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 649 records · Page 36

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Improving ADAM through an implicit-explicit (IMEX) time-stepping approach

The ADAM optimizer, often used in machine learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. Here, this work shows that the classical ADAM algorithm is a first-order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the ADAM scheme obtained by using higher-order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical ADAM on several regression and classification problems.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Bright, Waveguide-based Entanglement Sources for High-rate Quantum Networking

We designed and built two polarization entanglement sources optimized for high-rate quantum networking under pump power constraints. We demonstrated entanglement swapping between the sources.

quantum↗

DOE OSTI2024

Approximating accelerator impedances with resonator networks

It is common in the accelerator community to use the impedance of accelerator components to describe wake interactions in the frequency domain. However, it is often desirable to understand such wake interactions in the time domain in a general manner for excitations that are not necessarily Gaussian in nature. Here, the conventional method for doing this involves taking the inverse Fourier Transform of the component impedance, obtaining the Green's Function, and then convolving it with the desired excitation distribution. This method can prove numerically cumbersome, for a convolution integral must be evaluated for each individual point in time when the wake function is desired. An alternative to this method would be to compute the wake function analytically, which would sidestep the need for repetitive integration. Only a handful of cases, however, are simple enough for this method to be tenable. One of these cases is the case where the component in question is an RLC resonator, which has a closed-form analytical wake function solution. This means that a component which can be represented in terms of resonators can leverage this solution. As it happens, common network synthesis techniques may be used to map arbitrary impedance profiles to RLC resonator networks in a manner the accelerator community has yet to take advantage of. In this work, we will use Foster Canonical Resonator Networks and partial derivative descent optimization to develop a technique for synthesizing resonator networks that well approximate the impedances of real-world accelerator components. We will link this synthesis to the closed-form resonator wake function solution, giving rise to a powerful workflow that may be used to streamline beam dynamics simulations.

43 PARTICLE ACCELERATORS↗

DOE OSTI2019

Convolutional Neural Networks for Hydrometeor Classification using Dual Polarization Doppler Radars

Traditional fuzzy logic hydrometeor classification algorithm is a common way to classify precipitation type from dual polarization doppler radar. We propose a deep learning-based method to estimate hydrometeors efficiently using observed radar variables such as horizontal reflectivity (Z H ), differential reflectivity (Z DR ), correlation coefficient (ρ HV ) and specific differential phase (K DP ) from National Weather Service NEXRAD collected at Vance AFB facility at the first elevation angle from January 1st, 2015 to July 31th, 2019. We stack matrices of values from these four polarimetric variables as one 3D array. Samples are preprocessed and divided into training, validation and test set with four target hydrometeor categories (Ice Crystals (IC), Dry Snow (DS), Light and/or Moderate Rain (RA) and Big Drops (rain) (BD)). We developed and optimized five Convolutional Neural Networks (CNNs) architectures and achieved an accuracy of 87.23% and 93.736% respectively using modified ResNet with two different input data selection strategies for hydrometeor classification. Training data selection strategies were important to ensure use of available samples in training for robust performance evaluated by applying the models to novel time period beyond what was use to train the model. Seasonal variation in atmospheric conditions lead to seasonal patterns of liquid vs solid forms of precipitation, that poses challenge for classifier and offer insights into domain specific approaches required for problem of hydrometeor identification. Computationally efficient and scalable approach for classification of hydrometeors offer opportunties to effectively use the large volumes of rich time series of radar observations that are becoming increasingly available.

Lu, Yuping↗

DOE OSTI2018

A superstructure optimization approach for process synthesis under complex reaction networks

Here in this work, we present mixed integer linear programming methods for the synthesis of processes that involve complex reaction networks. Specifically, we consider the modeling of reactors and interconnecting streams in systems where the composition of the reactor inlet streams can vary substantially, thereby making the determination of the limiting component as well as the calculation of the stream heating/cooling and power requirements challenging. First, towards the modeling of reactors, we develop an extent-based method which detects the limiting reactant of each reaction occurring in parallel with others, based on the inlet flows of the reactants. Second, we develop a computationally tractable method for the calculation of the work and heating/cooling duty needed to condition any stream of a process based on simple calculations that can be performed offline. Finally, we present how the two aforementioned components can be integrated in an optimization model generated based on a process superstructure. We demonstrate the application of the developed methods for the synthesis of a biorefinery.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2018

A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers

Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; (2) the networks are manually configured to achieve optimal results, and (3) the implementation of the network model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. Finally, we show that a quantum computer can find high quality values of intra-layer connection weights in a tractable time as the complexity of the network increases, a high performance computer can find optimal layer-based topologies, and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Finding diverse ways to improve algebraic connectivity through multi-start optimization

