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 1,549 records · Page 86
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Accelerating computational fluid dynamics simulation of post-combustion carbon capture modeling with MeshGraphNets

Packed columns are commonly used in post-combustion processes to capture CO 2 emissions by providing enhanced contact area between a CO 2 -laden gas and CO 2 -absorbing solvent. To study and optimize solvent-based post-combustion carbon capture systems (CCSs), computational fluid dynamics (CFD) can be used to model the liquid–gas countercurrent flow hydrodynamics in these columns and derive key determinants of CO 2 -capture efficiency. However, the large design space of these systems hinders the application of CFD for design optimization due to its high computational cost. In contrast, data-driven modeling approaches can produce fast surrogates to study large-scale physics problems. We build our surrogates using MeshGraphNets (MGN), a graph neural network framework that efficiently learns and produces mesh-based simulations. We apply MGN to a random packed column modeled with over 160K graph nodes and a design space consisting of three key input parameters: solvent surface tension, inlet velocity, and contact angle. Our models can adapt to a wide range of these parameters and accurately predict the complex interactions within the system at rates over 1700 times faster than CFD, affirming its practicality in downstream design optimization tasks. This underscores the robustness and versatility of MGN in modeling complex fluid dynamics for large-scale CCS analyses.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Tailor : Altering Skip Connections for Resource-Efficient Inference

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this article, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network’s skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware-efficient implementation with minimal to no accuracy loss. We introduceTailor, a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network’s skip connections to lower the hardware cost.Tailorimproves resource utilization by up to 34% for block random access memories (BRAMs), 13% for flip-flops (FFs), and 16% for look-up tables (LUTs) for on-chip, dataflow-style architectures.Tailorincreases performance by 30% and reduces memory bandwidth by 45% for a two-dimensional processing element array architecture.

Computer Science↗
DOE OSTI2022

Transfer learning driven design optimization for inertial confinement fusion

Transfer learning is a promising approach to create predictive models that incorporate simulation and experimental data into a common framework. In this technique, a neural network is first trained on a large database of simulations and then partially retrained on sparse sets of experimental data to adjust predictions to be more consistent with reality. Previously, this technique has been used to create predictive models of Omega [Humbird et al., IEEE Trans. Plasma Sci. 48, 61–70 (2019)] and NIF [Humbird et al., Phys. Plasmas 28, 042709 (2021); Kustowski et al., Mach. Learn. 3, 015035 (2022)] inertial confinement fusion (ICF) experiments that are more accurate than simulations alone. Here, in this work, we conduct a transfer learning driven hypothetical ICF campaign in which the goal is to maximize experimental neutron yield via Bayesian optimization. The transfer learning model achieves yields within 5% of the maximum achievable yield in a modest-sized design space in fewer than 20 experiments. Furthermore, we demonstrate that this method is more efficient at optimizing designs than traditional model calibration techniques commonly employed in ICF design. Such an approach to ICF design could enable robust optimization of experimental performance under uncertainty.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Spatiotemporal forecasting of the edge localized modes in tokamak plasmas using neural networks

Artificial intelligence techniques have been increasingly adopted by the plasma and fusion science to address problems like plasma reconstruction, surrogate modeling, and tokamak/stellarator optimization. A key focus in sustained fusion research is the prediction and mitigation of edge-localized-modes (ELMs), instabilities that occur in short, periodic bursts and can cause erosion to the tokamak vessel wall. Recent research has demonstrated the power of neural networks in approximating continuous functions. In this work, we build spatiotemporal forecasting models that can predict the onset of ELMs and their evolution at early stages. We leverage recent advances in generative modeling, sequence-to-sequence modeling, and Fourier neural operators to propose architectures and training strategies that can learn to forecast short to long term dynamics of the noisy signals due to ELMs. We benchmark the developed model against a state-of-the-art foundation model using the beam emission spectroscopy (BES) data that captures the plasma fluctuations due to ELMs over a 8 x 8 spatial grid. Our models demonstrate high accuracy, outperforming the baselines, in predicting the evolution of BES signals during ELM events. Furthermore, the developed models exhibit high accuracy in predicting the rapid rise and relaxation of the signals due to ELMs within 30–80 µs.

