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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning

We reconstruct the extra-galactic gamma-ray source-count distribution, or dN/dS, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the Fermi-LAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the (1,10) GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from cataloged sources, and then extends as dN/dS ~ S -2 in the unresolved regime, down to fluxes of 5 · 10 -12 cm -2 s -1 . The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Quantum Reinforcement Learning for Volt-VAR Control in Power Distribution Systems

Volt-VAR control (VVC) is crucial in active distribution networks for optimizing voltage profiles and minimizing network losses. While traditional deep reinforcement learning (DRL) algorithms exhibit promise for VVC, they often require extensive computational resources to handle such a high-dimensional problem. As a potential solution, quantum reinforcement learning (QRL) algorithms integrate the computational capabilities of quantum computing into the DRL framework. However, existing QRL algorithms struggle with complex VVC problems due to the limitations of current quantum hardware. To bridge this gap, this paper proposes an innovative QRL algorithm featuring an end-to-end architecture that integrates a classical autoencoder, variational quantum circuits (VQCs), and classical post-processing layers. This design efficiently compresses high-dimensional grid states, enabling VQCs to leverage quantum advantages while producing multiple control device outputs tailored for VVC tasks. Numerical studies on three representative distribution systems verify the effectiveness and scalability of the proposed QRL algorithm, and demonstrate its enhanced performance over classical approaches with only approximately 1% of the parameters. Additionally, the robustness of our developed algorithm is validated through noisy quantum environments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Postdisaster Routing of Movable Energy Resources for Enhanced Distribution System Resilience: A Deep Reinforcement Learning-Based Approach

The deployment of movable energy resources (MERs) can be an effective strategy to restore critical loads to enhance power system resilience when no other energy sources are available after the occurrence of an extreme event. Since the optimal locations of MERs following an extreme event are dependent on system operating states (e.g., the loads at each node, on/off status of system branches, and so on), existing analytical and population-based approaches must repeat the entire analysis and calculation when the system operating states change. On the contrary, if deep reinforcement learning (DRL)-based algorithms are sufficiently trained with a wide range of scenarios, they can quickly find optimal or near-optimal locations irrespective of changes in system states. A deep Q-learning-based approach is proposed for optimal MER deployment to enhance power system resilience. MERs can be also utilized to complement other types of resources, if available. The proposed approach operates in two stages after the occurrence of extreme events. In the first stage, the distribution network is represented as a graph, and the network is then reconfigured using tie switches by using Kruskal’s spanning forest search algorithm (KSFSA). To maximize critical load recovery, the optimal or near-optimal locations of MERs are chosen in the second stage. Further, case studies on a 33-node distribution system and a modified IEEE 123-node system demonstrate the effectiveness of the proposed approach for postdisaster routing of MERs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2019

Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements

Inversion of temperature and species concentration distributions from radiometric measurements involves solving nonlinear, ill-posed and high-dimensional problems. Machine Learning methods offer solving such highly nonlinear problems, offering an alternative way to deal with complex and dynamic systems with good flexibility. Here, we present a machine learning approach for retrieving temperatures and species concentrations from spectral infrared emission measurements in combustion systems. The training spectra for the machine learning model were synthesized through calculations from HITEMP 2010 for gas mixtures of CO 2 , H 2 O, and CO. The method was tested for different line-of-sight temperature and concentration distributions, different gas path lengths and different spectral intervals. Experimental validation was carried out by measuring spectral emission from a Hencken flat flame burner with a Fourier-transform infrared spectrometer with different spectral resolutions. The temperature fields above the burner for combustion with equivalence ratios of 𝜙 = 1, 𝜙 = 0.8, and 𝜙 = 1.4 were retrieved and were in excellent agreement with temperatures deduced from Rayleigh scattering thermometry.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm

