Search NASA⌕ Search

SEARCH · Search NASA

Results for “Operator 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 1,351 records · Page 75
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. Here, in this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Use of Machine Learning on PMU Data for Transmission System Fault Analysis

Synchrophasor technology has been used for monitoring, control, and protection of bulk power system for over 10 years. Deployment of phasor measurement units (PMUs) in the USA power system has surpassed 3000 units installed in the transmission substations as stand-alone intelligent electronic devices (IEDs) or as a software add-on to other devices such as digital protective relays (DPRs) or digital fault recorders (DFRs). By now, thousands of terabytes of PMU data may have been captured and stored by various transmission system operators (TSOs) and independent system operators (ISOs). This creates an opportunity to deploy advanced machine learning (ML) techniques to detect and classify faults recorded by PMUs automatically to be used by the system operators for rapid, critical decision-making when manual analysis of the past or unfolding events is not feasible. In this paper we offer a brief background on how the automated fault analysis may be done using DPR and/or DFR data, and compare some of the legacy approaches to the new ML approaches in the context of the system-wide PMU recordings. We then offer insights from developing practical ML solutions that have been applied on field recordings captured by close to 450 PMUs from all three US interconnections (Western, Eastern and ERCOT) over two years (2016-2017). We identify and illustrate ML challenges we addressed: inaccurate data, data with scarce and temporally imprecise fault labels, data recorded by PMUs sparsely located at substations resulting in the fault records taken afar from the ends of the faulted lines, data containing only positive sequence values, and data taken at different voltage levels. We then illustrate the ML model results for fault analysis under different application scenarios. The novelty of this study is not only in the design, implementation, and performance analysis of the ML algorithms, but also in the use of advanced fault modelling and simulation approaches to improve the training results when developing supervised ML models for fault detection and classification. Extensive simulations of faults were conducted on a 14-bus power system to create a training dataset with over 1400 accurately labelled faults. This dataset was applied to enhance the accuracy of fault detection and classification of machine learning-based models trained with small number of labelled faults in large datasets recorded in the grid interconnections ranging from 5,000 to 70,000 buses.

Synchrophasors, Machine Learning, Fault Analysis, ↗
DOE OSTI2023

Cyber threat assessment of machine learning driven autonomous control systems of nuclear power plants

We report advanced cyber-attacks against critical infrastructure and the energy sector are becoming more common. With the invention of autonomous control systems (ACS) within advanced nuclear reactor designs, system designers, reactor operators, and regulators must consider cybersecurity during the design and operational phases. This article provides a cyber threat assessment of machine learning (ML)-based digital twinning (DT) technologies in the context of advanced reactor ACS. A cyber–physical testbed was created to emulate nuclear reactor digital instrumentation and controls (I&C) and act as a basis for the ACS. The ACS was designed as two plant-level DTs predicting reactor malfunctions and determining control actions and two component-level DTs responsible for classifying component states and forecasting component inputs and outputs (I/O). Two duplicate ACS designs– one using a traditional ML framework and one using an automated ML (AutoML) framework– were created and tested against cyber-attacks on training data, real-time process data, and ML model architectures to determine their respective qualitative cyber-risk in terms of likelihood and impact. Both frameworks showed similar cyber-resilience against training, real-time, and ML architecture attacks, proving that neither is inherently more secure. Recommended safeguard and security measures are posed to system designers, reactor operators, and regulators to maintain the cybersecurity of ML-based DT technologies such as ACS, prompting a holistic view of shared responsibility for maintaining cyber-secure ML-based systems.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2022

Fluid-Kinetic Coupling: Advanced Discretizations for Simulations on Emerging Heterogeneous Architectures (LDRD FY20-0643)