edge localized modes↗
DOE OSTI2016

High-resolution Groundwater Investigation at a FUSRAP Site with an Aging Water-supply Infrastructure: Former Harshaw Chemical Company, Ohio - 16146

The Former Harshaw Chemical Company (HCC) Site is located in Cleveland, Ohio, approximately 5 kilometers (km) (3 miles) south of downtown Cleveland, in an industrialized area adjacent to the Cuyahoga River and Big Creek. Developed site parcels include former production areas with legacy buildings, former production area foundations, parking areas associated with previously demolished buildings, and re-developed privately-owned commercial properties. The HCC Site was initially developed 1905 and commercially manufactured chemical solvents, metal salts, fluorides, hydrofluoric acids, and other chemical products. HCC began production activities for the Manhattan Engineer District (MED) in late 1942 in support of the United States' early atomic weapons program. The primary process conducted by the HCC consisted of the refining of uranium oxide to produce several uranium-bearing materials, including uranium hexafluoride (UF{sub 6}), uranium tetrafluoride (UF{sub 4}), and uranium tetrachloride (UCl{sub 4}). The HCC also conducted numerous chemical and radiological research and production activities for the MED and later for the Atomic Energy Commission (AEC). Groundwater and soil contamination resulting from these activities is characterized in the site Remedial Investigation Report (USACE 2009) and primarily found near the G-1 process building. A Feasibility Study (USACE 2012) evaluated soil remediation alternatives and their potential impacts to future groundwater conditions. Since there is no groundwater pathway in the assumed industrial future land use, groundwater evaluations are intended to demonstrate that further degradation of groundwater will not occur after potential soil remediation. Total uranium is the primary MED-based groundwater contaminant and was numerically simulated using a site-specific groundwater flow and transport model. Remedial results are judged in terms of no significant impact, significant positive impact (i.e., significantly decreased extent of contamination), or significant negative impact (i.e., significantly increased extent of contamination). A complicating factor in the groundwater simulation and decision-making process for this site is the existence of municipal water-line leakage on and around the site. This aging infrastructure, in conjunction with the generations of modifications, promoted leakage and fresh-water contact with contaminated soils. To optimize the groundwater conceptual site model for numerical model updates, a high-density groundwater well network was installed in conjunction with the demolition of the G-1 building. The results of the detailed groundwater investigation, coincident soil sampling, utility-line termination, municipal water-line repairs, water-level collection, and uranium sampling indicates the groundwater is re-equilibrating and will lead to optimal decisions and site remediation. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2020

Machine learning coupled multi-scale modeling for redox flow batteries

The reaction distribution in macro or device-scale has been studied for redox flow batteries. The reaction distribution on electrode pore-scale structure however is not well understood, lacking especially on how the reaction distribution on the pore-scale may impact the overall performance of a flow battery. This study introduces for the first time a framework of a multi-scale model that provides understanding of the relationship between the pore-scale electrode structure reaction and the device-scale electrochemical reaction uniformity within the flow battery. A reduced order model is constructed based on 128 pore-scale simulations, which provide a quantitative relationship between the battery operation conditions (inlet velocity, current density, inlet concentration) and the surface reaction uniformity for the pore-scale sample. The multi-scale framework upscales this pore-scale surface reaction uniformity to device-scale combined uniformity. Based on the multi-scale model, a time-varying optimization of the inlet velocity is established, leading to significant reduction on pump power consumption with targeted surface reaction uniformity. The multi-scale model establishes the critical link between the micro-structure of a flow battery component and its performance at the macro-scale, therefore providing rationale for further operational or material optimization.

