Search NASA⌕ Search

SEARCH · Search NASA

Results for “network optimization”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,675 records · Page 93
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Performance trade-offs in reconfigurable networks for HPC

Designing efficient interconnects to support high-bandwidth and low-latency communication is critical toward realizing high performance computing (HPC) and data center (DC) systems in the exascale era. At extreme computing scales, providing the requisite bandwidth through overprovisioning becomes impractical. These challenges have motivated studies exploring reconfigurable network architectures that can adapt to traffic patterns at runtime using optical circuit switching. Despite the plethora of proposed architectures, surprisingly little is known about the relative performances and trade-offs among different reconfigurable network designs. We aim to bridge this gap by tackling two key issues in reconfigurable network design. First, we study how cost, power consumption, network performance, and scalability vary based on optical circuit switch (OCS) placement in the physical topology. Specifically, we consider two classes of reconfigurable architectures: one that places OCSs between top-of-rack (ToR) switches—ToR-reconfigurable networks (TRNs)—and one that places OCSs between pods of racks—pod-reconfigurable networks (PRNs). Second, we tackle the effects of reconfiguration frequency on network performance. Our results, based on network simulations driven by real HPC and DC workloads, show that while TRNs are optimized for low fan-out communication patterns, they are less suited for carrying high fan-out workloads. PRNs exhibit better overall trade-off, capable of performing comparably to a fully non-blocking fat tree for low fan-out workloads, and significantly outperform TRNs for high fan-out communication patterns.

Teh, Min Yee↗
DOE OSTI2021

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2017

Packet Capture Solutions: PcapDB Benchmark for High-Bandwidth Capture, Storage, and Searching

PcapDB stands alone when looking at the overall field of competitors, from the cost-effective COTS hardware, to the efficient utilization of disk space that enables a longer packet history. A scalable, 100GbE-enabled system that indexes every packet and indexes flow data without complicated load-balancing requirements. The Transport Layer search and indexing approach led to patent-pending flow indexing technology, providing a specialized database system specifically optimized around providing fast flow searches. While there are a plethora of options in network packet capture, there are very few that are able to effectively manage capture rates of more than 10 Gb/s, distributed capture and querying, and a responsive user interface. By far, the primary competitor in the market place is Endace and DeepSee; in addition to meeting the technical requirements we set out in this document, they provide technical support and a fully 'appliance like' system. In terms of cost, however, our experience has been that the yearly maintenance charges alone outstrip the entire hardware cost of solutions like PcapDB. Investment in cyber security research and development is a large part of what has enabled us to build the base of knowlegable workers needed to defend government resources in the rapidly evolving cyber security landscape. We believe projects like Bro, WireCap, and Farm do more than just fill temporary gaps in our capabilities. They give allow us to build the firm foundation needed to tackle the next generation of cyber challenges. PcapDB was built with loftier ambitions than simply solving the packet capture of a single lab site, but instead to provide a robust, scaleable packet capture solution to the DOE complex and beyond.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2018

Integrated Cyber/Physical Grid Resiliency Modeling

This project explored coupling modeling and analysis methods from multiple domains to address complex hybrid (cyber and physical) attacks on mission critical infrastructure. Robust methods to integrate these complex systems are necessary to enable large trade-space exploration including dynamic and evolving cyber threats and mitigations. Reinforcement learning employing deep neural networks, as in the AlphaGo Zero solution, was used to identify "best" (or approximately optimal) resilience strategies for operation of a cyber/physical grid model. A prototype platform was developed and the machine learning (ML) algorithm was made to play itself in a game of 'Hurt the Grid'. This proof of concept shows that machine learning optimization can help us understand and control complex, multi-dimensional grid space. A simple, yet high-fidelity model proves that the data have spatial correlation which is necessary for any optimization or control. Our prototype analysis showed that the reinforcement learning successfully improved adversary and defender knowledge to manipulate the grid. When expanded to more representative models, this exact type of machine learning will inform grid operations and defense - supporting mitigation development to defend the grid from complex cyber attacks! This same research can be expanded to similar complex domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Reification of latent microstructures: On supervised unsupervised and semi-supervised deep learning applications for microstructures in materials informatics

Machine learning (ML), including deep learning (DL), has become increasingly popular in the last few years due to its continually outstanding performance. In this context, we apply machine learning techniques to "learn" the microstructure using both supervised and unsupervised DL techniques. In particular, we focus (1) on the localization problem bridging (micro)structure (localized) property using supervised DL and (2) on the microstructure reconstruction problem in latent space using unsupervised DL. The goal of supervised and semi-supervised DL is to replace crystal plasticity finite element model (CPFEM) that maps from (micro)structure (localized) property, and implicitly the (micro)structure (homogenized) property relationships, while the goal of unsupervised DL is (1) to represent high-dimensional microstructure images in a non-linear low-dimensional manifold, and (2) to discover a way to interpolate microstructures via latent space associating with latent microstructure variables. At the heart of this report is the applications of several common DL architectures, including convolutional neural networks (CNN), autoencoder (AE), and generative adversarial network (GAN), to multiple microstructure datasets, and the quest of neural architecture search for optimal DL architectures.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Y-12 Groundwater Protection Program Monitoring Well Inspection and Maintenance Plan

