SEARCH · Search NASA
Results for “Learning systems”
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.
Machine Learning-Based PV Reserve Determination Strategy for Frequency Control on the WECC System
This paper proposes a machine learning based strategy, that is suitable for real-time operation, to determine the optimal photovoltaic (PV) power plants reserve for frequency control. The proposed machine learning algorithm is trained and tested on 1,987 offline simulations of a 60% renewable penetration Western Electricity Coordinating Council (WECC) system. On a realistic 1-day operation profile of the WECC system, the ML model demonstrates a savings of more than 40% PV headroom compared to a conservative approach.
Integrating Machine-learning-assisted Computer Vision with RICH System
Developments in artificial intelligence have vastly expanded the capabilities of robots. Currently, the Spallation Neutron Source (SNS) beamlines at Oak Ridge National Lab (ORNL) have robotic sample loaders to increase the efficiency of running experiments. However, they require retraining if anything about the situation changes, e.g., where the samples are, and cannot notice if errors occur. So, the viability of using computer vision and machine learning to enhance these sample loaders’ functionality was investigated. In this project, the RICH system with a Dobot CR3 6-axis robot present at the VULCAN beamline assisted by an Intel Realsense D435i camera, a unique camera that enables convenient translation of 2D pixel coordinates to 3D world points, was programmed to load ceramic crucibles into a thermogravimetric analyzer (TGA) furnace. An algorithm was constructed in Python with three major phases planned: (1) obtaining a sample, (2) moving it to the target location, and then (3) bringing the sample back to its original location once the experiment finished. In the first phase, the algorithm would dynamically detect sample locations using ArUco markers to recognize the samples’ general location and a custom-trained yolov5 object detection model to locate the crucibles’ centers. Afterward, the robot would be directed to pick up samples based on the crucibles’ calculated positions. In the second phase, the robot would move the sample to a secondary point, reorient its grip, and place the sample at the target location. In the final phase, the robot would determine whether the sample was intact and would bring it back to its original place if it was or raise an alarm. Using this algorithm, the robot was able to pick up different types of crucibles at varying positions. These results indicate that integrating machine-learning-assisted computer vision with robotic sample loaders can result in effective autonomous detection of samples.
Reservoir Computing as a Tool for Climate Predictability Studies
Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate models. In this context, the linear inverse modeling (LIM) approach, by capturing a few essential interactions between dynamical components of the full system, has proven valuable in providing insights into predictability of the full system. We demonstrate that reservoir computing (RC), a form of learning suitable for systems with chaotic dynamics, provides an alternative nonlinear approach that improves on the predictive skill of the LIM approach. We do this in the example setting of predicting sea surface temperature in the North Atlantic in the preindustrial control simulation of a popular earth system model, the Community Earth System Model so that we can compare the performance of the new RC-based approach with the traditional LIM approach both when learning data are plentiful and when such data are more limited. The improved predictive skill of the RC approach over a wide range of conditions—larger number of retained EOF coefficients, extending well into the limited data regime, etc.—suggests that this machine-learning technique may have a use in climate predictability studies. While the possibility of developing a climate emulator—the ability to continue the evolution of the system on the attractor long after failing to be able to track the reference trajectory—is demonstrated in the Lorenz-63 system, it is suggested that further development of the RC approach may permit such uses of the new approach in more realistic predictability studies.
Generative AI models for learning flow maps of stochastic dynamical systems in bounded domains
Simulating stochastic differential equations (SDEs) in bounded domains, presents significant computational challenges due to particle exit phenomena, which requires accurate modeling of interior stochastic dynamics and boundary interactions. Despite the success of machine learning-based methods in learning SDEs, existing learning methods are not applicable to SDEs in bounded domains because they cannot accurately capture the particle exit dynamics. We present a unified hybrid data-driven approach that combines a conditional diffusion model with an exit prediction neural network to capture both interior stochastic dynamics and boundary exit phenomena. Our ML model consists of two major components: a neural network that learns exit probabilities using binary cross-entropy loss with rigorous convergence guarantees, and a training-free diffusion model that generates state transitions for non-exiting particles using closed-form score functions. The two components are integrated through a probabilistic sampling algorithm that determines particle exit at each time step and generates appropriate state transitions. Here, the performance of the proposed approach is demonstrated via three test cases: a one-dimensional simplified problem for theoretical verification, a two-dimensional advection-diffusion problem in a bounded domain, and a three-dimensional problem of interest to magnetically confined fusion plasmas.
