Search NASA⌕ Search

SEARCH · Search NASA

Results for “feed forward”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Machine learning the spectral function of a hole in a quantum antiferromagnet

Understanding charge motion in a background of interacting quantum spins is a fundamental problem in quantum many-body physics. The most extensively studied model for this problem is the so-called t-t'-t''-J model, where the determination of the parameter t' in the context of cuprate superconductors is challenging. Here we present a theoretical study of the spectral functions of a mobile hole in the t-t'-t''-J model using two machine-learning techniques: K-nearest neighbor regression (KNN) and a feed-forward neural network (FFNN). We employ the self-consistent Born approximation to generate a dataset of about 1.3 x 10 5 spectral functions. Here we show that, for the forward problem, both methods allow for the accurate and efficient prediction of spectral functions, allowing, e.g., rapid searches through parameter space. Furthermore, we find that for the inverse problem (inferring Hamiltonian parameters from spectra), the FFNN can, but the KNN cannot, accurately predict the model parameters using merely the density of states. Our results suggest that it may be possible to use deep-learning methods to predict materials parameters from experimentally measured spectral functions.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Training toward significance with the decorrelated event classifier transformer neural network

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

Astronomy & Astrophysics↗
DOE OSTI2022

Charge-Based Droop Control Addressing Control Saturation for Low-Inertia Converters

With bulky dc-link capacitors/inductors, traditional voltage-source converters (VSCs) and current-source converters (CSCs) feature a large inertia to facilitate the converter control under large transients. To achieve high power density with reduced cost, low-inertia converters (LICs) featuring significantly reduced dc-link capacitors/inductors have attracted growing attention. However, without bulky dc-link energy buffer, LICs are prone to control saturation under large transients, resulting in undesired oscillation and instability. This issue cannot be managed by traditional proportional-integral based control due to the low inertia. And it will deteriorate when several LICs are connected in series. To address this challenge in LICs, a model-predictive control (MPC) with a computation-inexpensive feed-forward compensation method has been proposed to provide fast dynamic responses. But it would suffer control saturation under larger transients that degrades the control performance. In this article, a charge-based droop control (CDC) is proposed to address this remaining challenge. This paper firstly analyzes the control saturation challenge in LICs by using a tri-port soft-switching solid-state transformer as an example. Next, the operating principle of the proposed CDC are introduced. Two different implementation approaches are discussed in detail. Lastly, the proposed scheme is validated in simulation with a high-fidelity model of hardware prototype. As a result, the proposed CDC eliminated the 2 kHz oscillation and reduced the dc-link ripple and overshoot due to control saturation by 75% and 50%, respectively.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

A Parallel Alternative for Energy-Efficient Neural Network Training and Inferencing

Energy efficiency of training and inferencing with large neural network models is a critical challenge facing the future of sustainable large-scale machine learning workloads. This paper introduces an alternative strategy, called phantom parallelism, to minimize the net energy consumption of traditional tensor (model) parallelism, the most energy-inefficient component of large neural network training. The approach is presented in the context of feed-forward network architectures as a preliminary, but comprehensive, proof-of-principle study of the proposed methodology. We derive new forward and backward propagation operators for phantom parallelism, implement them as custom autograd operations within an end-to-end phantom parallel training pipeline and compare its parallel performance and energy-efficiency against those of conventional tensor parallel training pipelines. Formal analyses that predict lower bandwidth and FLOP counts are presented with supporting empirical results on up to 256 GPUs that corroborate these gains. Experiments are shown to deliver ∼50% reduction in the energy consumed to train FFNs using the proposed phantom parallel approach when compared with conventional tensor parallel methods. Additionally, the proposed approach is shown to train smaller phantom models to the same model loss on smaller GPU counts as larger tensor parallel models on larger GPU counts offering the possibility for even greater energy savings.

Seal, Sudip [ORNL] (ORCID:0000000332330656)↗
DOE OSTI2024

Artificial Neural Network-based State Estimation for Low Observable, Unbalanced Microgrids for Microgrid Building Blocks

The microgrid building blocks (MBB) were proposed as microgrid components with combined sub-components with power conversion, communication, and microgrid control capability, or a subset of such sub-components. This work addresses the microgrid controller, present in an MBB, which requires accurate state estimation to perform its tasks, including for monitoring, power flow (dispatch), fault detection, etc. In this paper, an artificial neural network (ANN)-based framework for state estimation is proposed for an MBB, especially for unbalanced and low observable microgrids. To overcome the challenge of low observability in unbalanced systems, a concept of extended adjacent matrix is introduced to reduce the required number of measurements for state estimation. Addressing the challenges, a feed forward neural network (FNN) is utilized to enhance estimation accuracy and reliability with the reduced number of measurements. The proposed state estimation is validated through extensive simulations on a microgrid, which was achieved from the modified IEEE 34-bus distribution test feeder with multiple distributed energy resources (DERs) and demonstrated superior performance in estimation accuracy and low observability.

