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.

SourceResearch connectionFrom yearThrough year

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

At least 1,387 records · Page 77

All sources NASA NTRS DOE OSTI

DOE OSTI2017

A learning-based measurement framework for traffic matrix inference in software defined networks

Here, we propose an intelligent framework for Traffic Matrix (TM) inference in Software Defined Networks (SDN) where the Ternary Content Addressable Memory (TCAM) entries of switches are partitioned into two parts to: (1) effectively aggregate part of incoming flows for aggregate measurements, and (2) de-aggregate and directly measure the most informative flows for per-flow measurements. These measurements are then processed to effectively estimate the size of network flows. Under hard resource constraints of limited TCAM sizes, we show how to design the optimal and efficient-compressed flow aggregation matrices. We propose an optimal Multi-Armed Bandit (MAB) based algorithm to adaptively measure the most rewarding flows. We evaluate the performance of our framework using real traffic traces from different network environments and by considering two main applications: TM estimation and Heavy Hitter (HH) detection. Moreover, we have implemented a prototype of our framework in Mininet to demonstrate its effectiveness.

42 ENGINEERING↗

DOE OSTI2021

State-of-the-Art Techniques for Large-Scale Stochastic Unit Commitment

Recent advances in deterministic unit commitment, both formulaic and algorithmic, along with modern algorithmic approaches for stochastic programming, have enabled the solution of stochastic unit commitment problems with hundreds of scenarios on large-scale transmission networks. In this presentation, we will give an overview of these methods, including lazy transmission constraint generation, lower-bounding techniques, and heuristics, all of which can be executed in concert with customized decomposition approaches for optimization under uncertainty. We demonstrate the effectiveness of these techniques on the TAMU Texas7K synthetic transmission network, leveraging realistic high-resolution forecasts based on NREL renewable resource availability data. The software leveraged for these demonstrations is available via the open-source software packages EGRET (for electrical grid optimization) and mpi-sppy (for optimization under uncertainty).

27 ARPA - Advanced Research Projects Agency-Energy↗

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

Insights into Constraining Rate Coefficients in Fuel Oxidation Mechanisms Using Genetic Algorithm Optimization

Accurate fuel oxidation mechanisms can enable predictive capabilities that aid in advancing combustion technologies. High-level computational kinetics can yield reasonable rate coefficients with uncertainties, in some cases, below a factor of 2. Computed rate coefficients can be constrained further by optimizing against experimental data. Here, we explore the application of genetic algorithm (GA) optimization to constrain computed rate coefficients in complex fuel oxidation mechanisms in conjunction with temperature-dependent species mole fractions from jet-stirred reactor (JSR) measurements. Cyclohexane is a model candidate for understanding the reactivity of cyclic fuels. In this work, we optimize the rate coefficients of the most recent literature cyclohexane mechanism, which incorporates theoretically computed rate coefficients for the reaction networks stemming from the first and second O 2 addition pathways, against the experimental results of two separate literature JSR studies. Optimization consistency is evaluated by carrying out three GA optimizations: fitting to the temperature-dependent species mole fractions in each JSR experiment separately and simultaneously fitting the species mole fractions in both experiments. Local sensitivity analyses are used to identify five influential low-temperature oxidation reactions for optimization. Although the three optimizations do not yield identical rate coefficients, the direction of change in all five rate coefficients is consistent among the three optimizations. Performance of the models from the three optimizations is assessed against literature ignition delay times with differences in the level of agreement observed among the different optimizations. In conclusion, comparisons are made with our recent optimization work of a cyclopentane oxidation master-equation model against time-resolved species concentrations, and insights and improvements of the strategy for constraining rate coefficients using GA optimization are discussed.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2026

Data for High Yield Production of 3-Hydroxypropionic Acid Using Issatchenkia orientalis

