Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Learning”

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces

Historically, surface complexation model (SCM) constants and distribution coefficients (K d ) have been employed to quantify mineral-based retardation effects controlling the fate of metals in subsurface geologic systems. Our recent SCM development workflow, based on the Lawrence Livermore National Laboratory Surface Complexation/Ion Exchange (L-SCIE) database, illustrated a community FAIR data approach to SCM development by predicting uranium(VI)-quartz adsorption for a large number of literature-mined data. Here, we present an alternative hybrid machine learning (ML) approach that shows promise in achieving equivalent high-quality predictions compared to traditional surface complexation models. At its core, the hybrid random forest (RF) ML approach is motivated by the proliferation of incongruent SCMs in the literature that limit their applicability in reactive transport models. Our hybrid ML approach implements PHREEQC-based aqueous speciation calculations; values from these simulations are automatically used as input features for a random forest (RF) algorithm to quantify adsorption and avoid SCM modeling constraints entirely. Named the LLNL Speciation Updated Random Forest (L-SURF) model, this hybrid approach is shown to have applicability to U(VI) sorption cases driven by both ion-exchange and surface complexation, as is shown for quartz and montmorillonite cases. The approach can be applied to reactive transport modeling and may provide an alternative to the costly development of self-consistent SCM reaction databases.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
NASA NTRS2022

Scheduling For Urban Air Mobility Using Safe Learning

This work considers the scheduling problem for Urban Air Mobility (UAM) vehicles travelling between origin-destination pairs with both hard and soft trip deadlines. Each route is described by a discrete probability distribution over trip completion times (or delay) and over interarrival times of requests (or demand) for the route along with a fixed hard or soft deadline. Soft deadlines carry a cost that is incurred when the deadline is missed. An online, safe scheduler is developed that ensures that hard deadlines are never missed and that average cost of missing soft deadlines is minimized. The system is modelled as a Markov Decision Process (MDP) and safe model based learning is used to find the probabilistic distributions over route delays and demand. Monte Carlo Tree Search (MCTS) Earliest Deadline First (EDF) is used to safely explore the learned models in an online fashion and develop a near-optimal non-preemptive scheduling policy. These results are compared with Value Iteration (VI) and MCTS (Random) scheduling solutions.

Urban Air Mobility↗
NASA NTRSDate not supplied

Scheduling for Urban Air Mobility using Safe Learning

This work considers the scheduling problem for Urban Air Mobility (UAM) vehicles travelling between origin-destination pairs with both hard and soft trip deadlines. Each route is described by a discrete probability distribution over trip completion times (or delay) and over interarrival times of requests (or demand) for the route along with a fixed hard or soft deadline. Soft deadlines carry a cost that is incurred when the deadline is missed. An online, safe scheduler is developed that ensures that hard deadlines are never missed and that average cost of missing soft deadlines is minimized. The system is modelled as a Markov Decision Process (MDP) and safe model based learning is used to find the probabilistic distributions over route delays and demand. Monte Carlo Tree Search (MCTS) Earliest Deadline First (EDF) is used to safely explore the learned models in an online fashion and develop a near-optimal non-preemptive scheduling policy. These results are compared with Value Iteration (VI) and MCTS (Random) scheduling solutions.

Urban Air Mobility↗
DOE OSTI2018

Alternative Database Designs for the Distribution Common Information Model

The distribution Common Information Model (CIM) offers a means for interoperable distribution system applications. Adoption has been slow in part because of the steep learning curve, and the mismatch between CIM’s object-oriented schema and widely-used relational database schemas. We evaluated alternative database technologies, and tested a triple-store database with SPARQL queries on a set of IEEE distribution test feeders. These alternative queries were much simpler to design and use, so they should help lower one of the important barriers to CIM adoption. An open-source platform has been provided for other developers to work with CIM in this way. One use case is to more rapidly develop interoperable ADMS and DERMS applications. Another use case is to convert feeder models between commercial CIM-compliant products and research software like GridLAB-D and OpenDSS.

lenses, computational modeling, relational databas↗
DOE OSTI2019

Deep learning as a tool for neural data analysis: Speech classification and cross-frequency coupling in human sensorimotor cortex