Choi, Jongchan↗
DOE OSTI2026

Accelerating Traction Motor Optimization Design with AI Surrogate Models

The advancement of artificial intelligence systems enables the use of data-driven physics-based surrogate models to explore design spaces rapidly and deeply for engineering projects. This work presents a surrogate model workflow that accelerates electric traction motor design optimization by replacing finite element analysis (FEA) with an artificial neural network (ANN) and using this model in a genetic algorithm for design optimization. A baseline interior permanent-magnet motor is parameterized and sampled to generate FEA-labeled training data, after which a feed-forward ANN predicts key outputs (e.g., loss components and weight). The validated surrogate enables genetic-algorithm optimization and deep search over the design space without new FEA runs, producing Pareto-optimal trade-offs between weight and losses and set of optimized designs for rapid downselection of manufacturable motor designs.

Ribeiro, Pedro [ORNL] (ORCID:0009000921026641)↗
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2022

A Tri-Port Current-Source Soft-Switching Medium-Voltage String Inverter for Large-Scale Solar-Plus-Storage Farms

This article presents a tri-port current-source soft-switching medium-voltage string inverter (TMVSI) to reduce the Levelized cost of energy (LCOE) of large-scale solar-plus-storage (SPS) farms. Throughout this work, the topology, operating principle, circuit simulation, control, and hardware design of the TMVSI are introduced. In addition, three key challenges compromising the performance of the TMVSI are addressed in this article. First, a new feed-forward compensation for model predictive control of the TMVSI is proposed to compensate for sampling and computational delay and high dc-link ripple with low computational cost and high scalability. Second, the use of laminated permanent magnets is proposed to reduce the losses of the MV medium-frequency transformer (MFT) in the TMVSI while increasing its saturation current. Finally, an improved U-shape winding pattern is proposed to decrease the leakage inductance of the MV MFT and reduce the voltage stress across semiconductor switches without adding cost or complexity. Here, the effectiveness of the TMVSI is validated by experiments at up to 20kW/500V in different test cases with custom-built prototypes. The contributions of this work make the TMVSI a viable solution to SPS farms and unleash its potential for LCOE reduction.

14 SOLAR ENERGY↗
DOE OSTI2021

Examining the Economic Optimality of Automatic Generation Control

The automatic generation control (AGC) system is temporally situated between economic dispatch and synchronous generator dynamics, and its primary role is to regulate frequency within and tie-line flows between control areas. Given appropriate choice of participation factors (feed-forward controller gains that govern the disaggregation of the area-level power requirement to individual generators), the AGC can be engineered to nudge system dynamics toward a steady-state operating point corresponding to economic optimality. This paper establishes necessary and sufficient conditions under which a widely accepted choice of participation factors guarantees the alignment of steady-state synchronous generator outputs with a global minimum of a prototypical economic dispatch problem. In so doing, it resolves several ambiguities and formalizes technical assumptions governing the role of the standard AGC architecture in the context of economic dispatch and steady-state operation. Numerical case studies tailored to a modified version of the New England 39-bus 10-machine test system validate the theoretical results.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Practical Challenges in Real-Time Demand Response

We report on a real-time demand response experiment with 100 controllable devices. The experiment reveals several key challenges in the deployment of a real-time demand response program, including time delays, uncertainties, characterization errors, multiple timescales, and nonlinearity, which have been largely ignored in previous studies. To resolve these practical issues, we develop and implement a two-level multi-loop control structure integrating feed-forward proportional-integral controllers and optimization solvers in closed loops, which eliminates steady-state errors and improves the dynamical performance of the overall building response. Furthermore, the proposed methods are validated by Hardware-in-the-Loop (HiL) tests.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

A Transported Livengood–Wu Integral Model for Knock Prediction in Computational Fluid Dynamics Simulation

This work describes the development of a transported Livengood–Wu (L–W) integral model for computational fluid dynamics (CFD) simulation to predict autoignition and engine knock tendency. The currently employed L–W integral model considers both single-stage and two-stage ignition processes, thus can be generally applied to different fuels such as paraffin, olefin, aromatics, and alcohol. The model implementation is first validated in simulations of homogeneous charge compression ignition (HCCI) combustion for three different fuels, showing good accuracy in prediction of autoignition timing for fuels with either single-stage or two-stage ignition characteristics. Then, the L–W integral model is coupled with G-equation model to indicate end-gas autoignition and knock tendency in CFD simulations of a direct-injection spark-ignition engine. This modeling approach is about 10 times more efficient than the ones that based on detailed chemistry calculation and pressure oscillation analysis. Two fuels with same Research Octane Number (RON) but different octane sensitivity are studied, namely, Co-Optima alkylate and Co-Optima E30. Feed-forward neural network model in conjunction with multivariable minimization technique is used to generate fuel surrogates with targets of matched RON, octane sensitivity, and ethanol content. The CFD model is validated against experimental data in terms of pressure traces and heat release rate for both fuels under a wide range of operating conditions. The knock tendency—indicated by the fuel energy contained in the autoignited region—of the two fuels at different load conditions correlates well with the experimental results and the fuel octane sensitivity, implying the current knock modeling approach can capture the octane sensitivity effect and can be applied to further investigation on composition of octane sensitivity.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2020