This plan describes the systematic approach for: inspecting the physical condition of monitoring wells at Y-12, determining maintenance needs that extend the life of a well, and identifying those wells that no longer meet acceptable monitoring well design or well construction standards and require plugging and abandonment. The inspection and maintenance of groundwater monitoring wells is one of the primary management strategies of the Y-12 Groundwater Protection Program (GWPP) Management Plan, that is, the “proactive stewardship of the extensive monitoring well network at Y-12" (Consolidated Nuclear Security, L.L.C. [CNS], 2018). Effective stewardship, and a program of routine inspections of the physical condition of each monitoring well, ensures that representative water-quality samples and hydrologic data are obtained from the well network and protects the subsurface environment. In accordance with the Y-12 GWPP Monitoring Optimization Plan (MOP) for Groundwater Monitoring Wells at the Y-12 National Security Complex, Oak Ridge, Tennessee (CNS, 2017), the status designation (active or inactive) for each well determines the scope and extent of well inspections and maintenance activities. This plan, in conjunction with the above document, formalizes the GWPP approach to focus available resources on monitoring wells which provide the most useful data, and for that reason the GWPP inspects and performs maintenance on the wells sampled by the GWPP. This plan applies to groundwater monitoring wells installed at Y-12 and the related waste management facilities located within the three hydrogeologic regimes: (1) the Bear Creek Hydrogeologic Regime (Bear Creek Regime), (2) the Upper East Fork Poplar Creek Hydrogeologic Regime (East Fork Regime), and (3) the Chestnut Ridge Hydrogeologic Regime (Chestnut Ridge Regime). The Bear Creek Regime encompasses the section of Bear Creek Valley (BCV) immediately west of Y-12. The East Fork Regime encompasses most of the Y-12 process, operations, and support facilities in BCV west of Scarboro Road. The Chestnut Ridge Regime is directly south of Y-12 and encompasses a section of Chestnut Ridge that is bounded to the west by a surface drainage feature (Dunaway Branch, located immediately west of Industrial Landfill II) and by Scarboro Road to the east. The GWPP maintains an extensive database of geographic and construction details and related information for the monitoring wells in each hydrogeologic regime in the Updated Subsurface Database for Bear Creek Valley, Chestnut Ridge, and Parts of Bethel Valley on the U.S. DOE Oak Ridge Reservation (CNS, 2019). A detailed description of the hydrogeologic framework at Y-12 can be found in the GWPP Management Plan (CNS, 2018).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Emerging Jets Search, Triton Server Deployment, and Track Quality Development: Machine Learning Applications in High Energy Physics

Machine learning is becoming prevalent in high energy physics, with numerous applications in physics analyses and event reconstruction showing great improvements compared to traditional computing methods. This thesis studies three projects which each propose new avenues for machine learning applications within the high energy physics CMS experiment located at CERN. In the first project, a search for a dark matter signal called “emerging jets” is performed, using graph neural networks to greatly increase sensitivity to the signal’s signature within the data. The result of this dark matter search sets the most stringent exclusion limits to date on theoretical emerging jet models. Motivated by inefficiencies encountered when processing the emerging jet graph neural network at Fermi National Accelerator Laboratory’s computing centers, the second project re-optimizes the computing centers for machine learning inference. This re-optimization uses NVIDIA Triton Inference Servers to process users’ analysis code heterogeneously, therefore achieving high processing throughput and decreasing user time-to-insight. The last project focuses on an upgrade to the CMS experiment’s real-time event selection system which improves physics object reconstruction under harsh processing conditions. A boosted decision tree is used to quickly and efficiently quantify a reconstructed particle’s “track quality” in order to remove particle tracks reconstructed erroneously. In summary, this thesis will not only present examples of how high energy physics can greatly benefit by leveraging machine learning techniques for physics analysis and reconstruction, but will also provide guidance on how the field can prepare for the inevitable increase in machine learning applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Feasibility of Hybrid Electro- and Acousto-Dynamical Systems for Quantum Optical Networks

We present results on an exploratory research program that aims to study the feasibility of novel, sustained, dense, and efficient quantum information generation, storage, retrieval, relay and distribution devices and systems towards future advanced quantum networking architectures. The pathfinder program is anchored on original ideas and device conceptual designs that turn the phononic-sourced challenges into an opportunity towards optimized transduction chains over a broad range of length and energy/temperature scales. The proposal involves conceptual design and feasibility towards integration, commissioning and benchmarking of challenging transduction devices in a scaled quantum network setup.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