Lessons Learned and Scalability Achieved When Porting Uintah to DOE Exascale Systems
A key challenge faced when preparing codes for Department of Energy (DOE) exascale systems was designing scalable applications for systems featuring hardware and software not yet available at leadership-class scale. With such systems now available, it is important to evaluate scalability of the resulting software solutions on these target systems. One such code designed with the exascale DOE Aurora and DOE Frontier systems in mind is the Uintah Computational Framework, an open-source asynchronous many-task (AMT) runtime system. To prepare for exascale, Uintah adopted a portable MPI+X hybrid parallelism approach using the Kokkos performance portability library (i.e., MPI+Kokkos). This paper complements recent work with additional details and an evaluation of the resulting approach on Aurora and Frontier. Results are shown for a challenging benchmark demonstrating interoperability of 3 portable codes essential to Uintah-related combustion research. These results demonstrate single-source portability across Aurora and Frontier with scaling characteristics shown to 3,072 Aurora nodes and 9,216 Frontier nodes. In addition to showing results run to new scales on new systems, this paper also discusses lessons learned through efforts preparing Uintah for exascale systems.
A Deep Reinforcement Learning-based Reserve Optimization in Active Distribution Systems for Tertiary Frequency Regulation
Federal Energy Regulatory Commission (FERC)Orders 841 and 2222 have recommended that distributed energy resources (DERs) should participate in energy and reserve markets; therefore, a mechanism needs to be developed to facilitate DERs’ participation at the distribution level. Although the available reserve from a single distribution system may not be sufficient for tertiary frequency regulation, stacked and coordinated contributions from several distribution systems can enable them participate in tertiary frequency regulation at scale. This paper proposes a deep reinforcement learning (DRL)-based approach for optimization of requested aggregated reserves by system operators among the clusters of DERs. The co-optimization of cost of reserve, distribution network loss, and voltage regulation of the feeders are considered while optimizing the reserves among participating DERs. The proposed framework adopts deep deterministic policy gradient (DDPG), which is an algorithm based on an actor-critic method. The effectiveness of the proposed method for allocating reserves among DERs is demonstrated through case studies on a modified IEEE 34-node distribution system.
Reinforcement Learning for Intelligent Building Energy Management System Control *
A building energy management system (BEMS) is a computer-based system designed to monitor and control a building's energy needs. Modern BEMS rely on the sensing and connectivity capabilities of Internet of Things (IoT) technology to intelligently adjust the energy consumption to reduce cost while respecting the consumers' preferences. Increasingly, control decisions are made based on predictions by models trained using supervised machine learning methods, which still requires control policies to be formulated in a rule-based fashion. When using reinforcement learning (RL) instead, control policies are learned by observing the utility in terms of cost and comfort associated with actions such as a change in the heating system's setpoint. The resulting RL-based controllers can capture not only the dynamics of the building and the associated electrical devices, but also fluctuations in electricity prices and user demand, avoiding the need to combine multiple predictive models with tailored control policies. This chapter will provide an overview of RL-based approaches for BEMS. After sketching the taxonomy of general RL methods, we discuss the implications of relying on the individual methods in a BEMS context. Existing work applying RL is presented along the key devices controlled by BEMS systems. Finally, we summarize the state-of-the-art and sketch limitations and open research directions.