Biomanufacturing provides a more sustainable alternative to fossil-based chemical manufacturing. 3-Hydroxypropionic acid (3HP) is a top Department of Energy value-added chemical and precursor to bioplastics, yet cost-effective microbial production remains elusive. Here, we establish the acid-tolerant yeast Issatchenkia orientalis as a robust host for low-pH 3HP biosynthesis. Genome-scale modeling identifies the β-alanine pathway as optimal, offering the highest theoretical yield and lowest oxygen requirement. Thermodynamic analysis confirms its favorability under acidic conditions. Using sequence similarity network analysis, we discover highly active aspartate 1-decarboxylase (PAND), β-alanine-pyruvate aminotransferase (BAPAT), and 3HP dehydrogenase (YDFG), which significantly improve the pathway efficiency. Next, to further elevate the production, pathway optimization through multi-copy PAND integration, byproduct elimination (knockouts of pyruvate decarboxylase and glycerol-3-phosphate dehydrogenase), and reinforcement of aspartate flux by overexpression of pyruvate carboxylase and aspartate amino transferase improves the titer to 29 g/L in shake flasks. Fed-batch fermentation at pH 4 with low-cost corn steep liquor medium further increases the production to 92 g/L with 0.7 g/g yield and 0.55 g/L/h productivity. Techno-economic analysis indicates that such performance could potentially enable a financially viable process for sustainable acrylic acid production. This work establishes I. orientalis as a next-generation platform for cost-effective 3HP production and paves the way toward industrial commercialization.

Bioproducts↗

DOE OSTI2018

Microstructural Materials Design Via Deep Adversarial Learning Methodology

Identifying the key microstructure representations is crucial for computational materials design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for microstructural materials design. Some MCR approaches are not applicable for microstructural materials design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for microstructural materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Engineering↗

DOE OSTI2023

Journey Over Destination: Differentiable Sensor Placement Enhances Generalization [Poster]

The challenge of reconstructing spatial fields that change over time from limited sensor data has been a focal point for many research studies. Various machine learning methods have been used in attempts to address this complex issue, including convolutional neural networks. All of the proposed methods share a common requirement that the user needs to manually determine the sensor positions. This requirement remains a limiting factor in the ongoing quest for efficient learning and accurate field reconstruction. This study aims to present a method that enables a model to optimize sensor positions via backpropagation, thereby facilitating the model’s exploration of the spatial domain and enhancing sensor positioning effectively. Indexing naturally incorporates discrete decisions. This operation is nondifferentiable which is a requirement for the application of gradient-based optimization methods. We showcased its effectiveness by training an attention-based neural network, which achieved top-tier performance on two separate datasets. To our knowledge, this represents the first fully end-to-end differentiable workflow for enhancing sensor placement within a neural network model.

58 GEOSCIENCES↗

DOE OSTI2022

Sparse Deep Neural Network Inference using different Programming Models

Sparse deep neural networks have gained increasing attention recently in achieving speedups on inference with reduced memory footprints. However, the real-world applications are little shown with specialized optimizations, yet a wide variety of DNN tasks remain dense without exploiting the advantages of sparsity in networks. Recent work presented by MIT/IEEE/Amazon GraphChallenge has demonstrated significant speedups and various techniques. Still, we find that there is limited investigation of the impact of various Python and C\slash C++ based programming models to explore new opportunities in general cases. In this work, we provide performance evaluation through different programming models using CuPy, cuSPARSE, and OpenMP to discuss the advantages and disadvantages of our sparse implementations on single-GPU and multiple GPUs of NVIDIA DGX-A100 40GB/80GB platforms.

machine learning, HPC↗

DOE OSTI2026

Deciphering the Conflict Between Ion and Electron Percolating Networks in Solid-State Battery Cathodes