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a simple, linear transformations between neural features and features of the sensory stimuli or motor task. While successful in some early sensory processing areas, linear mappings are unlikely to be ideal tools for elucidating nonlinear, hierarchical representations of higher-order brain areas during complex tasks, such as the production of speech by humans. Here, we apply deep networks to predict produced speech syllables from a dataset of high gamma cortical surface electric potentials recorded from human sensorimotor cortex. We find that deep networks had higher decoding prediction accuracy compared to baseline models. Having established that deep networks extract more task relevant information from neural data sets relative to linear models (i.e., higher predictive accuracy), we next sought to demonstrate their utility as a data analysis tool for neuroscience. We first show that deep network's confusions revealed hierarchical latent structure in the neural data, which recapitulated the underlying articulatory nature of speech motor control. We next broadened the frequency features beyond high-gamma and identified a novel high-gamma-to-beta coupling during speech production. Finally, we used deep networks to compare task-relevant information in different neural frequency bands, and found that the high-gamma band contains the vast majority of information relevant for the speech prediction task, with little-to-no additional contribution from lower-frequency amplitudes. Together, these results demonstrate the utility of deep networks as a data analysis tool for basic and applied neuroscience.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

An adaptive Hessian approximated stochastic gradient MCMC method

Bayesian approaches have been successfully integrated into training deep neural networks. One popular family is stochastic gradient Markov chain Monte Carlo methods (SG-MCMC), which have gained increasing interest due to their ability to handle large datasets and the potential to avoid overfitting. Although standard SG-MCMC methods have shown great performance in a variety of problems, they may be inefficient when the random variables in the target posterior densities have scale differences or are highly correlated. Here, we present an adaptive Hessian approximated stochastic gradient MCMC method to incorporate local geometric information while sampling from the posterior. The idea is to apply stochastic approximation (SA) to sequentially update a preconditioning matrix at each iteration. The preconditioner possesses second-order information and can guide the random walk of a sampler efficiently. Instead of computing and saving the full Hessian of the log posterior, we use limited memory of the samples and their stochastic gradients to approximate the inverse Hessian-vector multiplication in the updating formula. Moreover, by smoothly optimizing the preconditioning matrix via SA, our proposed algorithm can asymptotically converge to the target distribution with a controllable bias under mild conditions. To reduce the training and testing computational burden, we adopt a magnitude-based weight pruning method to enforce the sparsity of the network. Our method is user-friendly and demonstrates better learning results compared to standard SG-MCMC updating rules. The approximation of inverse Hessian alleviates storage and computational complexities for large dimensional models. Numerical experiments are performed on several problems, including sampling from 2D correlated distribution, synthetic regression problems, and learning the numerical solutions of heterogeneous elliptic PDE. The numerical results demonstrate great improvement in both the convergence rate and accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems

This paper presents a 1-D convolutional and graph convolutional networks for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spatial-temporal correlations from the voltage measurements in microgrids. The fault detection scheme includes fault event detection, fault type and phase classification, and fault location. There are five neural network model training to handle these tasks. Transfer learning and fine-tuning are applied to reduce training efforts. The combined 1-D convolutional and graph convolutional networks (1D-CGCN) is compared with the traditional ANN structure on the Potsdam 13-bus microgrid dataset. The accuracy of 99.5%, 98.4%, 99.2%, and 95.5% are achieved in fault event detection, fault type classification, fault phase identification, and fault location respectively. The detailed confusion matrices of fault type and fault phase classification are provided for validation.

deep neural network↗
DOE OSTI2022

Time Sequence Machine Learning-Based Data Intrusion Detection for Smart Voltage Source Converter-Enabled Power Grid

Smart inverters of distributed energy resources can enable cloud computing, condition monitoring, result visualization, remote control, and peer-to-peer energy trading in advanced power systems. However, the advent of data injection attacks in the communication architecture can alter measurement characteristics of power grids and have devastating consequences. In this article, we propose a time sequence machine learning-based anomaly detection methodology for detecting cyber intrusion into control signal setpoints and dc voltage signal measurement bias of the voltage source converter (VSC) in wind generators. We first investigated the effects of four types of denial of service, tampering signal, and stealthy-type data intrusion attacks on smart VSCs and overall wind farms. We then proposed a novel time sequence machine learning-based intrusion detection framework that can be implemented to detect different cyberattacks in the VSCs. The performance of the proposed framework has been compared with that of autoencoder and clustering-based intrusion detection framework. The proposed framework was validated by using the IEEE 39 bus power system in the presence of four wind farms in different locations. Using several metrics for intrusion detection performance, we validated the effectiveness of the proposed framework.