In this article, a Blockchain Enabled Intelligence of Federated Systems (BELIEFS) is proposed to conduct cooperative control for the multi-regional large-scale power system with a multi-agents system (MAS). By establishing a two levels blockchain, each regional AI agent can simultaneously manage intra-regional controllers and cooperate with other AI agents. Under the consensus mechanism, the agents, which respectively conducted distributed deep reinforcement learning (DDRL) algorithm in multi-regions, can have the tolerant capability of malicious attacks in their training process. The demonstration of the proposed approach is within a multi-regional large-scale interconnected power system. Under the mode of "centralized dispatching and hierarchical management", this article aims to definite a mathematical model to deal with the control problem of the power systems. With the comparison experiments, the effectiveness and efficiency of our proposed method in the training process are verified. In addition, malicious attacks are set on the main chain and shard chains to verify the attack-tolerant capability. We expect that such approach and results can suggest a new paradigm of attack-tolerant trustable distributed AI deployment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

(Active) Learning on Groups of Data with Information-Theoretic Estimators

A wide range of machine learning problems, including astronomical inference about galaxy clusters, scene classification, parametric statistical inference, and predictions of public opinion, can be well-modeled as learning a function on (samples from) distributions. This project explores problems in learning such functions via kernel methods, particularly for large-scale problems. When learning from large numbers of distributions, the computation of typical methods scales between quadratically and cubically, and so they are not amenable to large datasets. We investigate the approach of approximate embeddings into Euclidean spaces such that inner products in the embedding space approximate kernel values between the source distributions. We first improve the understanding of the workhorse methods of random Fourier features: we show that of the two approaches in common usage, one is strictly superior. We then present a new embedding for a class of information-theoretic distribution distances, and evaluate it and existing embeddings on several real-world applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Machine Learning Analysis of Hydrologic Exchange Flows and Transit Time Distributions in a Large Regulated River

Hydrologic exchange between river channels and adjacent subsurface environments is a key process that influences water quality and ecosystem function in river corridors. High-resolution numerical models were often used to resolve the spatial and temporal variations of exchange flows, which are computationally expensive. In this study, we adopt Random Forest (RF) and Extreme Gradient Boosting (XGB) approaches for deriving reduced order models of hydrologic exchange flows and associated transit time distributions, with integrated field observations (e.g., bathymetry) and hydrodynamic simulation data (e.g., river velocity, depth). The setup allows an improved understanding of the influences of various physical, spatial, and temporal factors on the hydrologic exchange flows and transit times. The predictors also contain those derived using hybrid clustering, leveraging our previous work on river corridor system hydromorphic classification. The machine learning-based predictive models are developed and validated along the Columbia River Corridor, and the results show that the top parameters are the thickness of the top geological formation layer, the flow regime, river velocity, and river depth; the RF and XGB models can achieve 70% to 80% accuracy and therefore are effective alternatives to the computational demanding numerical models of exchange flows and transit time distributions. Each machine learning model with its favorable configuration and setup have been evaluated. The transferability of the models to other river reaches and larger scales, which mostly depends on data availability, is also discussed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Joint Chance Constraints in AC Optimal Power Flow: Improving Bounds through Learning

This paper considers distribution systems with a high penetration of distributed, renewable generation and addresses the problem of incorporating the associated uncertainty into the optimal operation of these networks. Joint chance constraints, which satisfy multiple constraints simultaneously with a prescribed probability, are one way to incorporate uncertainty across sets of constraints, leading to a chance-constrained optimal power flow problem. Departing from the computationally-heavy scenario-based approaches or approximations that transform the joint constraint into conservative deterministic constraints, this paper develops a scalable, data-driven approach which learns operational trends in a power network, eliminates zero-probability events (e.g., inactive constraints), and accurately and efficiently approximates bounds on the joint chance constraint iteratively. In particular, the proposed framework improves upon the classic methods based on the union bound (or Boole's inequality) by generating a much less conservative set of single chance constraints that also guarantees the satisfaction of the original joint constraint. The proposed framework is evaluated numerically using the IEEE 37-node test feeder, focusing on the problem of voltage regulation in distribution grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2009

Bio-Inspired Neural Model for Learning Dynamic Models

A neural-network mathematical model that, relative to prior such models, places greater emphasis on some of the temporal aspects of real neural physical processes, has been proposed as a basis for massively parallel, distributed algorithms that learn dynamic models of possibly complex external processes by means of learning rules that are local in space and time. The algorithms could be made to perform such functions as recognition and prediction of words in speech and of objects depicted in video images. The approach embodied in this model is said to be "hardware-friendly" in the following sense: The algorithms would be amenable to execution by special-purpose computers implemented as very-large-scale integrated (VLSI) circuits that would operate at relatively high speeds and low power demands.

