Search NASA⌕ Search

SEARCH · Search NASA

Results for “Value function”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

A publicly available PyTorch-$\mathrm{ABAQUS}$ $\mathrm{UMAT}$ deep-learning framework for level-set plasticity

Here this paper introduces a publicly available PyTorch-ABAQUS deep-learning framework of a family of plasticity models where the yield surface is implicitly represented by a scalar-valued function. In particular, our focus is to introduce a practical framework that can be deployed for engineering analysis that employs a user-defined material subroutine (UMAT/VUMAT) for ABAQUS, which is written in FORTRAN. To accomplish this task while leveraging the back-propagation learning algorithm to speed up the neural-network training, we introduce an interface code where the weights and biases of the trained neural networks obtained via the PyTorch library can be automatically converted into a generic FORTRAN code that can be a part of the UMAT/VUMAT algorithm. To enable third-party validation, we purposely make all the data sets, source code used to train the neural-network-based constitutive models, and the trained models available in a public repository. Furthermore, the practicality of the workflow is then further tested on a dataset for anisotropic yield function to showcase the extensibility of the proposed framework. A number of representative numerical experiments are used to examine the accuracy, robustness and reproducibility of the results generated by the neural network models.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Compound Meta-Optics for Complete and Loss-Less Field Control

Optical metasurfaces offer a compact platform for manipulation of the amplitude, phase, and polarization state of light. Independent control over these properties, however, is hindered by the symmetric transmission matrix associated with single-layer metasurfaces. Here, we utilize multilayer birefringent meta-optics to realize high-efficiency, independent control over the amplitude, phase, and polarization state of light. In this work, high-efficiency control is enabled by redistributing the wavefront between cascaded metasurfaces, while end-to-end inverse design is used to realize independent complex-valued functions for orthogonal polarization states. Based on this platform, we demonstrate spatial mode division multiplexing, optical mode conversion, and universal vectorial holograms, all with diffraction efficiencies over 80%. This meta-optic platform expands the design space of flat optics and could lead to advances in optical communications, quantum entanglement, and information encryption.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

2D perovskite-based high spatial resolution X-ray detectors

Abstract X-ray radiography is the most widely used imaging technique with applications encompassing medical and industrial imaging, homeland security, and materials research. Although a significant amount of research and development has gone into improving the spatial resolution of the current state-of-the-art indirect X-ray detectors, it is still limited by the detector thickness and microcolumnar structure quality. This paper demonstrates high spatial resolution X-ray imaging with solution-processable two-dimensional hybrid perovskite single-crystal scintillators grown inside microcapillary channels as small as 20 µm. These highly scalable non-hygroscopic detectors demonstrate excellent spatial resolution similar to the direct X-ray detectors. X-ray imaging results of a camera constructed using this scintillator show Modulation Transfer Function values significantly better than the current state-of-the-art X-ray detectors. These structured detectors open up a new era of low-cost large-area ultrahigh spatial resolution high frame rate X-ray imaging with numerous applications.

2D perovskite↗
DOE OSTI2023

Single-stage stellarator optimization: combining coils with fixed boundary equilibria

We introduce a novel approach for the simultaneous optimization of plasma physics and coil engineering objectives using fixed-boundary equilibria that is computationally efficient and applicable to a broad range of vacuum and finite plasma pressure scenarios. Our approach treats the plasma boundary and coil shapes as independently optimized variables, penalizing the mismatch between the two using a quadratic flux term in the objective function. Four use cases are presented to demonstrate the effectiveness of the approach, including simple and complex stellarator geometries. As shown here, this method outperforms previous two-stage approaches, achieving smaller plasma objective function values when coils are taken into account.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Amortized simulation-based frequentist inference for tractable and intractable likelihoods

Abstract High-fidelity simulators that connect theoretical models with observations are indispensable tools in many sciences. If the likelihood is known, inference can proceed using standard techniques. However, when the likelihood is intractable or unknown, a simulator makes it possible to infer the parameters of a theoretical model directly from real and simulated observations when coupled with machine learning. We introduce an extension of the recently proposed likelihood-free frequentist inference ( LF2I ) approach that makes it possible to construct confidence sets with the p -value function and to use the same function to check the coverage explicitly at any given parameter point. Like LF2I , this extension yields provably valid confidence sets in parameter inference problems for which a high-fidelity simulator is available. The utility of our algorithm is illustrated by applying it to three pedagogically interesting examples: the first is from cosmology, the second from high-energy physics and astronomy, both with tractable likelihoods, while the third, with an intractable likelihood, is from epidemiology 3 3 Code to reproduce all of our results is available on https://github.com/AliAlkadhim/ALFFI . .