flow batteries, machine learning, multi-scale mode↗
DOE OSTI2019

2019 Wireless Test Bed Range Manual

Idaho National Laboratory (INL), Next Generation Wireless Test Bed (NGWTB) program, is part of the Critical Infrastructure Protection (CIP) initiative. Our nation’s reliance on wireless and Internet technology is rapidly evolving as more corporations and government agencies, employees, and handheld devices include mobile connectivity for both voice and data. The competitive advantage offered by a mobile workforce is leading many corporations to make wireless integration and convergence a top business priority. Similarly, military systems worldwide are rapidly embracing next-generation commercial technologies to accelerate network-centric capabilities and provide enhanced situational awareness. While handheld devices such as laptops, BlackBerrys, and cell phones once had limited mobility and range, they are rapidly incorporating new and multiple protocols such as Bluetooth, Wi-Fi, Satellite, and broadband cellular (3G/4G) on a single platform to increase their effectiveness and agility. Worldwide there is exponential growth in public Wi-Fi and/or Satellite connectivity access nodes, and 3G/4G cellular continues to evolve and expand the range and speed of these devices. Additionally, critical infrastructure networks, previously isolated or connected with dedicated wireline circuits, are incorporating Zigbee for wireless sensor networks, wireless LANs for maintenance functions, and cellular or Internet based backhaul to manage control centers. Yet with all the build-up surrounding wireless technology, few understand the complexities surrounding wireless protocols and security, the risks of converged network infrastructures, need for interoperability of communication systems, or mitigation measures to safely use and improve new technologies in both commercial and military environments. With no single vendor source for all the telecommunications equipment needed for wireless infrastructure upgrades, and no one entity providing end-to-end testing or independent validation, the INL's NGWTB program fulfills a niche for facilitating integrated testing of multiple technologies, across multiple wireless domains, of next generation wireless telecommunications systems. NGWTB engineers and technicians have constructed and operate domain infrastructure in the Wireless Personal Area Network (WPAN), Wireless Local Area Network (WLAN), Wireless Metropolitan Area Networks (WMAN), and Wireless Wide Area Networks (WWAN). Advantages that make the INL's NGWTB the place to conduct project and programmatic testing include: • NTIA Experimental Station authority • Geographically isolated and low-noise radio frequency (RF) test areas located on a 890 sm DOE reservation • Access to isolated high-speed LAN and FOT networks The rollout of next-generation networks will involve deploying new technologies at every level including new: handsets, frequencies, antenna arrays, cell configurations that are optimized for both data and voice, massive upgrade of cell controllers’ “land-line” phone links from low bandwidth connections to higher capacity fiber or wireless backhaul, and integration of voice switching and Internet/data network protocols (Voice-Over-IP, Web phones). These systems are expected to greatly transform our nation's communications infrastructure and the types of services it provides.

2G↗
DOE OSTI2019

Using Real-Time Electricity Prices to Leverage Electrical Energy Storage and Flexible Loads in a Smart Grid Environment Utilizing Machine Learning Techniques

With exposure to real-time market pricing structures, consumers would be incentivized to invest in electrical energy storage systems and smart predictive automation of their home energy systems. Smart home automation through optimizing HVAC (heating, ventilation, and air conditioning) temperature set points, along with distributed energy storage, could be utilized in the process of optimizing the operation of the electric grid. Using electricity prices as decision variables to leverage electrical energy storage and flexible loads can be a valuable tool to optimize the performance of the power grid and reduce electricity costs both on the supply and demand sides. Energy demand prediction is important for proper allocation and utilization of the available resources. Manipulating energy prices to leverage storage and flexible loads through these demand prediction models is a novel idea that needs to be studied. In this paper, different models for proactive prediction of the energy demand for an entire city using different machine learning techniques are presented and compared. The results of the machine learning techniques show that the proposed nonlinear autoregressive with exogenous inputs neural network model resulted in the most accurate predictions. These prediction models pave the way for the demand side to become an important asset for grid regulation by responding to variable price signals through battery energy storage and passive thermal energy storage using HVAC temperature set points.