Machine Learning for Mapping Multipactor Susceptibility in RF Systems: Capabilities and Generalization Constraints
Multipactor is a surface-driven electron avalanche phenomenon that degrades the performance and reliability of radio-frequency (RF) systems in particle accelerator and vacuum electronics applications. Multipactor behavior in a given device structure is conventionally assessed through susceptibility charts, which provide a parameter-space characterization of the instability. In this work, we assess the capabilities of machine-learning (ML) models to learn and predict such susceptibility charts and analyze the constraints governing their generalization across materials. Using a simulation-derived dataset spanning six distinct secondary-electron-yield material profiles in a canonical two-surface planar geometry, we train supervised regression models and artificial neural networks to predict the time-averaged electron growth rate, δavg, across the relevant parameter space. Model performance is evaluated using metrics that explicitly probe the structure of susceptibility charts, including Intersection over Union, Structural Similarity Index, and correlation analysis. Tree-based ensemble models outperform neural-network models in reconstructing susceptibility regions and in generalizing across material domains. Principal-component analysis reveals disjoint material feature distributions, indicating that the piecewise mode structure of multipactor susceptibility is difficult to represent with a single global model and that generalization is constrained by data coverage rather than by model complexity. An exhaustive reduced-coverage study further shows that sparse material-space coverage can yield mean performance in the same general range but producing large variability in the susceptibility-region overlap. These results clarify the capabilities of ML-based surrogate models for parameter-space characterization of multipactor discharge. They also provide guidance for their appropriate use in RF system design.
Thermodynamic properties of the Nd-Bi system via emf measurements, $\mathrm{DFT}$ calculations, machine learning, and $\mathrm{CALPHAD}$ modeling
Thermodynamic properties of the Nd-Bi system were investigated using a combination of experimental measurements, first-principles calculations based on density functional theory (DFT), data mining and machine learning (DM + ML) predictions, and calculation of phase diagrams (CALPHAD) modeling. The electromotive force (emf) of Nd-Bi alloys in molten LiCl-KCl-NdCl 3 at 773–973 K was measured via coulometric titration of Nd into Bi for the determination of thermochemical properties such as activity coefficients and solubilities of Nd in Bi. A new peritectic reaction of [liquid + NdBi 2 = Nd 3 Bi 7 ] at 774 K was confirmed using differential scanning calorimetry, structural (X-ray diffraction), and microstructural (scanning electron microscopy) analyses. The unknown crystal structure of NdBi2 was suggested to be a mixture of the anti-La 2 Sb configuration and the La 2 Te-type configuration based on ML predictions for over 26,000 data-mined AB 2 -type configurations together with DFT-based verifications. Using the newly acquired experimental data and DFT-based calculations, the thermodynamic description of the Nd-Bi system was remodeled, and a more complete Nd-Bi phase diagram was calculated, including the Nd 3 Bi 7 compound, invariant transition reactions, and liquidus temperatures.
Learning thermodynamic master equations for open quantum systems
The characterization of Hamiltonians and other components of open quantum dynamical systems plays a crucial role in quantum computing and other applications. Scientific machine learning techniques have been applied to this problem in a variety of ways, including by modeling with deep neural networks. However, the majority of mathematical models describing open quantum systems are linear, and the natural nonlinearities in learnable models have not been incorporated using physical principles. We present a data-driven model for open quantum systems that includes learnable, thermodynamically consistent terms. The trained model is interpretable, as it directly estimates the system Hamiltonian and linear components of coupling to the environment. We validate the model on synthetic two and three-level data, as well as experimental two-level data collected from a quantum device at Lawrence Livermore National Laboratory.
Learning Distributed Geometric Koopman Operator for Sparse Networked Dynamical Systems
Koopman operator theory provides an alternative to study nonlinear networked dynamical systems by mapping the state space to an abstract higher dimensional space where the system evolution is linear. Recent works show the application of graph neural networks (GNNs) to learn state to object-centric embeddings and achieve centralized block-wise computation of Koopman operator (KO) under additional assumptions on the underlying agents properties and constraints on the KO structure. However, the computational complexity of learning the Koopman increases exponentially for networked systems where the number of possible system states grows in a combinatorial fashion with the number of nodes. The learning challenge is further amplified for sparse networks by two factors: 1) sample sparsity for learning the Koopman operator in the non-linear space, and 2) the divergence in the dynamics of individual nodes or from one subgraph to another. Our work aims to address these challenge by formulating the representation learning of networked dynamical systems into a multi-agent paradigm and learning the Koopman operator in a distributive manner. The computational as well as performance advantages of distributed Koopman is predominant for sparse networks whereas for fully connected networks, it is shown to coincide with the centralized one. The empirical study on rope system, network of oscillators and a synthetic power system show comparable and superior performance along with computational benefits with the state-of-the-art methods.