High-energy- and power-density solid state batteries require an optimal cathode composition and microstructural arrangement of cathode active material, solid-state electrolyte, conductive carbon, and binder to simultaneously support lithium-ion transport, electron conduction, and storage capacity. The ion and electron conducting phases in solid-state cathodes counteract each other's percolating networks as their mass ratios increase or decrease relative to each other. Here, we investigate targeted mass ratio variations of argyrodite solid electrolyte and two different types of conductive carbon (particles and fibers) in composite LiNi0.8Mn0.1Co0.1O2 (NMC811) solid-state cathodes to ascertain the ionic-electronic tradeoffs in cathode performance. Through ionic and electronic conductivity measurements on composite cathodes, as well as rate-testing and cycling performance in full cells, it is shown that the conductive carbon fibers form a percolative electronic network within the composite at a lower mass ratio (3-5 wt%) than particulate carbon (>5 wt%). The threshold to achieve electronic percolation coincides with higher accessible capacity in the cathode as the active material particles become electronically connected. However, carbon loadings beyond this percolation threshold lead to increased ion transport resistance, arising from disruptions to ionic conduction pathways and degraded contact at the interface between the electrolyte and active materials. Imaging, spectroscopy, and physics-based models quantitatively describe the relationship between carbon and electrolyte compositions and the cell's capacity and rate performance through percolation theory. This work demonstrates the importance of quantitatively understanding percolating networks in solid-state cells and that strategic engineering of conductive carbon morphologies can further increase the energy- and power-density of solid-state cells.

25 ENERGY STORAGE↗

DOE OSTI2019

Assessment of Existing Capabilities and Future Needs for Designing Networked Microgrids

This is a review of existing microgrid design tool capabilities, such as the Microgrid Design Tool (MDT), LANL PNNL NRECA Optimal Resilience Model (LPNORM), Distributed Energy Resource-Customer Adoption Model (DER-CAM), Renewable Energy Optimization (REopt), and the Hybrid Optimization Model for Multiple Energy Resources (HOMER). Additionally, other simulation and analysis tools which may provide fundamental support will be examined. These will include GridLAB-DTM, OpenDSS, and the hierarchical Engine for Large-scale Infrastructure Co-Simulation (HELICS). Their applicability to networked microgrid operations will be evaluated, and strengths and gaps of existing tools will be identified. This review will help to determine which elements of the proposed optimal design and operations (OD&D) tool should be formulated from first principles, and which elements should be integrated from past DOE investments.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with convergence rate, where is the number of iterations.

reinforcement learning, structured learning, conve↗

DOE OSTI2024

Modern deep neural networks for Direct Normal Irradiance forecasting: A classification approach

The escalating energy demand and the adverse environmental impacts of fossil-fuel use necessitate a shift towards cleaner and renewable alternatives. Concentrated Solar Power (CSP) technology emerges as a promising solution, offering a carbon-free alternative for power generation. The efficiency and profitability of CSP depend on the Direct Normal Irradiance (DNI) component of solar radiation; hence, accurate DNI forecasting can help optimize CSP plants’ operations and performance. The unpredictable nature of weather phenomena, particularly cloud cover, introduces uncertainty into DNI projections. Existing DNI forecasting models use meteorological factors, which are both challenging to estimate numerically over short prediction windows and expensive to model through data at a sufficiently high spatial and temporal resolution. This research addresses the challenge by presenting a novel approach that formulates DNI prediction as a multi-class classification problem, departing from conventional regression-based methods. The primary objective of this classification framework is to identify optimal periods aligning with specific operational thresholds for CSP plants, contributing to enhanced dispatch optimization strategies. We model the DNI classification problem using four advanced deep neural networks – rectified linear unit (ReLU) networks, 1D residual networks (ResNets), bidirectional long short-term memory (BiLSTM) networks, and transformers – achieving accuracies up to 93.5% without requiring meteorological parameters.