A Two-Stage Stochastic Programming Approach for the Design of Renewable Ammonia Supply Chain Networks

This work considers the incorporation of renewable ammonia manufacturing sites into existing ammonia supply chain networks while accounting for ammonia price uncertainty from existing producers. We propose a two-stage stochastic programming approach to determine the optimal investment decisions such that the ammonia demand is satisfied and the net present cost is minimized. We apply the proposed approach to a case study considering deploying in-state renewable ammonia manufacturing in Minnesota’s supply chain network. We find that accounting for price uncertainty leads to supply chains with more ammonia demand met via renewable production and thus lower costs from importing ammonia from existing producers. These results show that the in-state renewable production of ammonia can act as a hedge against the volatility of the conventional ammonia market.

Mitrai, Ilias (ORCID:0000000289896864)↗
DOE OSTI2025

Functionalized Porous Polymer Networks as High-Performance PFAS Adsorbents

Toxic per- and polyfluoroalkyl substances (PFAS) are now found in nearly every water source on the planet. Exposure to these molecules can have negative health consequences, but the low concentration of PFAS relative to other solutes in water makes their removal challenging. Adsorbents offer a promising treatment route, but often exhibit low selectivities and removal capacities, as well as slow kinetics. The performance in these metrics can be improved by chemically optimizing PFAS binding sites and maximizing PFAS-adsorbent interactions. To explore how to achieve this, a porous polymer network solid (PPN-6, also known as PAF-1) was postsynthetically modified with various chemical moieties capable of leveraging unique combinations of electrostatic, hydrogen-bonding, hydrophobic, and fluorophilic interactions with PFAS molecules. Batch adsorption experiments and computational studies revealed that electrostatic and hydrogen-bonding interactions drive short-chain PFAS adsorption, while hydrophobic and fluorophilic interactions improve long-chain PFAS adsorption. In complex water matrices, a combination of electrostatic and fluorophilic interactions led to the greatest total PFAS removal. The best-performing material, functionalized with a fluorinated alkylammonium (PPN-6-FNDMB), selectively adsorbs PFAS with high capacity (up to 4.0 mmol/g) and rapid kinetics (equilibrium reached in <30 s). Furthermore, PPN-6-FNDMB outperforms several commercial adsorbents, achieving near-complete removal of 21 different PFAS from a groundwater sample collected at a US Air Force base. The PFAS could subsequently be desorbed from PPN-6-FNDMB, concentrating them by a factor of over 50 times. The recycled PPN-6-FNDMB could then be reused with minimal losses in long-chain PFAS adsorption capacity over four cycles.

Pezoulas, Ethan R↗
DOE OSTI2016

Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach

Here, this paper considers the problem of high-dimensional signal detection in a large distributed network whose nodes can collaborate with their one-hop neighboring nodes (spatial collaboration). We assume that only a small subset of nodes communicate with the fusion center (FC). We design optimal collaboration strategies which are universal for a class of deterministic signals. By establishing the equivalence between the collaboration strategy design problem and sparse principal component analysis (PCA), we solve the problem efficiently and evaluate the impact of collaboration on detection performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Sensitivity Analysis of Genome-Scale Metabolic Flux Prediction

TRIMER, Transcription Regulation Integrated with MEtabolic Regulation, is a genome-scale modeling pipeline targeting at metabolic engineering applications. Using TRIMER, regulated metabolic reactions can be effectively predicted by integrative modeling of metabolic reactions with a Transcription Factor (TF)-gene regulatory network (TRN), which is modeled via a Bayesian network (BN). In this paper, we focus on sensitivity analysis of metabolic flux prediction for uncertainty quantification of BN structures for TRN modeling in TRIMER. We propose a computational strategy to construct the uncertainty class of TRN models based on the inferred regulatory order uncertainty given transcriptomic expression data. With that, we analyze the prediction sensitivity of the TRIMER pipeline for the metabolite yields of interest. The obtained sensitivity analyses can guide Optimal Experimental Design (OED) to help acquire new data that can enhance TRN modeling and achieve specific metabolic engineering objectives, including metabolite yield alterations. Here we have performed small- and large-scale simulated experiments, demonstrating the effectiveness of our developed sensitivity analysis strategy for BN structure learning to quantify the edge importance in terms of metabolic flux prediction uncertainty reduction and its potential to effectively guide OED.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging

There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ~2800 galaxies with visual classification from GZ1, we reach an accuracy of ~0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ~2.5 percent galaxies are misclassified by GZ1 in our study. After correcting these galaxies’ labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Optimization of Canister Loading Patterns in Dual Purpose Canisters for Criticality Suppression