The algebraic connectivity, also known as the Fiedler value, is a spectral measure of network connectivity that can be increased through edge addition. We present an algorithm for producing many diverse ways to add a fixed number of edges to a network to achieve a near optimal Fiedler value. Previous Fielder value optimization algorithms (i.e. the greedy algorithm) output only one solution. Obtaining a single solution is rarely good enough for real-world network redesign problems, as practical constraints (political, physical or financial) may prevent implementation. Our algorithm takes a multi-start optimization approach, adding a random initial edge and then applies a greedy heuristic to improve the Fiedler value. The random choice moves us to a new region of the search space, enabling discovery of diverse solutions. Additionally, we present a Determinantal Point Process framework for quantifying diversity. We then apply a Markov chain Monte Carlo technique to sift through the large number of output solutions and locate a smaller, more manageable collection of highly diverse solutions that can be presented to network redesign engineers. We demonstrate the effectiveness of our algorithm on real-world graphs with varied structures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server

Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2020

Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability

Abstract Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of neural networks can enable the discovery of scientifically meaningful connections within geoscientific data. In particular, we use two methods for neural network interpretation called backward optimization and layerwise relevance propagation, both of which project the decision pathways of a network back onto the original input dimensions. To the best of our knowledge, LRP has not yet been applied to geoscientific research, and we believe it has great potential in this area. We show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network‐related geoscience research.

58 GEOSCIENCES↗

NASA NTRS1995

Parallel CFD design on network-based computer

Combining multiple engineering workstations into a network-based heterogeneous parallel computer allows application of aerodynamic optimization with advanced computational fluid dynamics codes, which can be computationally expensive on mainframe supercomputers. This paper introduces a nonlinear quasi-Newton optimizer designed for this network-based heterogeneous parallel computing environment utilizing a software called Parallel Virtual Machine. This paper will introduce the methodology behind coupling a Parabolized Navier-Stokes flow solver to the nonlinear optimizer. This parallel optimization package is applied to reduce the wave drag of a body of revolution and a wing/body configuration with results of 5% to 6% drag reduction.

Cheung, Samson↗

DOE OSTI2020

Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow

We develop, in this paper, a machine learning approach to optimize the real-time operation of electric power grids. In particular, we learn feasible solutions to the AC optimal power flow (OPF) problem with negligible optimality gaps. The AC OPF problem aims at identifying optimal operational conditions of the power grids that minimize power losses and/or generation costs. Due to the computational challenges with solving this nonconvex problem, many efforts have focused on linearizing or approximating the problem in order to solve the AC OPF on faster timescales. However, many of these approximations can be fairly poor representations of the actual system state and still require solving an optimization problem, which can be time consuming for large networks. In this work, we learn a mapping between the system loading and optimal generation values, enabling us to find near-optimal and feasible AC OPF solutions. This allows us to bypass solving the traditionally nonconvex AC OPF problem, resulting in a significant decrease in computational burden for grid operators.

machine learning↗

DOE OSTI2020

Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow: Preprint

machine learning↗

DOE OSTI2019

Matching networks for wireless power transfer and related techniques

In one implementation, an analytical approach to determining an improved and/or optimal design of a matching network in a capacitive or inductive WPT system is provided. In one implementation, for example, a framework is provided to enable stage(s) of the network to simultaneously provide gain and compensation. The multistage matching network efficiency can be improved and/or optimized, such as by using the method of Lagrange multipliers, resulting in the optimum distribution of gain and compensation among the L-section stages.

Sinha, Sreyam↗

DOE OSTI2026

A Reverse Logistics Tool For Ev Battery Recycling And Repurposing,

The demand for electric vehicles (EVs) in the United States is projected to rise significantly, with sales expected to reach approximately 4.1 million units by 2030. However, the U.S. remains heavily reliant on imports for the batteries and critical raw materials—such as lithium, cobalt, and nickel—that power these vehicles. As of 2024, around 70% of these imports originate from China. This dependency has become even more precarious following China’s imposition of export restrictions in April 2025, a retaliatory move against U.S. tariffs. These developments highlight the strategic vulnerabilities posed by China’s dominant position in the critical materials market. Compounding the issue, decades of intensive extraction have severely depleted global reserves of critical materials, widening the gap between supply and growing demand. This situation underscores the urgent need for the U.S. and other nations to diversify their sources of critical materials and enhance domestic capabilities to secure these resources—an essential step toward ensuring long-term energy security. At the end of their lifecycle—whether due to the battery’s degradation or the retirement of the vehicle—EV batteries are often improperly disposed of or sent to landfills. However, many of these batteries still retain usable capacity and can follow one of three alternative pathways: (a) Re-used: deployed in another vehicle with a shorter driving range, (b) Re-purposed: utilized act as a backup storage/power for data centers, solar panels, and e-scotters or (c) Recycled: broken down to recover the critical materials. To that end, the proposed tool (REBORN) is designed to optimize the reverse logistics network for battery repurposing and recycling. Its goal is to minimize associated costs while identifying optimal locations for battery collection and processing. Ultimately, REBORN ensures that each battery is used to its fullest potential.