A transported Livengood-Wu integral model for knock prediction in CFD simulation

This work describes the development of a transported Livengood-Wu (L-W) integral model for computational fluid dynamics (CFD) simulation to predict auto-ignition and engine knock tendency. The currently employed L-W integral model considers both single-stage and two-stage ignition processes, thus can be generally applied to different fuels such as paraffin, olefin, aromatics and alcohol. The model implementation is first validated in simulations of homogeneous charge compression ignition combustion for three different fuels, showing good accuracy in prediction of auto-ignition timing for fuels with either single-stage or two-stage ignition characteristics. Then, the L-W integral model is coupled with G-equation model to indicate end-gas auto-ignition and knock tendency in CFD simulations of a direct injection spark ignition engine. This modeling approach is about 10 times more efficient than the ones that based on detailed chemistry calculation and pressure oscillation analysis. Two fuels with same Research Octane Number (RON) but different octane sensitivity are studied, namely Co-Optima Alkylate and Co-Optima E30. Feed-forward neural network model in conjunction with multi-variable minimization technique is used to generate fuel surrogates with targets of matched RON, octane sensitivity and ethanol content. The CFD model is validated against experimental data in terms of pressure traces and heat release rate for both fuels under a wide range of operating conditions. The knock tendency indicated by the fuel energy contained in the auto-ignited region of the two fuels at different load conditions correlates well with the experimental results and the fuel octane sensitivity, implying the current knock modeling approach can capture the octane sensitivity effect and can be applied to further investigation on composition of octane sensitivity.

Yue, Zongyu↗
DOE OSTI2024

Transcriptional response of Methanosarcina acetivorans to repression of the energy-conserving methanophenazine: CoM-CoB heterodisulfide reductase enzyme HdrED

ABSTRACT Methane-producing archaea are key organisms in the anaerobic carbon cycle. These organisms, also called methanogens, grow by converting substrate to methane gas in a process called methanogenesis. Previous research showed that the reduction of the terminal electron acceptor is the rate-limiting step in methanogenesis by Methanosarcina acetivorans . In order to gain insight into how the cells sense and respond to the availability of the terminal electron acceptor, we designed an experiment to deplete cells of the essential terminal oxidase enzyme, HdrED. We found that the depletion of HdrED in vivo results in a higher abundance of transcripts for methyltransferases ( mtaC2, mtaB3, mtaC3 ), coenzyme B biosynthesis, C1 metabolism, and pyrimidine compounds. In most cases, these changes were distinct from transcript abundance changes observed during the transition from exponential growth to stationary phase cultures. These data implicate the methylotrophic methanogenesis regulator MsrC (MA4383) in CoM-S-S-CoB heterodisulfide sensing and indicate cells have a specific mechanism to sense intracellular ratio of CoM-S-S-CoB, coenzyme M, and coenzyme B thiols and further suggest transcripts encoding translation and methanogenesis functions are controlled by feed-forward regulation depending on substrate availability. IMPORTANCE Methanosarcina is an emerging model archaeon and synthetic biology platform for the production of renewable energy and sustainable chemicals to reduce dependence on petroleum. Research into metabolic networks and gene regulation in this organism and other methanogens will inform genome-scale metabolic modeling and microbial function prediction in uncultured or non-model anaerobes and archaea. This study suggests methanogens use unknown mechanisms to efficiently couple methanogenesis to gene regulation via CoM-S-S-CoB and ATP availability.

Buan, Nicole R. (ORCID:000000027560973X)↗
DOE OSTI2020

3D-ReG: A 3D ReRAM-based Heterogeneous Architecture for Training Deep Neural Networks