This report documents work performed in support of the US Department of Energy Office of Nuclear Energy (NE) Spent Fuel and Waste Disposition, Spent Fuel and Waste Science and Technology, under work breakdown structure element 1.08.01.03.05, “Direct Disposal of Dual Purpose Canisters.” In particular, this report fulfills milestone M3SF-22PN010305094, “Application of AI/ML techniques to optimize DPC loading,” within work package SF-22PN01030509, “Direct Disposal of Dual Purpose Canisters - PNNL.” This report continues the process of examining the potential for using loading optimization as a disposal criticality suppression technique. This latest update to the report added: 1. A validation of the artificial neural network (ANN) reactivity prediction tool against as-loaded dual-purpose canisters from the UNF-ST&DARDS database 2. Refinement of the algorithm to incorporate an additional DPC design to improve the predictions 3. Investigation of a storage and transportation focused loading optimization algorithm. A key result from this year’s work is that the ANN performance was significantly improved by including the additional model for the NUHOMS canisters and it is apparent that fuel type specific modeling considerations should be incorporated into the ANN in future work. The GRASP-enabled adaptive multi-objective memetic algorithm with partial clustering (GAMMA-PC) algorithm was evaluated as a tool for storage and transportation oriented optimization. The GAMMA-PC optimization routine considers decay heat at loading, the time between loading and when the canister is eligible for transportation and minimizes the number of casks loaded. Future work will develop a dose minimization optimization routine.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2016

Understanding the representativeness of FLUXNET for upscaling carbon flux from eddy covariance measurements

Eddy covariance data from regional flux networks are direct in situ measurement of carbon, water, and energy fluxes and are of vital importance for understanding the spatio-temporal dynamics of the the global carbon cycle. FLUXNET links regional networks of eddy covariance sites across the globe to quantify the spatial and temporal variability of fluxes at regional to global scales and to detect emergent ecosystem properties. This study presents an assessment of the representativeness of FLUXNET based on the recently released FLUXNET2015 data set. We present a detailed high resolution analysis of the evolving representativeness of FLUXNET through time. Results provide quantitative insights into the extent that various biomes are sampled by the network of networks, the role of the spatial distribution of the sites on the network scale representativeness at any given time, and how that representativeness has changed through time due to changing operational status and data availability at sites in the network. To realize the full potential of FLUXNET observations for understanding emergent ecosystem properties at regional and global scales, we present an approach for upscaling eddy covariance measurements. Informed by the representativeness of observations at the flux sites in the network, the upscaled data reflects the spatio-temporal dynamics of the carbon cycle captured by the in situ measurements. In conclusion, this study presents a method for optimal use of the rich point measurements from FLUXNET to derive an understanding of upscaled carbon fluxes, which can be routinely updated as new data become available, and direct network expansion by identifying regions poorly sampled by the current network.

58 GEOSCIENCES↗
DOE OSTI2026

Explainable physics-based constraints on reinforcement learning for accelerator optimization

We present a reinforcement learning (RL) framework for optimizing particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator optimization environments designed to emulate the Continuous Electron Beam Accelerator Facility at Jefferson Lab. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment. In addition, we find that the introduction of a physics-based surrogate enables our RL algorithms to reliably converge for difficult high-dimensional accelerator optimization environments.

explainability↗
DOE OSTI2019

Selection of a Cutting Tool by Means of a Digital Model

A digital model of a cutting tool produced by neural-network modeling is considered. By means of this model, the composition and structure of a wear-resistant coating may be optimized. The machining conditions that ensure maximum wear resistance of the tool may also be identified.

42 ENGINEERING↗
DOE OSTI2020

TensorFlow Quantum: A Software Framework for Quantum Machine Learning

We introduce TensorFlow Quantum (TFQ), an open source library for the rapid prototyping of hybrid quantum-classical models for classical or quantum data. This framework offers high-level abstractions for the design and training of both discriminative and generative quantum models under TensorFlow and supports high-performance quantum circuit simulators. We provide an overview of the software architecture and building blocks through several examples and review the theory of hybrid quantum-classical neural networks. We illustrate TFQ functionalities via several basic applications including supervised learning for quantum classification, quantum control, simulating noisy quantum circuits, and quantum approximate optimization. Moreover, we demonstrate how one can apply TFQ to tackle advanced quantum learning tasks including meta-learning, layerwise learning, Hamiltonian learning, sampling thermal states, variational quantum eigensolvers, classification of quantum phase transitions, generative adversarial networks, and reinforcement learning. We hope this framework provides the necessary tools for the quantum computing and machine learning research communities to explore models of both natural and artificial quantum systems, and ultimately discover new quantum algorithms which could potentially yield a quantum advantage.

Broughton, Michael↗