Srinivas, SrikarV. [Idaho National Laboratory (INL↗

DOE OSTI2020

Embedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaics

Process optimization of photovoltaic devices is a time-intensive, trial-and-error endeavor, which lacks full transparency of the underlying physics and relies on user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach for gallium arsenide (GaAs) solar cells that identifies the root cause(s) of underperformance with layer-by-layer resolution and reveals alternative optimal process windows beyond traditional black-box optimization. Our Bayesian network approach links a key GaAs process variable (growth temperature) to material descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency). For this purpose, we combine a Bayesian inference framework with a neural network surrogate device-physics model that is 100× faster than numerical solvers. With the trained surrogate model and only a small number of experimental samples, our approach reduces significantly the time-consuming intervention and characterization required by the experimentalist. As a demonstration of our method, in only five metal organic chemical vapor depositions, we identify a superior growth temperature profile for the window, bulk, and back surface field layer of a GaAs solar cell, without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above traditional grid search methods.

14 SOLAR ENERGY↗

DOE OSTI2024

Optimal environmental and economic performance trade-offs for fifth generation district heating and cooling network topologies with waste heat recovery

Network topology greatly influences both the economic and environmental performance of fifth generation district heating and cooling (5GDHC) systems. In this study the optimal trade-offs between the environmental and economic performance of 5GDHC network topologies for a five-building district with waste heat recovery were explored. A life cycle assessment method was used to calculate the total life cycle CO 2 emissions (LCCO2) associated with the installation and operation of various network topologies. Twelve months of empirical data from a data center cooling system were analyzed to assess its suitability for integration into a 5GDHC system. The most suitable method for utilizing this waste heat was selected based on the ambient loop warm pipe setpoint, waste heat temperature, and district energy system configuration. A multi-objective optimization algorithm was used to select the 5GDHC network topology that provided the optimal trade-off between LCCO2 and life cycle cost (LCC). A trade-off parameter was employed to weigh the importance of each objective in the selection process. The results showed waste heat from the data center was suitable for integration into the 5GDHC system due to its availability and consistent temperature profile. When return temperatures of 25 °C or higher were available from the liquid-cooled system, direct pre-heating of the ambient loop warm pipe was found to be the most effective waste heat integration method. The selection of the network topology that provided the optimal trade-off between LCCO2 and LCC (optimal trade-off topology) was highly dependent on factors such as fuel prices, CO 2 prices, electricity CO 2 emissions factors, availability of waste heat, embodied CO 2 emissions associated with network installation and network infrastructure costs. Optimal trade-off topologies produced substantial LCCO2 reductions relative to corresponding LCC increases. LCCO2 reduction to LCC increase ratios from 5.78 to 117.79 were identified with CO 2 offset costs ranging from 4.77 to 60.08 ($/tCO 2 e).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2024

Grad–Shafranov equilibria via data-free physics informed neural networks

A large number of magnetohydrodynamic (MHD) equilibrium calculations are often required for uncertainty quantification, optimization, and real-time diagnostic information, making MHD equilibrium codes vital to the field of plasma physics. In this paper, we explore a method for solving the Grad–Shafranov equation by using physics-informed neural networks (PINNs). For PINNs, we optimize neural networks by directly minimizing the residual of the partial differential equation as a loss function. We show that PINNs can accurately and effectively solve the Grad–Shafranov equation with several different boundary conditions, making it more flexible than traditional solvers. This method is flexible as it does not require any mesh and basis choice, thereby streamlining the computational process. We also explore the parameter space by varying the size of the model, the learning rate, and boundary conditions to map various tradeoffs such as between reconstruction error and computational speed. Additionally, we introduce a parameterized PINN framework, expanding the input space to include variables such as pressure, aspect ratio, elongation, and triangularity in order to handle a broader range of plasma scenarios within a single network. Parameterized PINNs could be used in future work to solve inverse problems such as shape optimization.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

Optimizing Signal Timing Control for Large Urban Traffic Networks Using an Adaptive Linear Quadratic Regulator Control Strategy

We discuss how traffic signal control is important for intersection safety and efficiency. However, most traffic signal control methods are designed for individual intersections or corridors. Although some adaptive control systems have been developed, the methods used are often proprietary and not published, making it difficult to evaluate their effectiveness. This study proposes an adaptive multi-input and multi-output traffic signal control method that not only can improve network-wide traffic operations in terms of reduced traffic delay and energy consumption, but also is more computationally feasible than existing centralized signal control methods. Considering intersection interactions, a linear dynamic traffic system model was built and adaptively updated to reflect how the signal control input of each intersection affects network-wide vehicle travel delay. Based on the system model, an adaptive linear-quadratic regulator (LQR) was designed to minimize both traffic delay and incremental changes in the control input. The proposed control method was evaluated in a microscopic traffic simulation environment with a 35-intersection network of Bellevue City, Washington. Simulation results show that the proposed method had shorter average traffic delays in the network when compared with the traffic delays controlled by the state-of-the-art max-pressure, self-organizing traffic lights, and independent deep Q network methods.

42 ENGINEERING↗