42 ENGINEERING↗
DOE OSTI2025

ARM-IRL: Adaptive Resilience Metric Quantification Using Inverse Reinforcement Learning

The resilience of safety-critical systems is gaining importance due to the rise in cyber and physical threats, especially within critical infrastructure. Traditional static resilience metrics may not capture dynamic system states, leading to inaccurate assessments and ineffective responses to cyber threats. This work aims to develop a data-driven, adaptive method for resilience metric learning. We propose a data-driven approach using inverse reinforcement learning (IRL) to learn a single, adaptive resilience metric. The method infers a reward function from expert control actions. Unlike previous approaches using static weights or fuzzy logic, this work applies adversarial inverse reinforcement learning (AIRL), training a generator and discriminator in parallel to learn the reward structure and derive an optimal policy. The proposed approach is evaluated on multiple scenarios: optimal communication network rerouting, power distribution network reconfiguration, and cyber–physical restoration of critical loads using the IEEE 123-bus system. The adaptive, learned resilience metric enables faster critical load restoration in comparison to conventional RL approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Local and utility-wide cost allocations for a more equitable wildfire-resilient distribution grid

Climate-induced extreme weather conditions make electricity infrastructure more vulnerable. They increase the risk of power-line-ignited wildfires which can, in turn, jeopardize electric power delivery. Here, leveraging machine learning, we show that lower-income communities in California not only have lower fractions of power distribution lines undergrounded, but overhead lines and poles in their neighbourhoods are also more vulnerable to wildfires. Should they bear the cost of undergrounding fire-prone lines themselves, they would have to pay a disproportionately higher cost per household. We propose a cost allocation scheme with an income threshold below which the cost is borne by utility-wide ratepayers and above which the cost is borne locally. This scheme can not only minimize the average of undergrounding costs per household as a share of income, but also homogenize such cost–income ratios across communities. Furthermore, our research demonstrates the opportunity to appropriately integrate existing policies to make electricity infrastructure affordable, equitable and reliable amidst climate change.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Business Models for Scaling Demand Flexibility Volume III – Stakeholder ecosystem management challenges, and lessons learned from U.S. programs

Load growth at the grid edge is driving increased attention to the distribution system and its ability to enable customer technology adoption in an affordable and timely manner. Key industry stakeholders, including electric utilities and regulators, can benefit from strategies to manage and balance customer needs with infrastructure investments, such as demand flexibility. This report focuses on demand flexibility—the ability to reduce, shift, shed, generate, or modulate loads in response to building and grid needs—to reduce the need for costly grid upgrades by deferring investment needs and increase system reliability by shifting electricity usage during periods of high risk. Specifically, we focus on the emerging characteristics of business models for demand flexibility as a framework to understand how demand flexibility programs generate value. In this report, we focus on demand flexibility program stakeholder ecosystem management strategies, which provide information on value delivery and describe how program implementers leverage partner capabilities and collaborate to deliver customer and grid benefits. This report discusses the role of stakeholder ecosystem management in demand flexibility programs, identifies existing challenges to effective stakeholder management, and describes lessons learned. This report is part of a series that includes reports on value propositions, customer relationship management strategies, and program life cycle.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Business Models for Scaling Demand Flexibility Volume II – Customer relationship management strategies, challenges, and lessons learned from U.S. programs

Load growth at the grid edge is driving increased attention to the distribution system and its ability to enable customer technology adoption in an affordable and timely manner. Key industry stakeholders, including electric utilities and regulators, can benefit from strategies to manage and balance customer needs with infrastructure investments, such as demand flexibility. This report focuses on demand flexibility—the ability to reduce, shift, shed, generate, or modulate loads in response to building and grid needs—to reduce the need for costly grid upgrades by deferring investment needs and increase system reliability by shifting electricity usage during periods of high risk. Specifically, we focus on the emerging characteristics of business models for demand flexibility as a framework to understand how demand flexibility programs generate value. In this report, we focus on demand flexibility program customer relationship management strategies, which provide information on value creation and focus on ensuring customers can navigate programs smoothly. This report discusses the role of customer relationship management strategies in demand flexibility programs, characterizes customer relationship management strategies that can be considered during program design and implementation, identifies existing challenges to customer relationship management strategies, and describes lessons learned. This report is part of a series that includes reports on value propositions, stakeholder ecosystem management, and program life cycle.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Business Models for Scaling Demand Flexibility Volume I – Value proposition characteristics, challenges, and lessons learned from U.S. programs

Load growth at the grid edge is driving increased attention to the distribution system and its ability to enable customer technology adoption in an affordable and timely manner. Key industry stakeholders, including electric utilities and regulators, can benefit from strategies to manage and balance customer needs with infrastructure investments, such as demand flexibility. This report focuses on demand flexibility—the ability to reduce, shift, shed, generate, or modulate loads in response to building and grid needs—to reduce the need for costly grid upgrades by deferring investment needs and increase system reliability by shifting electricity usage during periods of high risk. Specifically, we focus on the emerging characteristics of business models for demand flexibility as a framework to understand how demand flexibility programs generate value. In this report, we focus on demand flexibility value propositions, which provide information on value creation and describe how programs deliver clear benefits that address customer and grid needs. This report discusses the role of value propositions in demand flexibility programs, provides an overview of value propositions for a range of demand flexibility stakeholders, identifies existing challenges to establishing an effective value proposition, and describes lessons learned. This report is part of a series that includes reports on customer relationship management strategies, stakeholder ecosystem management, and program life cycle.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Business Models for Scaling Demand Flexibility Volume IV – Program life cycle challenges and lessons learned from U.S. programs

