SEARCH · Search NASA

Results for “replay”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Optimizing and Extending the Functionality of EXARL for Scalable Reinforcement Learning [Slides]

The main goal of the Co-Design Summer School 2021 is to provide algorithmic improvements to EXARL framework by improving performance and by adding functionalities. This presentation includes an introduction to reinforcement learning and to EXARL. The researchers expanded the capability of EXARL by including additional agents like (Asynchronized) Advantage Actor Critic (A2C/A3C) and Twin Delayed Deep Deterministic Policy Gradient (TD3). They also explored algorithmic improvements such as v-trace and Prioritized Experience Replay. They found that A2C/A3C performed best with v-trace and outperformed Deep Q-Network (DQN) on both the CartPole game and the ExaBooster scientific environment. Additionally, they found that TD3 performed as good as the existing Deep Deterministic Policy Gradient (DDPG) agent and that adding Prioritized Experience Replay to DDPG accelerated convergence.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Performance for GPU exceptions

Techniques for improving performance of accelerated processing devices (“APDs”) when exceptions occur are provided. In APDs, the very large number of parallel processing execution units, and the complexity of the hardware used to execute a large number of work-items in parallel, means that APDs typically stall when an exception occurs (unlike in central processing units (“CPUs”), which are able to execute speculatively and out-of-order). However, the techniques provided herein allow at least some execution to occur past exceptions. Execution past an exception generating instruction occurs by executing instructions that would not lead to a corruption while skipping those that would lead to a corruption. After the exception has been satisfied, execution occurs in a replay mode in which the potentially exception-generating instruction is executed and in which instructions that did not execute in the exception-wait mode are executed. A mask and counter are used to control execution in replay mode.

Gutierrez, Anthony T.↗

DOE OSTI2024

Efficient distributed continual learning for steering experiments in real-time

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs to achieve high accuracy, short runtime, and scalability. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input minibatches using unbiased, global sampling. We further propose a generalization of rehearsal buffers to support both classification and generative learning tasks, as well as more advanced rehearsal strategies (notably Dark Experience Replay, leveraging knowledge distillation). We illustrate this approach with a real-life HPC streaming application from the domain of ptychographic image reconstruction. Furthermore, we run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 validation accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

Asynchronous data management↗

DOE OSTI2024

Investigating the effects of cooperative transmission expansion planning on grid performance during heat waves with varying spatial scales

There is growing recognition of the advantages of interregional transmission capacity to decarbonize electricity grids. A less explored benefit is potential performance improvements during extreme weather events. This study examines the impacts of cooperative transmission expansion planning using an advanced modeling chain to simulate power grid operations of the United States Western Interconnection in 2019 and 2059 under different levels of collaboration between transmission planning regions. Two historical heat waves in 2019 with varying geographical coverage are replayed under future climate change in 2059 to assess the transmission cooperation benefits during grid stress. The results show that cooperative transmission planning yields the best outcomes in terms of reducing wholesale electricity prices and minimizing energy outages both for the whole interconnection and individual transmission planning regions. Compared to individual planning, cooperative planning reduces wholesale electricity prices by 64.3 % and interconnection-wide total costs (transmission investments + grid operations) by 34.6 % in 2059. It also helps decrease greenhouse gas emissions by increasing renewable energy utilization. However, the benefits of cooperation diminish during the widespread heat wave when all regions face extreme electricity demand due to higher space cooling needs. Despite this, cooperative transmission planning remains advantageous, particularly for California Independent System Operator with significant diurnal solar generation capacity. This study suggests that cooperation in transmission planning is crucial for reducing costs and increasing reliability both during normal periods and extreme weather events. It highlights the importance of optimizing the strategic investments to mitigate challenges posed by wider-scale extreme weather events of the future.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

Impact of cyber attacks on distributed compressive sensing based state estimation in power distribution grids

Modern power distribution grids suffer from multiple vulnerabilities due to the tight integration between the physical system and the cyber infrastructure. Sophisticated and malicious cyber attacks continue to adversely impact the grid operation leading to performance degradation, service interruption, and grid failure. State estimation plays an essential role in grid monitoring and advancing cyber-attack situational awareness. In this regard, this paper first proposes a distributed compressive sensing (CS) state estimation approach for an unobservable distribution grid. Further, the proposed distributed CS approach divides the distribution grid into sub-areas to perform local state estimation. Then an alternating direction method of multipliers (ADMM) based iterative information exchange among neighboring areas is employed to complete the estimation process. In this estimation process, the impact of loss of measurement data, false data injection (FDI), replay, and neighborhood cyber-attacks is analyzed. Extensive simulations are performed on the IEEE 37-bus and IEEE 123-bus standard networks to demonstrate the algorithm’s robustness to the aforementioned cyber-attacks. A quantitative analysis of computational complexity and simulation time of the distributed CS based approach is also presented.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Microgrid energy scheduling under uncertain extreme weather: Adaptation from parallelized reinforcement learning agents