Plasma physics simulations are vital for a host of Sandia mission concerns, for fundamental science, and for clean energy in the form of fusion power. Sandia's most mature plasma physics simulation capabilities come in the form of particle-in-cell (PIC) models and magnetohydrodynamics (MHD) models. MHD models for a plasma work well in denser plasma regimes when there is enough material that the plasma approximates a fluid. PIC models, on the other hand, work well in lower-density regimes, in which there is not too much to simulate; error in PIC scales as the square root of the number of particles, making high-accuracy simulations expensive. Real-world applications, however, almost always involve a transition region between the high-density regimes where MHD is appropriate, and the low-density regimes for PIC. In such a transition region, a direct discretization of Vlasov is appropriate. Such discretizations come with their own computational costs, however; the phase-space mesh for Vlasov can involve up to six dimensions (seven if time is included), and to apply appropriate homogeneous boundary conditions in velocity space requires meshing a substantial padding region to ensure that the distribution remains sufficiently close to zero at the velocity boundaries. Moreover, for collisional plasmas, the right-hand side of the Vlasov equation is a collision operator, which is non-local in velocity space, and which may dominate the cost of the Vlasov solver. The present LDRD project endeavors to develop modern, foundational tools for the development of continuum-kinetic Vlasov solvers, using the discontinuous Petrov-Galerkin (DPG) methodology, for discretization of Vlasov, and machine-learning (ML) models to enable efficient evaluation of collision operators. DPG affords several key advantages. First, it has a built-in, robust error indicator, allowing us to adapt the mesh in a very natural way, enabling a coarse velocity-space mesh near the homogeneous boundaries, and a fine mesh where the solution has fine features. Second, it is an inherently high-order, high-intensity method, requiring extra local computations to determine so-called optimal test functions, which makes it particularly suited to modern hardware in which floating-point throughput is increasing at a faster rate than memory bandwidth. Finally, DPG is a residual-minimizing method, which enables high-accuracy computation: in typical cases, the method delivers something very close to the $L^2$ projection of the exact solution. Meanwhile, the ML-based collision model we adopt affords a cost structure that scales as the square root of a standard direct evaluation. Moreover, we design our model to conserve mass, momentum, and energy by construction, and our approach to training is highly flexible, in that it can incorporate not only synthetic data from direct-simulation Monte Carlo (DSMC) codes, but also experimental data. We have developed two DPG formulations for Vlasov-Poisson: a time-marching, backward-Euler discretization and a space-time discretization. We have conducted a number of numerical experiments to verify the approach in a 1D1V setting. In this report, we detail these formulations and experiments. We also summarize some new theoretical results developed as part of this project (published as papers previously): some new analysis of DPG for the convection-reaction problem (of which the Vlasov equation is an instance), a new exponential integrator for DPG, and some numerical exploration of various DPG-based time-marching approaches to the heat equation. As part of this work, we have contributed extensively to the Camellia open-source library; we also describe the new capabilities and their usage. We have also developed a well-documented methodology for single-species collision operators, which we applied to argon and demonstrated with numerical experiments. We summarize those results here, as well as describing at a high level a design extending the methodology to multi-species operators. We have released a new open-source library, MLC, under a BSD license; we include a summary of its capabilities as well.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2018

History and Archives Contribute to the Success of Space Flight Programs

Final Paper, not the Abstract, is attached: This report discusses how history can be used by management, engineering, and operations personnel within space flight programs. Works by professional historians and sociologists inform key decision makers and policy specialists on lessons learned from space flight program management successes and failures, as well as from legislative affairs, policy making, and commercial space efforts. Vehicle engineering history written by engineers for an engineering or operations audience informs project management and technical personnel on lessons learned, best practices, and the rationale behind the design and operation of flight vehicles and supporting ground systems. Archives play a critical role in supporting the efforts of both professional historians and flight program personnel. Suggestions are made concerning how professional historians could leverage the interests and knowledge of flight program personnel to obtain more insight that is needed to support historical research efforts.