25 ENERGY STORAGE↗
DOE OSTI2024

Source localization for neutron imaging systems using convolutional neural networks

The nuclear imaging system at the National Ignition Facility (NIF) is a crucial diagnostic for determining the geometry of inertial confinement fusion implosions. The geometry is reconstructed from a neutron aperture image via a set of reconstruction algorithms using an iterative Bayesian inference approach. An important step in these reconstruction algorithms is finding the fusion source location within the camera field-of-view. Currently, source localization is achieved via an iterative optimization algorithm. In this paper, we introduce a machine learning approach for source localization. Specifically, we train a convolutional neural network to predict source locations given a neutron aperture image. We show that this approach decreases computation time by several orders of magnitude compared to the current optimization-based source localization while achieving similar accuracy on both synthetic data and a collection of recent NIF deuterium–tritium shots.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

A Cross-Domain Optimization Framework of PMU and Communication Placement for Multidomain Resiliency and Cost Reduction

Phasor measurement units (PMUs) play a crucial role in real-time monitoring and control of power grids. They rely on a communication network to transfer measurement data to the phasor data concentrator (PDC) for further processing and analysis. In this paper, a resilient cross-domain PMU and communication link placement method for minimizing the overall installation cost of the wide-area measurement system (WAMS) is proposed. Here, the main idea is to break down the barrier between the power grid domain and the communication domain, and consider the impact of one when design the other. The PMU placement in the power grid domain takes into account the cost of communication links by generating multiple solutions with equally minimum PMU costs for communication link placement evaluation. On the other hand, the communication link placement problem reduces the cost by customizing the routing policies based on the different roles of PMUs in grid observability. The proposed WAMS design is capable of withstanding any single component failure in the power domain (PMU failure or power branch failure) or in the communication domain (communication link failure or PDC failure). Numerical study on the IEEE 57-bus system reveals that the developed cross-domain optimization framework can significantly reduce the overall installation cost of WAMS while attaining multi-domain resiliency.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Source localization for neutron imaging systems using convolutional neural networks

The nuclear imaging system at the National Ignition Facility (NIF) is a crucial diagnostic for determining the geometry of inertial confinement fusion implosions. The geometry is reconstructed from a neutron aperture image via a set of reconstruction algorithms using an iterative Bayesian inference approach. An important step in these reconstruction algorithms is finding the fusion source location within the camera field-of-view. Currently, source localization is achieved via an iterative optimization algorithm. In this paper, we introduce a machine learning approach for source localization. Specifically, we train a convolutional neural network to predict source locations given a neutron aperture image. We show that this approach decreases computation time by several orders of magnitude compared to the current optimization-based source localization while achieving similar accuracy on both synthetic data and a collection of recent NIF deuterium–tritium shots.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Automated Control of Transactive HVACs in Energy Distribution Systems

Heating, Ventilation, and Air Conditioning (HVAC) systems contribute significantly to a building’s energy consumption. In the recent years, there is an increased interest in developing transactive approaches which could enable automated and flexible scheduling of HVAC systems based on the customer demand and the electricity prices decided by the suppliers. Flexible and automated scheduling of the HVAC systems make it a prime source for participation in residential demand response or transactive energy systems. Therefore, it is of significant interest to identify an optimal strategy to control the HVAC systems. Here, reducing the energy cost while keeping the comfort level acceptable to the users, we argue that such a control strategy should consider both the energy cost and user comfort simultaneously. Accordingly, we develop the control strategy through the solution of an optimization problem that balances between the energy cost and consumer’s dissatisfaction. This optimization enables us to solve a decision-making problem through first price prediction and then choosing HVAC temperature settings throughout the day based on the predicted price, history of the price and HVAC settings, and outside temperature. More specifically, we formulate the control design as a Markov decision process (MDP) using deep neural networks and use Deep Deterministic Policy Gradients (DDPG)-based deep reinforcement learning algorithm to find the optimal control strategy for HVAC systems that balances between electricity cost and user comfort.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