Visualization System for Evolutionary Neural Networks for Deep Learning
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hyper-parameters (at each layer). Evolving architectures and hyper-parameters using a genetic algorithm is one current approach to search the huge space of all possible configurations to find those more optimal for the problem. However, examining an evolutionary process and tuning the genetic algorithm are challenging, pushing most users to treat the process as a black box. To address this challenge, we propose a visualization system for evolutionary neural networks for deep learning. The key feature of our visualization system is to provide a visual analytics environment for evaluating a genetic algorithm in order to improve the underlying operations to reduce time to find good solutions. Our system is able to not only visualize how a genetic algorithm traverses its search space but also allows users to examine evolving networks in-depth to get insights to improve performance through interactive visualization components.
Enhanced Machine-Learning Flow for Microwave-Sensing Systems for Contaminant Detection in Food
The presence of foreign bodies in packaged food is a serious concern for both fnal consumers (allergies, injuries, choking) and food manufacturers (reputation and economic losses). In particular, low-density plastics, glass and wood splinters are hard to detect even by the most advanced X-ray imagers. One solution is Machine-Learning-based Microwave Sensing (MLMWS): a non-invasive, contactless, and real-time method which uses a machine-learning (ML) classifer to analyze the scattered microwaves from the irradiated target object. In this paper, we want to extend our previous work about contaminant detection in cocoa-hazelnut spread jars by proposing an enhanced ML flow to increase the accuracy of the ML classifier. For the first time in this case study, we use a multi-class classifier, we train it with scattering parameters measured at multiple microwave frequencies, with a new pre-processing scaler, data augmentation, quantization-aware training and a pruning schedule. The results show a contaminant detection multi-class accuracy of 94.167% with a latency of 26 µs when targeting an AMD/Xilinx Kria K26 FPGA. Finally, we released our datasets publicly to OpenML.
Risk-Constrained Reinforcement Learning for Inverter-Dominated Power System Controls
Here, this paper develops a risk-aware controller for grid-forming inverters (GFMs) to minimize large frequency oscillations in GFM inverter-dominated power systems. To tackle the high variability from loads/renewables, we incorporate a mean-variance risk constraint into the classical linear quadratic regulator (LQR) formulation for this problem. The risk constraint aims to bound the time-averaged cost of state variability and thus can improve the worst-case performance for large disturbances. The resulting risk-constrained LQR problem is solved through the dual reformulation to a minimax problem, by using a reinforcement learning (RL) method termed as stochastic gradient-descent with max-oracle (SGDmax). In particular, the zero-order policy gradient (ZOPG) approach is used to simplify the gradient estimation using simulated system trajectories. Numerical tests conducted on the IEEE 68-bus system have validated the convergence of our proposed SGDmax for GFM model and corroborate the effectiveness of the risk constraint in improving the worst-case performance while reducing the variability of the overall control cost.