Archive↗
DOE OSTI2020

Uncertainty Quantification for Capacity Expansion Planning

This report quantifies the uncertainty in output decisions from a Capacity Expansion Planning (CEP) model. The need to understand how uncertainties within CEP models and modeling assumptions affect Quantities of Interest (QoIs) such as expansion and operating costs, as well as expansion decisions remains an ongoing challenge in scientific research and industrial operations. This area of research is particularly important for models which seek to capture how large networks will evolve and operate under increased sources of variable generation, i.e., higher penetration of renewable technologies such as solar and wind generators. Uncertainty quantification (UQ) of CEP models which estimate expansion costs and decisions, and production cost models which estimate operating costs and dispatch decisions, is a key focus of research at NREL. The Regional Energy Deployment System (ReEDS) represents a state-of-the-art CEP model and considers a range of possible grid evolutions in an attempt to identify key drivers, ramifications, and decisions which contribute to better informed investment and policy decisions. However, research to quantify how uncertainties and model assumptions, such as unit commitment (UC), within ReEDS may be affecting its outputs remains challenging due to to size and complexity of the model

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

On the Feasibility of Using Reduced-Precision Tensor Core Operations for Graph Analytics

Today’s data-driven analytics and machine learning workload have been largely driven by the General-PurposeGraphics Processing Units (GPGPUs). To accelerate dense matrix multiplications on the GPUs, Tensor Core Units (TCUs) have been introduced in recent years. In this paper, we study linear-algebra-based and vertex-centric algorithms for various graph kernels on the GPUs with an objective of applying this new hardware feature to graph applications. We identify the potential stages in these graph kernels that can be executed on the Tensor Core Units. In particular, we leverage the reformulation of the reduction and scan operations in terms of matrix multiplication [1]on the TCUs. We demonstrate that executing these operations on the TCUs, available inside different graph kernels, can assist in establishing an end-to-end pipeline on the GPGPUs without depending on hand-tuned external libraries and still can deliver comparable performance for various graph analytics.

Graph algorithms, GPU computing↗
NASA NTRS2007

Building Operations Efficiencies into NASA's Ares I Crew Launch Vehicle Design

The U.S. Vision for Space Exploration guides the National Aeronautics and Space Administration's (NASA's) challenging missions that expand humanity's boundaries and open new routes to the space frontier. With the Agency's commitment to complete the International Space Station (ISS) and to retire the venerable Space Shuttle by 2010, the NASA Administrator commissioned the Exploration Systems Architecture Study (ESAS) in 2005 to analyze options for safe, simple, cost-efficient launch solutions that could deliver human-rated space transportation capabilities in a timely manner within fixed budget guidelines. The Exploration Launch Projects (ELP) Office, chartered by the Constellation Program in October 2005, has been conducting systems engineering studies and business planning to successively refine the design configurations and better align vehicle concepts with customer and stakeholder requirements, such as significantly reduced life-cycle costs. As the Agency begins the process of replacing the Shuttle with a new generation of spacecraft destined for missions beyond low-Earth orbit to the Moon and Mars, NASA is designing the follow-on crew and cargo launch systems for maximum operational efficiencies. To sustain the long-term exploration of space, it is imperative to reduce the $4 billion NASA typically spends on space transportation each year. This paper gives toplevel information about how the follow-on Ares I Crew Launch Vehicle (CLV) is being designed for improved safety and reliability, coupled with reduced operations costs. These methods include carefully developing operational requirements; conducting operability design and analysis; using the latest information technology tools to design and simulate the vehicle; and developing a learning culture across the workforce to ensure a smooth transition between Space Shuttle operations and Ares vehicle development.

Dumbacher, Daniel L.↗
NASA NTRS2004

Inductive System Health Monitoring

The Inductive Monitoring System (IMS) software was developed to provide a technique to automatically produce health monitoring knowledge bases for systems that are either difficult to model (simulate) with a computer or which require computer models that are too complex to use for real time monitoring. IMS uses nominal data sets collected either directly from the system or from simulations to build a knowledge base that can be used to detect anomalous behavior in the system. Machine learning and data mining techniques are used to characterize typical system behavior by extracting general classes of nominal data from archived data sets. IMS is able to monitor the system by comparing real time operational data with these classes. We present a description of learning and monitoring method used by IMS and summarize some recent IMS results.

Iverson, David L.↗
DOE OSTI2023

Devices and methods for increasing the speed or power efficiency of a computer when performing machine learning using spiking neural networks

A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.