Duong, Tuan↗
DOE OSTI2021

Application of machine learning for the estimation of electron energy distribution from optical emission spectra

Abstract This paper discusses the use of probabilistic deep neural networks for the prediction of the electron energy probability function in low-temperature non-thermal plasmas. The neural networks are trained using optical emission spectroscopy and Langmuir probe measurements, with the goal of providing a reliable estimate of the electron energy probability function solely from optical emission data. The performance of both non-Bayesian and Bayesian networks is evaluated. It is found that Bayesian models are preferable as they assign a higher level of uncertainty to their prediction especially when the dataset used to train them is small. This work describes one of the many potential applications of machine learning in plasma science and technology.

Physics↗
DOE OSTI2022

Machine Learning Based Network Parameter Estimation Using AMI Data

The expansion of distribution power system and the growing penetration of distributed energy resources present new challenges for situational awareness. Calibrating the extended system model with sensor measurements and maintaining the usability is critical for utilities. This paper presents a distribution network parameter estimation (DNPE) approach using machine learning (ML) and metering data that improve the quality of extended distribution power system modeling. The reliability model can improve the ability of endpoint data to be translated into network-level situational awareness in real time and help distribution system operators (DSOs) solve branch flow and voltage problems. In addition, a data analytic and automate processing scheme is proposed to improve the sensor data quality and prevent misleading information. The effectiveness of the proposed method is verified with actual advanced metering infrastructure (AMI) data on a real utility feeder model, while considering the higher penetration of photovoltaic power generation. The test of DNPE and study results are demonstrated in this paper.

Parameter estimation, machine learning, power dist↗
DOE OSTI2025

Cyberattack Detection and Mitigation on Central Volt‐VAr Using Circuit Law and Machine Learning

ABSTRACT In a distribution grid, voltage is maintained within a nominal range through a Volt‐VAr function that controls capacitor banks, reactive power of distributed energy resources (DER), and on‐load tap changers (OLTC). Availability of communications helps with the implementation of central Volt‐VAr control; however, it also opens the system to cyberattacks, causing voltage disturbances. Previous work has shown the adverse impacts of false data injection (FDI) on the central Volt‐VAr control; however, very few works have studied methods to detect and mitigate FDI on Volt‐VAr control. This paper addresses gaps in the detection and mitigation of FDI on the measurement packets of a central Volt‐VAr control. This work uses a two‐stage algorithm for cyberattack detection since the accuracy of a single‐stage machine learning (ML)–based detection method decreases while dealing with unseen data. The first stage is based on the verification of measurements against circuit laws, and the second stage utilizes a tree search algorithm and an ML method to detect the falsified data. This paper compares long short‐term memory (LSTM) and bidirectional LSTM (BiLSTM) as the employed ML algorithms. Finally, the mitigation algorithm replaces the falsified data with the estimated output of the ML algorithm. The effectiveness of the proposed method is tested for several cases using the IEEE 13‐bus test system in PSCAD software.

Beikbabaei, Milad [Bradley Department of Electrica↗
DOE OSTI2021

Solving inverse problems in stochastic models using deep neural networks and adversarial training

Inverse problems associated with stochastic models constitute a significant portion of scientific and engineering applications. In such cases the unknown quantities are distributions. The applicability of traditional methods is limited because of their demanding assumptions or prohibitive computational consumption; for example, maximum likelihood methods require closed-form density functions, and Markov Chain Monte Carlo needs a large number of simulations. We propose a new method that estimates the unknown distribution by matching the statistical properties between observed and simulated random processes. We leverage the expressive power of neural networks to approximate the unknown distribution and use a discriminative neural network for computing the statistical discrepancies between the observed and simulated random processes. Here we demonstrated numerically that the proposed methods can estimate both the model parameters and learn complicated unknown distributions.