Deep neural network (DNN) models are being expanded to a broader range of applications. The computational capability of traditional hardware platforms cannot accommodate the growth of model complexity. Among recent technologies to accelerate DNN, resistive memory (ReRAM)-based processing-in-memory (PIM) emerged as a promising solution for DNN inference due to its high efficiency for matrix-based computation. We face two major technical challenges in extending the use of ReRAM-based accelerators for training: (1) full-precision data is essential in back-propagation; (2) the need to support both feed-forward and back-propagation aggravates the data-movement burden. We propose a heterogeneous architecture named as 3D-ReG, which leverages full-precision GPU to ensure training accuracy and low-overhead 3D integration to provide low-cost data movements. Moreover, we introduce conservative and aggressive task-mapping schemes, which partition the computation phases in different ways to balance execution efficiency and training accuracy. We evaluate 3D-ReG implemented with two 3D integration technologies, through-silicon vias (TSVs) and monolithic inter-tier vias (MIVs), and compare them with GPU-only and PIM-only counterparts. Various GPU-only platforms using two main-memory technologies (DRAM, ReRAM) and three interconnect technologies (2D, TSV, MIV) are evaluated as well. Experimental results show that 3D-ReG can achieve on average 5.64× training speedup and 3.56× higher energy efficiency compared with the GPU with DRAM as main memory, at the cost of 0.05%–3.39% accuracy drop. We define a new metric, gain-loss ratio (GLR), which quantitatively evaluates the capability of a DNN training hardware in terms of the model accuracy and hardware efficiency. The results of our comparison show that the aggressive task-mapping scheme on MIV-based 3D-ReG outperforms the other methods.

Computer Science↗
DOE OSTI2020

QCOR; A Language Extension Specification for the Heterogeneous Quantum-Classical Model of Computation

Quantum computing (QC) is an emerging computational paradigm that leverages the laws of quantum mechanics to perform elementary logic operations. Existing programming models for QC were designed with fault-tolerant hardware in mind, envisioning stand-alone applications. However, the susceptibility of near-term quantum computers to noise limits their stand-alone utility. To better leverage limited computational strengths of noisy quantum devices, hybrid algorithms have been suggested whereby quantum computers are used in tandem with their classical counterparts in a heterogeneous fashion. This modus operandi calls out for a programming model and a high-level programming language that natively and seamlessly supports heterogeneous quantum-classical hardware architectures in a single-source-code paradigm. Motivated by the lack of such a model, we introduce a language extension specification, called QCOR, which enables single-source quantum-classical programming. Programs written using the QCOR library–based language extensions can be compiled to produce functional hybrid binary executables. After defining QCOR’s programming model, memory model, and execution model, we discuss how QCOR enables variational, iterative, and feed-forward QC. Additionally, QCOR approaches quantum-classical computation in a hardware-agnostic heterogeneous fashion and strives to build on best practices of high-performance computing. The high level of abstraction in the language extension is intended to accelerate the adoption of QC by researchers familiar with classical high-performance computing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Extending C++ for Heterogeneous Quantum-Classical Computing

In this report we present qcor - a language extension to C++ and compiler implementation that enables heterogeneous quantum-classical programming, compilation, and execution in a single-source context. Our work provides a first-of-its-kind C++ compiler enabling high-level quantum kernel (function) expression in a quantum-language agnostic manner, as well as a hardware-agnostic, retargetable compiler workflow targeting a number of physical and virtual quantum computing backends. qcor leverages novel Clang plugin interfaces and builds upon the XACC system-level quantum programming framework to provide a state-of-the-art integration mechanism for quantum-classical compilation that leverages the best from the community at-large. qcor translates quantum kernels ultimately to the XACC intermediate representation, and provides user-extensible hooks for quantum compilation routines like circuit optimization, analysis, and placement. This work details the overall architecture and compiler workflow for qcor, and provides a number of illuminating programming examples demonstrating its utility for near-term variational tasks, quantum algorithm expression, and feed-forward error correction schemes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

ML–Enabled FPGA Framework for Fast Quantum State Discrimination in Mid-Circuit Measurement Regimes

Accurate and low-latency quantum state discrimination is essential for protocols involving mid-circuit measurement (MCM) and conditional feed-forward. In superconducting quantum systems, conventional readout pipelines transfer measurement data to host processors for post-processing, introducing millisecond-scale delays that far exceed qubit coherence times. To overcome this bottleneck, we present an in-situ machine learning (ML) inference engine implemented on an FPGA for real-time quantum state discrimination. Our design performs inference directly on digitized readout signals with 40 ns latency, supports both qubit and qutrit readout, and enables conditional operations without host-side intervention. This capability is critical for MCM and for feedback-driven protocols such as quantum error correction. We validate the system on superconducting transmon hardware, demonstrating robust discrimination fidelity across multiple qubit and qutrit channels. We further demonstrate conditional qutrit logic driven by FPGA-resident classification, highlighting the potential of low-latency ML-on-FPGA control for NISQ applications and scalable fault-tolerant quantum computing.

Vora, Neel [Lawrence Berkeley National Laboratory ↗
DOE OSTI2021

Netfabb to IFF XML converter

This software converts XML files created by the Netfabb software to the XML format used by the Intelligent Feed Forward (IFF) tools developed at LLNL.

Lapointe, Simon↗