Vineyard, Craig Michael↗
DOE OSTI2025

Physics-informed Deep Reinforcement Learning-based Control in Power systems

Incorporating physics information into the deep reinforcement learning (DRL) process is a promising approach for addressing the challenges faced in learning-based control design problems for physical systems. Power grid dynamics, being a physical system, adheres to specific physical laws, constraints, as well as operational and control rules. Therefore, consideration of such physics-based law improves the learning process drastically. In general, traditional grid control schemes rely on rule-based mechanisms that cannot adapt to changing operating conditions. To improve the adaptability and computation time, recent research has seen a surge of DRL-based applications in power grid control. A generic DRL-based control design imposes the system performance requirements through the design of reward functions. In some cases, some of the important physics information is injected through this reward function. However, due to the complex dynamics and large state-action space, learning an optimal DRL policy often becomes challenging. Inspired by the latest developments in general machine learning (ML) research, power system researchers have been investigating more direct ways of incorporating physics knowledge into DRL training. This chapter specifically focuses on these aspects of physics-informed DRL designs in grid control. It discusses the significance, applications, research gaps, and open problems that need to be addressed in future research.

artificial intelligence, machine learning↗
NASA NTRS2002

Science Planning for Multi-Spacecraft Coordinated Observations

Fulfilling the promise of an era of great observatories, NASA now has more than three space-based astronomical telescopes operating in different wavebands. This situation provides astronomers with a unique opportunity to simultaneously observe with multiple observatories. Yet scheduling multiple observatories simultaneously is highly inefficient when compared to single observatory observations. Thus, programs using multiple observatories are limited not due to scientific restrictions, but due to operational inefficiencies. Each year, a number of proposals are accepted by a space-based observatory for conduction of astronomical observations and gathering of science data for the study of galactic events. Since each space-based observatory uses a set of instruments designed to operate in specific energy regions, most such studies are conducted by submitting observation proposals to multiple observatories, with requests to coordinate among themselves. To assure that the proposed observations can be scheduled, each observatory's staff has to check that the observations are valid and meet all the constraints for their own observatory; in addition, they have to verify that the observations satisfy the constraints of the other observatories. Thus, coordinated observations require painstaking manual collaboration among the observatory staff at each observatory. In order to exploit new paradigms for observatory operation, the Goddard Space Flight Center's Advanced Architectures and Automation Branch has developed a prototype tool called the Visual Observation Layout Tool (VOLT). The main objective of VOLT is to provide a visual tool to automate the science planning of coordinated observations for multiple spacecraft, as well as to increase the scheduling probability of observations. However, VOLT is also useful for single observatory planning to optimize observatory control. Three space-based missions are interested in using VOLT (the Hubble Space Telescope, the Chandra X-Ray Observatory, and the Far Ultraviolet Spectroscopic Explorer). The VOLT team members have collaborated with these missions to gather requirements and obtain feedback on their mission planning processes. VOLT has been developed as a cross-platform Java client application for use by scientists and observatory science planning staff to visualize scheduling options and constraints. It also supports a lightweight graphical user interface for remote viewing via a Web front end. Additionally, it uniquely supports the ability to interact with multiple, diverse scheduling packages in order to determine windows of opportunity for observations and visually portray the constraints of each observation request. VOLT enables science data capture scenarios which are currently either impossible, or which require extensive time and manpower to coordinate amongst multiple observatories. it supports early detection of planning conflicts by generating coordinated solutions based on observatory schedulability and constraints. The project development approach has included frequent prototype demonstrations to our interested missions to obtain feedback after each release of the software. We will present an overview of our lessons learned in infusing the VOLT tool into the operations of the missions we have collaborated with and a brief demonstration of the software.