Computer Science↗
DOE OSTI2023

Convex Q-Learning in Continuous Time with Application to Dispatch of Distributed Energy Resources

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with a finite-horizon optimal control objective. The main contributions are (i) The new Q-ODE: a model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) A formulation of Convex Q-learning that avoids approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is necessary in the presence of measurement noise. (iii) Convex Q-learning with linear function approximation is a convex program. It is shown that the constraint region is bounded, subject to an exploration condition on the training input. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited.

Lu, Fan↗
DOE OSTI2022

Post-Disaster Microgrid Formation for Enhanced Distribution System Resilience

This paper proposes a deep reinforcement learning (DRL) based approach for post-disaster critical load restoration in active distribution systems to form microgrids through network reconfiguration to minimize critical load curtailments. Distribution networks are represented as graph networks, and optimal network configurations with microgrids are obtained by searching for the optimal spanning forest. The constraints to the research question being explored are the radial topology and power balance. Unlike existing analytical and population-based approaches, which necessitate the repetition of entire analyses and computation for each outage scenario to find the optimal spanning forest, the proposed approach, once properly trained, can quickly determine the optimal, or near-optimal, spanning forest even when outage scenarios change. When multiple lines fail in the system, the proposed approach forms microgrids with distributed energy resources in active distribution systems to reduce critical load curtailment. The proposed DRL-based model learns the action-value function using the REINFORCE algorithm, which is a model-free reinforcement learning technique based on stochastic policy gradients. A case study was conducted on a 33-node distribution test system, demonstrating the effectiveness of the proposed approach for post-disaster critical load restoration.

active distribution systems↗
DOE OSTI2021

Distributional Deep Reinforcement Learning-Based Emergency Frequency Control

Emergency frequency control is one of the most critical approaches to maintain power system stability after major disturbances. With the increasing number of grid-connected renewable energy sources, existing model-based methods of frequency control are facing up with challenges of computational speed and scalability for large-scale systems. In this paper, the emergency frequency control problem is formulated as a Markov Decision Process (MDP) and solved through a novel Distributional Deep Reinforcement Learning (DDRL) method, namely the distributional soft actor critic (DSAC) method. Compared with other RL methods that only estimate the mean value, the proposed DSAC model estimates the distribution of value function over returns. This advancement can lead to more insights and knowledge for the agent, with the benefit of a much faster and more stable learning process, and the improved frequency control performance. Here, the simulation results on IEEE 39-bus and IEEE 118-bus systems demonstrate the effectiveness and robustness of proposed models, as well as the advantage compared to other state-of-the-art DRL algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

FIRE: A Failure-Adaptive RL Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated between edge servers due to user mobility. Reinforcement Learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like AR/VR and real- time obstacle detection. These rare failures, being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. We introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose FIRE-ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove FIRE-ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (FIRE-ImDQL) and actor critic (FIRE-ImACRE) versions of our algorithm to enhance scalability. Here, we extend our framework to accommodate users with varying risk tolerances of rare failure events. Through trace-driven experiments, we show that FIRE reduces edge computing costs compared to vanilla RL and the greedy baseline in the event of failures.

Edge computing↗
DOE OSTI2021

Room-temperature single-photon emitters in silicon nitride

Single-photon emitters are essential in enabling several emerging applications in quantum information technology, quantum sensing, and quantum communication. Scalable photonic platforms capable of hosting intrinsic or embedded sources of single-photon emission are of particular interest for the realization of integrated quantum photonic circuits. Here, we report on the observation of room-temperature single-photon emitters in silicon nitride (SiN) films grown on silicon dioxide substrates. Photophysical analysis reveals bright (>10 5 counts/s), stable, linearly polarized, and pure quantum emitters in SiN films with a second-order autocorrelation function value at zero time delay g (2) (0) below 0.2 at room temperature. We suggest that the emission originates from a specific defect center in SiN because of the narrow wavelength distribution of the observed luminescence peak. Single-photon emitters in SiN have the potential to enable direct, scalable, and low-loss integration of quantum light sources with a well-established photonic on-chip platform.