14 SOLAR ENERGY↗

DOE OSTI2018

Programmable design of orthogonal protein heterodimers

Specificity of interactions between two DNA strands, or between protein and DNA, is often achieved by varying bases or side chains coming off the DNA or protein backbone—for example, the bases participating in Watson–Crick pairing in the double helix, or the side chains contacting DNA in TALEN–DNA complexes. By contrast, specificity of protein–protein interactions usually involves backbone shape complementarity1, which is less modular and hence harder to generalize. Coiled-coil heterodimers are an exception, but the restricted geometry of interactions across the heterodimer interface (primarily at the heptad a and d positions2) limits the number of orthogonal pairs that can be created simply by varying side-chain interactions3,4. Here we show that protein–protein interaction specificity can be achieved using extensive and modular side-chain hydrogen-bond networks. We used the Crick generating equations5 to produce millions of four-helix backbones with varying degrees of supercoiling around a central axis, identified those accommodating extensive hydrogen-bond networks, and used Rosetta to connect pairs of helices with short loops and to optimize the remainder of the sequence. Of 97 such designs expressed in Escherichia coli, 65 formed constitutive heterodimers, and the crystal structures of four designs were in close agreement with the computational models and confirmed the designed hydrogen-bond networks. In cells, six heterodimers were fully orthogonal, and in vitro—following mixing of 32 chains from 16 heterodimer designs, denaturation in 5 M guanidine hydrochloride and reannealing—almost all of the interactions observed by native mass spectrometry were between the designed cognate pairs. The ability to design orthogonal protein heterodimers should enable sophisticated protein-based control logic for synthetic biology, and illustrates that nature has not fully explored the possibilities for programmable biomolecular interaction modalities.

Chen, Zibo↗

DOE OSTI2025

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗

DOE OSTI2016

Transitions in genetic toggle switches driven by dynamic disorder in rate coefficients

In biochemical systems, intrinsic noise may drive the system switch from one stable state to another. We investigate how kinetic switching between stable states in a bistable network is influenced by dynamic disorder, i.e., fluctuations in the rate coefficients. Using the geometric minimum action method, we first investigate the optimal transition paths and the corresponding minimum actions based on a genetic toggle switch model in which reaction coefficients draw from a discrete probability distribution. For the continuous probability distribution of the rate coefficient, we then consider two models of dynamic disorder in which reaction coefficients undergo different stochastic processes with the same stationary distribution. In one, the kinetic parameters follow a discrete Markov process and in the other they follow continuous Langevin dynamics. We find that regulation of the parameters modulating the dynamic disorder, as has been demonstrated to occur through allosteric control in bistable networks in the immune system, can be crucial in shaping the statistics of optimal transition paths, transition probabilities, and the stationary probability distribution of the network.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Learning high-dimensional parametric maps via reduced basis adaptive residual networks

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is beneficial to have a compact parametrization in order to ameliorate the ill-posedness of the neural network training problem. By linearly restricting high-dimensional maps to informed reduced bases of the inputs, one can compress high-dimensional maps in a constructive way that can be used to detect appropriate basis ranks, equipped with rigorous error estimates. A scalable neural network learning framework is thus to learn the nonlinear compressed reduced basis mapping. Unlike the reduced basis construction, however, neural network constructions are not guaranteed to reduce errors by adding representation power, making it difficult to achieve good practical performance. Inspired by recent approximation theory that connects ResNets to sequential minimizing flows, we present an adaptive ResNet construction algorithm. This algorithm allows for depth-wise enrichment of the neural network approximation, in a manner that can achieve good practical performance by first training a shallow network and then adapting. We prove universal approximation of the associated neural network class for $L^2_v$ functions on compact sets. Our overall framework allows for constructive means to detect appropriate breadth and depth, and related compact parametrizations of neural networks, significantly reducing the need for architectural hyperparameter tuning. Numerical experiments for parametric PDE problems and a 3D CFD wing design optimization parametric map demonstrate that the proposed methodology can achieve remarkably high accuracy for limited training data, and outperformed other neural network strategies we compared against.

42 ENGINEERING↗

DOE OSTI2023

A GPU-Accelerated Population Generation, Sorting, and Mutation Kernel for an Optimization-Based Causal Inference Model

We develop a GPU-accelerated machine learning generative adversarial network model that can be used with observational data for the purpose of constructing causal inferences. The theoretical basis of our machine learning model is novel and is conceptualized to be operable and scalable for high performance computing platforms. Our GPU-accelerated code enables large-scale parallelization of the computation within a common and accessible computing environment. This will expand the reach of our model and empower research in new substantive domains while maintaining the underlying theoretical properties.

Cho, Wendy K. Tam↗