Maks, Lori↗
DOE OSTI2023

Bi-Level Adaptive Storage Expansion Strategy for Microgrids Using Deep Reinforcement Learning

Battery energy storage (BES) is a versatile resource for the secure and economic operation of microgrids (MGs). Prevailing stochastic optimization-based approaches for BES expansion planning for MGs are computationally complicated. This work proposes a data-driven bi-level multi-period BES expansion planning framework to determine the siting, sizing, and timing of BES installations. The proposed planning framework unifies deep reinforcement learning (DRL) and linear programming, thereby decoupling the determinations for the integer and continuous decision variables in two time scales, respectively. In the upper level, a rainbow DRL agent with quantile regression is trained to provide dynamic planning policies to accommodate stochastic renewable energy resources (RESs), load, and battery price changes efficiently. Further, the lower level computes the optimal operation of MGs with frequency constraints to hedge the islanding contingency. The two levels communicate with one another by exchanging storage configuration and operating expenses in order to accomplish the shared goal of minimizing investment and operation costs. Comparative case studies on an MG are carried out to demonstrate the superiority of the proposed DRL-based solution to the mixed-integer linear programming counterpart on efficiency, scalability, and adaptability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2018

Insights Gained from the Ongoing Integrated Arrival/Departure/Surface (IADS) Traffic Flow Operational Prototype

The Insights Gained from the Ongoing Integrated Arrival/Departure/Surface (IADS) Traffic Flow Operational Prototype presentation will include a definition of the learning objectives for the audience, an overview/explanation of the ATD-2 project, an overview of the ATC/Operator data exchange and integration that is foundational for advanced surface capability, and a description of the ATC/Operator data exchange and integration research questions and insights. It will also give an overview of the overhead stream around CLT and a preview of the operational integration benefits, research questions, and insights related to the overhead stream. It will continue with a surface metering process flow overview, a description of local surface demand/capacity imbalance, the benefits of collaborative surface metering, the associated research questions and insights, and wrap up with the next steps planned for ATD-2.

collaborative operational environment↗
DOE OSTI2024

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRSDate not supplied

Unsupervised Anomaly Detection in High-Dimensional Flight Data Using Convolutional Variational Auto-Encoder

The modern National Airspace System (NAS) is an extremely safe system. The industry has experienced a steady decrease in fatalities over the years. This can be contributed to both improved flight critical systems with redundant hardware and software protections as well as an increased focus on active monitoring and response to real time and historically identified vulnerabilities by implementing more resilient procedures and protocols. The main practice for identifying vulnerabilities in operations leverages domain expertise using knowledge about how the system should behave with the expected tolerances to known safety margins. This approach works well when the system has a well-defined operating condition. However, the operations in the NAS can be highly complex with various nuances that render it difficult to clearly pre-define all known safety vulnerabilities. With the advancement of data science and machine learning techniques, the potential to automatically identify emerging vulnerabilities in the observed operations has become more practical in recent years. The state-of-the-art anomaly detection approaches in aerospace data usually rely on supervised or semi-supervised learning. However, in many real-world problems such as flight safety creating labels for the data requires huge amount of efforts and is largely expensive. As a result, in this article, we develop a Convolutional Variational Auto-Encoder (CVAE), an unsupervised learning approach for anomaly detection in high-dimensional heterogeneous time-series data. We validate performance of CVAE compared to the state-of-the-art supervised learning approach (as an upper bound) as well as an supervised clustering based on K-Means (as a lower bound) on Yahoo!'s benchmark time series anomaly detection data. Finally, we showcase performance of CVAE on a case study of identifying anomalies in the first 60 seconds of commercial flights' take-offs using Flight Operational Quality Assurance (FOQA) data.

Milad Memarzadeh↗
NASA NTRS1997

Nonlinear Performance Seeking Control using Fuzzy Model Reference Learning Control and the Method of Steepest Descent

Performance Seeking Control (PSC) attempts to find and control the process at the operating condition that will generate maximum performance. In this paper a nonlinear multivariable PSC methodology will be developed, utilizing the Fuzzy Model Reference Learning Control (FMRLC) and the method of Steepest Descent or Gradient (SDG). This PSC control methodology employs the SDG method to find the operating condition that will generate maximum performance. This operating condition is in turn passed to the FMRLC controller as a set point for the control of the process. The conventional SDG algorithm is modified in this paper in order for convergence to occur monotonically. For the FMRLC control, the conventional fuzzy model reference learning control methodology is utilized, with guidelines generated here for effective tuning of the FMRLC controller.

Kopasakis, George↗