42 ENGINEERING↗
DOE OSTI2022

LBC (Learning Building Control)

LBC encompasses the source code and data to reproduce and extend results for a manuscript that compares demand responsive control schemes for multi-zone buildings. It includes examples of model predictive control (MPC), value function approximation via CVXPYLAYERS, and differentiable predictive control (DPC). The goal of the study is to evaluate state-of-the-art controllers and establish the efficacy (if any) of learning-based approaches that leverage deep neural networks in one way or another.

Zhang, Xiangyu↗
DOE OSTI2022

maestro

MÆSTRO stands for Multi-fidelity Adaptive Ensemble Stochastic Trust Region Optimization and it is a plug n play derivate fee stochastic optimization solver. The problem being considered in MÆSTRO involves fitting Monte Carlo simulations that describe complex phenomena to experiments. This is done by finding parameters of the resource intensive and noisy simulation that yield the least squares objective function value to the noisy experimental data. This problem is solved using a stochastic trust-region optimization algorithm where in each iteration, a local approximation of the simulation signal and of the simulation noise is constructed over data, which is obtained by running the simulation at strategically placed design points within the trust-region around the current iterate. Then the simulation components of the objective are replaced by their approximations and this analytical and closed-form optimization problem is solved to find the next iterate within the trust-region. Then the trust region is moved and the iterations continue until a satisfactory convergence criteria is met.

KRISHNAMOORTHY, MOHAN↗
DOE OSTI2024

Spiking Markov Reward Process v.0.1

SAND2024-11150O The Spiking Markov Reward Process software is a spiking neural network that streams binary arithmetic and computes the state value function of a Markov reward process. The software will be released to the SpiNNcloud group for development of neuromorphic acceleration. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Wang, Felix↗
DOE OSTI2024

Can Error Mitigation Improve Trainability of Noisy Variational Quantum Algorithms?

Variational Quantum Algorithms (VQAs) are often viewed as the best hope for near-term quantum advantage. However, recent studies have shown that noise can severely limit the trainability of VQAs, e.g., by exponentially flattening the cost landscape and suppressing the magnitudes of cost gradients. Error Mitigation (EM) shows promise in reducing the impact of noise on near-term devices. Thus, it is natural to ask whether EM can improve the trainability of VQAs. In this work, we first show that, for a broad class of EM strategies, exponential cost concentration cannot be resolved without committing exponential resources elsewhere. This class of strategies includes as special cases Zero Noise Extrapolation, Virtual Distillation, Probabilistic Error Cancellation, and Clifford Data Regression. Second, we perform analytical and numerical analysis of these EM protocols, and we find that some of them (e.g., Virtual Distillation) can make it harder to resolve cost function values compared to running no EM at all. As a positive result, we do find numerical evidence that Clifford Data Regression (CDR) can aid the training process in certain settings where cost concentration is not too severe. Our results show that care should be taken in applying EM protocols as they can either worsen or not improve trainability. On the other hand, our positive results for CDR highlight the possibility of engineering error mitigation methods to improve trainability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

On the practical usefulness of the Hardware Efficient Ansatz

Variational Quantum Algorithms (VQAs) and Quantum Machine Learning (QML) models train a parametrized quantum circuit to solve a given learning task. The success of these algorithms greatly hinges on appropriately choosing an ansatz for the quantum circuit. Perhaps one of the most famous ansatzes is the one-dimensional layered Hardware Efficient Ansatz (HEA), which seeks to minimize the effect of hardware noise by using native gates and connectives. The use of this HEA has generated a certain ambivalence arising from the fact that while it suffers from barren plateaus at long depths, it can also avoid them at shallow ones. In this work, we attempt to determine whether one should, or should not, use a HEA. We rigorously identify scenarios where shallow HEAs should likely be avoided (e.g., VQA or QML tasks with data satisfying a volume law of entanglement). More importantly, we identify a Goldilocks scenario where shallow HEAs could achieve a quantum speedup: QML tasks with data satisfying an area law of entanglement. We provide examples for such scenario (such as Gaussian diagonal ensemble random Hamiltonian discrimination), and we show that in these cases a shallow HEA is always trainable and that there exists an anti-concentration of loss function values. Our work highlights the crucial role that input states play in the trainability of a parametrized quantum circuit, a phenomenon that is verified in our numerics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

