESnet, as well as in GEANT2, RNP in Brazil and over international links to Korea and Japan. Phoebus is a system that implements a new protocol and associated forwarding infrastructure for improving throughput in high-speed dynamic networks. It was developed to serve the needs of large DOE applications on high-performance networks. The idea underlying the Phoebus model is to embed Phoebus Gateways (PGs) in the network as on-ramps to dynamic circuit networks. The gateways act as protocol translators that allow legacy applications to use dedicated paths with high performance.

99 GENERAL AND MISCELLANEOUS↗

Fast inference of deep neural networks in FPGAs for particle physics

Here, recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA (Field Programmable Gate Array) hardware has only just begun. FPGA-based trigger and data acquisition systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. A companion compiler package for this work is developed based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