A Privacy Preserving Model-Free Optimization and Control Framework for Demand Response from Residential Thermal Loads

We consider the problem of optimizing the cost of procuring electricity for a large collection of homes managed by a load serving entity, by pre-cooling or pre-heating the thermal inertial loads in the homes to avoid procuring power during periods of peak electricity pricing. We would like to accomplish this objective in a completely privacy-preserving and model-free manner, that is, without direct access to the state variables (temperatures or power consumption) or the dynamical models (thermal characteristics) of individual homes, while guaranteeing personal comfort constraints of the consumers. We propose a two-stage optimization and control framework to address this problem. In the first stage, we use a long short-term memory (LSTM) network to predict hourly electricity prices, based on historical pricing data and weather forecasts. Given the hourly price forecast and thermal models of the homes, the problem of designing an optimal power consumption trajectory that minimizes the total electricity procurement cost for the collection of thermal loads can be formulated as a large-scale integer program (with millions of variables) due to the on-off cyclical dynamics of such loads. We provide a simple heuristic relaxation to make this large-scale optimization problem model-free and computationally tractable. In the second stage, we translate the results of this optimization problem into distributed open-loop control laws that can be implemented at individual homes without measuring or estimating their state variables, while simultaneously ensuring consumer comfort constraints. We demonstrate the performance of this approach on a large-scale test case comprising of 500 homes in the Houston area and benchmark its performance against a direct model-based optimization and control solution.

Sivaranjani, S.↗
DOE OSTI2024

Neural network methods for radiation detectors and imaging

Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).

edge computing↗
DOE OSTI2022

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Resilience-based Recovery Scheduling of Transportation Network in Mixed Traffic Environment: A Deep-Ensemble-Assisted Active Learning Approach

Devising effective post-hazard recovery strategies is critical in enhancing the resilience of transportation networks (TNs). However, existing work does not consider the multiclass users’ travel behavior in network functionality quantification and the metaheuristic solution procedures often suffer from extensive computational burden due to the exploration need in large solution space and the expensive functionality quantification. Here, this study develops a bilevel decision-making framework for the resilience-based recovery scheduling of the TN in a mixed traffic environment with connected and autonomous vehicles (CAVs) and human-driven vehicles (HDVs). The lower level quantifies the TN's functionality over time considering different travel behavior of CAV and HDV users arisen from their different levels of information perception. The upper level presents a novel deep-ensemble-assisted active learning approach to balance optimization performance and computational cost. This framework can help decision makers better quantify the TN's functionality to support effective recovery scheduling of TN with different mixed traffic scenarios ranging from HDV-only to future CAV-dominant traffic. The optimization approach bears the potential to be extended to solving general large-scale network recovery scheduling problems effectively and efficiently. The proposed methodology is demonstrated using a real-world traffic network in Southern California under earthquake considering deterministic and stochastic repair durations.

42 ENGINEERING↗
DOE OSTI2017

Enhanced Grid Operation and Optimized PV Penetration Utilizing Highly Distributed Sensor Data

Sandia National Laboratories (SNL) and Enphase Energy, Inc. (Enphase) collaborated to address challenges related to the integration of Renewable Energy Systems. The goal of this research was to develop methods to cost-effectively achieve very high PV penetration scenarios (well beyond 100% of peak load at the feeder level) by leveraging distributed inverters to increase operator visibility and provide local voltage support This project focused on the integration of high penetration PV systems and other distributed resources such as energy storage, to determine how these technologies interoperate with each other and with utility distribution operations and management systems. To address the lack of coverage of feeder monitoring and communications infrastructure, SNL and Enphase leveraged highly distributed micro inverters that were installed in very large numbers in CA and Hawaii, and that have the ability to measure currant and voltage and communicate via a highly distributed network. The data was used to verify and enhance distribution system models and to optimize the control settings of distributed resources. SNL and Enphase demonstrated the effectiveness of these techniques by analyzing high PV penetration scenarios on distribution systems in California.

14 SOLAR ENERGY↗