Load growth at the grid edge is driving increased attention to the distribution system and its ability to enable customer technology adoption in an affordable and timely manner. Key industry stakeholders, including electric utilities and regulators, can benefit from strategies to manage and balance customer needs with infrastructure investments, such as demand flexibility. This report focuses on demand flexibility—the ability to reduce, shift, shed, generate, or modulate loads in response to building and grid needs—to reduce the need for costly grid upgrades by deferring investment needs and increase system reliability by shifting electricity usage during periods of high risk. Specifically, we focus on the emerging characteristics of business models for demand flexibility as a framework to understand how demand flexibility programs generate value. In this report, we focus on the life cycle of demand flexibility programs, which provides information on value creation and describes the various deployment phases program implementers navigate from initial program conceptualization through to program expansion and replication to new customer segments and regions. This report characterizes the key phases of the demand flexibility program life cycle, identifies existing challenges across the program deployment phases, and describes lessons learned. This report is part of a series that includes reports on customer relationship management strategies, stakeholder ecosystem management, and program life cycle.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A chloroplast protein atlas reveals punctate structures and spatial organization of biosynthetic pathways

Chloroplasts are eukaryotic photosynthetic organelles that drive the global carbon cycle. Despite their importance, our understanding of their protein composition, function, and spatial organization remains limited. Here, we determined the localizations of 1,034 candidate chloroplast proteins using fluorescent protein tagging in the model alga Chlamydomonas reinhardtii. The localizations provide insights into the functions of poorly characterized proteins; identify novel components of nucleoids, plastoglobules, and the pyrenoid; and reveal widespread protein targeting to multiple compartments. We discovered and further characterized cellular organizational features, including eleven chloroplast punctate structures, cytosolic crescent structures, and unexpected spatial distributions of enzymes within the chloroplast. We also used machine learning to predict the localizations of other nuclear-encoded Chlamydomonas proteins. The strains and localization atlas developed here will serve as a resource to accelerate studies of chloroplast architecture and functions.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Feedback Control Approaches for Restoration of Power Grids from Blackouts

The automated restoration of power systems with variable energy resources is a timely problem to tackle. Automated restoration advice can support operators in deciding on strategic actions to restore power grids from a blackout with a mix of conventional and renewable generation resources. To this end, this paper frames the restoration process of power grids with solar resources as a nonlinear dynamic model with algebraic constraints in discrete time which is steered by feedback control loops. We discuss two feedback-control strategies based on greedy and reinforcement learning algorithms, and contrast their performance with restoration plans generated by a mixed-integer linear program. We found that the reinforcement learning algorithm infers restoration actions faster than the greedy one. However, the tuning process of the reinforcement learning parameters is slower than for the greedy one.

machine learning↗
DOE OSTI2025

Parallel sorting algorithm classification: is manual instrumentation necessary?

Understanding parallel algorithms is crucial for accelerating scientific simulations on complex, distributed memory, high-performance computers. Modern algorithm classification approaches learn semantics directly from source code to differentiate between algorithms, however, accessing source code is not always possible. We can learn about parallel algorithms from observing their performance, as programs running the same algorithms and using the same hardware should exhibit similar performance characteristics. We present an approach to learn algorithm classes from parallel performance data directly in order to classify algorithms without access to the source code. We extend previous work to enable classifying parallel sorting algorithms using automatic instrumentation instead of requiring manual region annotations in the source code. In this work, we design and demonstrate a study for classification of parallel sorting algorithms using parallel performance data collected from automatic instrumentation, and evaluate the performance of our new methodology on classification. We leverage Caliper to collect the performance data, Thicket for our exploratory data analysis (EDA), and PyTorch and Scikit-learn to evaluate the effectiveness of random forests, support vector machines (SVMs), decision trees, neural networks, and logistic regressions on parallel performance data. Additionally, we study noise in parallel performance data, whether the removal of noise and pre-processing of the data is necessary to accurately classify parallel sorting algorithms, and determine the effectiveness of features created from performance data. In conclusion, we demonstrate classification accuracy for these five different models of up to 97.7% across four different parallel algorithm classes.

Algorithm Classification↗