ARPA-E Grid Optimization (GO) Competition Challenge 1

The ARPA-E Grid Optimization (GO) Competition Challenge 1, from 2018 to 2019, focused on the basic Security Constrained AC Optimal Power Flow problem (SCOPF) for a single time period. The Challenge utilized sets of unique datasets generated by the ARPA-E GRID DATA program. Each dataset consisted of a collection of power system network models of different sizes with associated operating scenarios (snapshots in time defining instantaneous power demand, renewable generation, generator and line availability, etc.). The datasets were of two types: Real-Time, which included starting-point information, and Online, which did not. Week-Ahead data is also provided for some cases but was not used in the Competition. Although most datasets were synthetic and generated by GRIDDATA, a few came from industry and were only used in the Final Event. All synthetic Input Data and Team Results for the GO Competition Challenge 1 for the Sandbox, Trial Events 1 to 3, and the Final Event along with problem, format, scoring and rules descriptions are available here. Data for industry scenarios will not be made public. Challenge 1, a minimization problem, required two computational steps. Solver 1 or Code 1 solved the base SCOPF problem under a strict wall clock time limit, as would be the case in industry, and reported the base case operating point as output, which was used to compute the Objective Function value that was used as the scenario score. The feasibility of the solution was provided by the Solver 2 or Code 2, which solves the power flow problem for all contingencies based on the results from Solver 1. This is not normally done in industry, so the time limits were relaxed. In fact, there were no time limits for Trial Event 1. This proved to be a mistake, with some codes running for more than 90 hours, and a time limit of 2 seconds per contingency was imposed for all other events. Entrants were free to use their own Solver 2 or use an open-source version provided by the Competition. Containers, such as Docker, were considered to improve the portability of codes, but none that could reliably support a multi-node parallel computing environment, e.g., MPI, could be found. For more information on the competition and challenge see the "GO Competition Challenge 1 Information" and "GO Competition Challenge 1 Additional Information" resources below.

ACOPF↗
DOE OSTI2019

Quasi-Stochastic Approximation and Off-Policy Reinforcement Learning: Preprint

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning and often an efficient approach to solving (or approximating the solution to) complex optimal control problems. In many cases, however, practitioners are unable to apply these techniques because of an inherent high variance. This paper aims to provide a general foundation for 'quasi-stochastic approximation,' in which all of the processes under consideration are deterministic, much like quasi-Monte Carlo for variance reduction in simulation. The variance reduction can be substantial, subject to tuning of pertinent parameters in the algorithm. This paper introduces a new coupling argument to establish the optimal rate of convergence provided the gain is sufficiently large. These results are established for linear models and tested also in nonideal settings. A major application of these general results is a new class of reinforcement learning algorithms for deterministic state space models. In this setting, the main contribution is a class of algorithms for approximating the value function for a given policy, using a different policy designed to introduce exploration.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Experimental Validation of Approximate Dynamic Programming Based Optimization and Convergence on Microgrid Applications

Stochastic optimization can better address uncertainties in power system problems. However, when state space and action space become large, many existing approaches become computationally expensive and even infeasible. Approximate dynamic programming (ADP) attracts researchers’ attention as a powerful tool for solving power system optimization problems with reduced computational cost. In this paper, in light of the existing literature, we investigate how the ADP approach with post-decision value function approximation converges to the nearly optimal solution with improved computational speed and experimentally validate the performance of the approach for a microgrid energy optimization problem. The approximation error versus the number of iteration is studied for convergence analysis of the post-decision ADP. A flowchart is provided to illustrate the proposed ADP algorithm for a microgrid energy optimization problem. The performance of ADP and dynamic programming (DP) is compared in terms of optimization error and computational time. It has found that the post-decision ADP approach can achieve competitive optimality with improved computational speed compared to the traditional DP.

Das, Avijit↗