Hybridizing Machine Learning and Physically-based Earth System Models to Improve Prediction of Multivariate Extreme Events (AI Exploration of Wildland Fire Prediction)
Focal Areas: This project responds to two focal areas identified in the DOE Call for AI4ESP White Papers: 1) Predictive modeling through the use of artificial intelligence (AI) techniques, and 2) insights gleaned from complex data using explainable AI and big data analytics. Science Challenge: Large wildland fires (hereafter wildfires) appearing as high-impact compound climate extreme events are closely related to hydroclimate and water cycle extremes that modulate surface fuel supply and combustibility. These compound events have multivariate climatic features (e.g., temperature, precipitation, relative humidity, wind, lightning) and societal drivers (e.g., forest management, land use change, human caused ignitions). Meanwhile, they induce strong feedbacks to the coupled atmosphere, biosphere, and hydrosphere by perturbing regional and global radiation budget as well as ecological, biogeochemical, and water cycles across multiple spatiotemporal scales. The nonlinear interactions between these natural and anthropogenic components of the Earth system are too complex to be completely and adequately represented in today’s Earth system models (ESMs). The inherent stochastic nature of fire activity at all scales further increases the difficulty of its prediction using ESMs that are usually developed from deterministic equations and parameterizations. Besides, concurrence of long-term (decadal to interdecadal) global climate change and fire regime shifts overlapping with short-term (intraseasonal to interannual) variations of regional fire weather and burning activity confound predictability of these compound extreme events. We propose to address the above scientific challenges by using machine learning (ML)-based data-driven modeling techniques to integrate observations and physically-based ESMs’ simulations in a computationally efficient hybrid prediction system. This prediction system is supposed to characterize the wildfire’s sensitivity to climate and exogenous drivers at high resolution (~ 0.25°) on subseasonal to seasonal (S2S) timescales providing improved predictability and explainability. We will use the system to help identify: (1) What are the computational elements of a hybrid system needed to predict compound climate extreme events such as global wildfires? (2) What are the key drivers (either natural or anthropogenic) that modulate short-term variations of multivariate fire weather and burning activity over different regions? How can one take advantage of those driver-response relationships to improve the predictability of large wildfires on S2S time scales? (3) What are the underlying physical mechanisms and sources of improved predictability? Which ML techniques are optimal in revealing and adapting these mechanisms?
Reinforcement Learning of Structured Stabilizing Control for Linear Systems With Unknown State Matrix
This paper delves into designing feedback control gains for a continuous-time linear quadratic regulator (LQR) problem that is constrained to certain predefined structure with unknown state matrix. We bring forth the ideas from reinforcement learning (RL) in conjunction with sufficient stability and performance guarantees in order to design these structured gains using the trajectory measurements of states and controls. Here we first formulate a model-based framework using dynamic programming (DP) to embed the structural constraint to the LQR gain computation in the continuous-time setting, and then subsequently, formulate a policy iteration RL algorithm that can alleviate the requirement of known state matrix in conjunction with maintaining the feedback gain structure. The design enables a distributed learning control design which is necessary for many large-scale cyber-physical systems. Theoretical guarantees are provided for stability and convergence of the structured reinforcement learning (SRL) algorithm. We validate our theoretical results with numerical simulations on a multi-agent networked linear time-invariant (LTI) dynamic system.
Automated System-wide Event Detection and Classification Using Machine Learning on Synchrophasor Data
As the number of phasor measurement units (PMUs) deployed in a power system increases, and their data volume streamed to the control canter intensifies, operators are facing challenges related to the analysis of such data, which need to be observed and responded to as the measurements are displayed in the Control Room. Humans are generally unable to process such large amount of data efficiently and rapidly. There is an apparent need for automated ways to analyze the data, extract actionable information about occurrence of specific events, and characterize the events quickly and cost effectively. This paper discusses the use of machine learning (ML) to facilitate such tasks by providing automated, highly computationally efficient, and cost-effective ways of extracting actionable information from synchrophasor big data in real-time. We developed Big Data Smart (BDSmart) ML-based prototype tool for the Control Room use that automatically analyses data properties from synchrophasor system measurements taken across the three grid Interconnections in the USA (Western, Eastern and ERCOT). The data collected from several hundreds of PMUs located across the Interconnections over a period of two years have been made available for our extensive study. As a result, we were able to identify a number of big data properties that influence how ML methodology is applied to select, develop, train and test the data models that can eventually be used for the tool implementation. The resulting set of candidate algorithms spans unsupervised, supervised, semi-supervised and transfer-learning approaches. Many ML techniques, such as decision trees, multinomial logistic regression, feed-forward neural networks, K-nearest neighbor, multiclass support vector machine, and single and multi-channel convolutional neural networks, are implemented, and their performance is examined. We offer the results from testing the data models. The novelty of our study is in the approaches for bad data detection and mitigation, selection of a simplified feature for event detection, and data label improvements. As a result, we came up with a list of recommendations for the utilities on how to improve the PMU recording practices to cater to the future ML applications aimed at automating the analysis of synchrophasor data.