42 ENGINEERING↗
DOE OSTI2021

FL-DISCO: Federated Generative Adversarial Network for Graph-based Molecule Drug Discovery: Special Session Paper

The outbreak of the global COVID-19 pandemic emphasizes the importance of collaborative drug discovery for high effectiveness; however, due to the stringent data regulation, data privacy becomes an imminent issue needing to be addressed to enable collaborative drug discovery. In addition to the data privacy issue, the efficiency of drug discovery is another key objective since infectious diseases spread exponentially and effectively conducting drug discovery could save lives. Advanced Artificial Intelligence (AI) techniques are promising to solve these problems: (1) Federated Learning (FL) is born to keep data privacy while learning data from distributed clients; (2) graph neural network (GNN) can extract structural properties of molecules whose underlying architecture is the connected atoms; and (3) generative adversarial network (GAN) can generate novel molecules while retaining the properties learned from the training data. In this work, we make the first attempt to build a holistic collaborative and privacy-preserving FL framework, namely FL- DISCO, which integrates GAN and GNN to generate molecular graphs. Experimental results demonstrate the effectiveness of FL- DISCO on: (1) IID data for ESOL and QM9, where FL-DISCO can generate highly novel compounds with high drug-likeliness, uniqueness and LogP scores compared to the baseline; (2) non- IID data for ESOL and QM9, where FL-DISCO generates 100% novel compounds with high validity and LogP scores compared to the baseline. We also demonstrate how different fractions of clients, generator and discriminator architectures affect our evaluation scores.

Manu, Daniel↗
DOE OSTI2019

Optimization of Workload Distribution of Data Centers Based on a Self-Learning In Situ Adaptive Tabulation Model

Data center cooling typically involves non-uniform airflow and temperature distributions, which are affected by the IT workload distribution. It is helpful to simulate the airflow and temperature to optimize the workload distribution. Traditional computational fluid dynamics (CFD) simulation is usually time-consuming while conventional reduced order models (ROMs), though computationally fast, may generate inaccurate results even after being fully trained. In Situ Adaptive Tabulation (ISAT), contracting to conventional ROM, can make prediction with error lower than a user-specified tolerance. To demonstrate using of ISAT for optimal workload distribution in data center, this paper presents a preliminary study of an ISAT-based genetic algorithm optimization platform. The ISAT is trained offline by using the results from CFD simulations using a hypothetical simple data center. The optimal workload distribution determined by the platform leads to approximately 6.8% of energy savings when compared to the benchmark with a uniform workload distribution. We note that the time cost for the entire optimization process, including the training of ISAT is about 4 hours, which is acceptable in the design phase.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Residuals-based distributionally robust optimization with covariate information

We consider data-driven approaches that integrate a machine learning prediction model within distributionally robust optimization (DRO) given limited joint observations of uncertain parameters and covariates. Our framework is flexible in the sense that it can accommodate a variety of regression setups and DRO ambiguity sets. We investigate asymptotic and finite sample properties of solutions obtained using Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets within our DRO formulations, and explore cross-validation approaches for sizing these ambiguity sets. Through numerical experiments, we validate our theoretical results, study the effectiveness of our approaches for sizing ambiguity sets, and illustrate the benefits of our DRO formulations in the limited data regime even when the prediction model is misspecified.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systems

Self-healing capability is a critical factor for a resilient distribution system, which requires intelligent agents to automatically perform service restoration online, including network reconfiguration and reactive power dispatch. Here, the article proposes the imitation learning framework for training such an agent, where the agent will interact with an expert built based on the mixed-integer program to learn its optimal policy, and therefore significantly improve the training efficiency compared with exploration-dominant reinforcement learning (RL) methods. This significantly improved training efficiency makes the training problem under N-k scenarios tractable. A hybrid policy network is proposed to handle tie-line operations and reactive power dispatch simultaneously to further improve the restoration performance. The 33-bus and 119-bus systems with N-k disturbances are employed to conduct the training. The results indicate that the proposed method outperforms traditional RL algorithms such as the deep-Q network.

42 ENGINEERING↗