Microgrids are useful solutions for integrating renewable energy resources and providing seamless green electricity to minimize carbon footprint. In recent years, extreme weather events happened often worldwide and caused significant economic and societal losses. Such events bring uncertainties to the microgrid energy scheduling problems and increase the challenges of microgrid operation. Traditional optimization approaches suffer from the inaccuracy of the uncertain microgrid model and the unseen events. Existing reinforcement learning (RL) - based approaches are also hampered by the limited generalization and the increasing computational burden when stochastic formulations are required to accommodate the uncertainties. This paper proposes a new parallelized reinforcement learning (PRL) method based on the probabilistic events to handle the microgrid energy uncertainties. Specifically, several local learning agents are employed to interact with pertinent microgrid environments in a distributed manner and report outcomes to the global agent, which will optimize microgrid energy resources online during extreme events. The stochastic microgrid energy optimization problem is reformulated to include all possible scenarios with probabilities. The advantage estimate functions of learning agents are designed with a backward sweep to transfer the outcomes to the value function updating process. Two simulation studies, stochastic optimization and online testing, are performed to compare with several existing RL approaches. Results substantiate that the proposed PRL method can achieve up to 20% optimization performance improvement with 4 and 28 times less computation cost than Q-learning with experience replay and multi-agent Q-learning approaches, respectively.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2026

Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN

Vehicular controller area networks (CANs) are susceptible to masquerade attacks by malicious adversaries. In masquerade attacks, adversaries silence a targeted ID and then send malicious frames with forged content at the expected timing of benign frames. As masquerade attacks could seriously harm vehicle functionality and are the stealthiest attacks to detect in CAN, recent work has devoted attention to compare frameworks for detecting masquerade attacks in CAN. However, most existing works report offline evaluations using CAN logs already collected using simulations that do not comply with the domain’s real-time constraints. Here we contribute to advance the state of the art by presenting a comparative evaluation of four different non-deep learning (DL)-based unsupervised online intrusion detection systems (IDS) for masquerade attacks in CAN. Our approach differs from existing comparative evaluations in that we analyze the effect of controlling streaming data conditions in a sliding window setting. In doing so, we use realistic masquerade attacks being replayed from the ROAD dataset. We show that although evaluated IDS are not effective at detecting every attack type, the method that relies on detecting changes in the hierarchical structure of clusters of time series produces the best results at the expense of higher computational overhead. We discuss limitations, open challenges, and how the evaluated methods can be used for practical unsupervised online CAN IDS for masquerade attacks.

Anomaly detection↗

DOE OSTI2026

Physics-aware adaptive checkpointing with shadow systems for nonlinear PDE simulations

Large-scale simulations of nonlinear partial differential equations (PDEs) that exhibit strongly transient behavior and pattern-forming dynamics produce enormous amounts of data, which, even with modern storage systems, cannot be stored for later curation. Current I/O strategies either write dense time series of snapshots, which is often prohibitive in I/O and storage, or store a few checkpoints that enable restart but incur expensive recomputation cost and provide no control over post-restart error growth, especially when lossy compression is used. Moreover, most, if not all, existing strategies take no account of the actual physical state of the system. Here, we present a simple physics-aware I/O framework in which a low-cost shadow system adaptively triggers lossy checkpoints when the shadow system deviates from the fine-scale simulation. The shadow system can be a coarsened replica of the fine-scale simulation that evolves concurrently. This means that checkpoints are taken based on the physical state of the system: fewer checkpoints are triggered when the system is quiescent while more are taken when the system undergoes a rapid change. This type of behavior is observed in many systems such as Brusselator and FitzHugh–Nagumo. We illustrate that our framework maintains stable restarts, keeps fine-scale restart errors bounded by shadow errors, and reconstructs the time history with significantly lower error and storage than interpolating fixed-interval snapshots, with low-cost shadow replay and modest online synchronization overhead.

Gong, Qian [ORNL] (ORCID:0000000235704142)↗

DOE OSTI2021

Polarization-Insensitive Medium-Switchable Holographic Metasurfaces

The adoption of metasurfaces has led to revolutionary advances in holography due to improved compactness, integrability, and performance. Switchable meta-holograms projecting different replay field images in a controllable manner are highly desirable. Still, existing technologies generally rely on the use of polarized light and additional optics to facilitate switching. Consequently, the potential benefits afforded through the use of metasurfaces are limited both by the system complexity and a fixed relationship between the optical input and output. In this manuscript, we demonstrate polarization-insensitive metasurfaces encoding arbitrary and independent holograms, which can be switched between by changing the refractive index of the infiltration medium while maintaining identical illumination conditions. Finally, by sidestepping the requirements for high-performance light sources, switching optics, or delicate alignment, this approach points toward ultracompact and cost-effective switchable meta-holograms for various practical applications, such as holographic image projection, eye-perceptible sensors, optical information storage, processing, and security.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Man‐in‐the‐middle attacks and defence in a power system cyber‐physical testbed

Abstract Man‐in‐The‐Middle (MiTM) attacks present numerous threats to a smart grid. In a MiTM attack, an intruder embeds itself within a conversation between two devices to either eavesdrop or impersonate one of the devices, making it appear to be a normal exchange of information. Thus, the intruder can perform false data injection (FDI) and false command injection (FCI) attacks that can compromise power system operations, such as state estimation, economic dispatch, and automatic generation control (AGC). Very few researchers have focused on MiTM methods that are difficult to detect within a smart grid. To address this, we are designing and implementing multi‐stage MiTM intrusions in an emulation‐based cyber‐physical power system testbed against a large‐scale synthetic grid model to demonstrate how such attacks can cause physical contingencies such as misguided operation and false measurements. MiTM intrusions create FCI, FDI, and replay attacks in this synthetic power grid. This work enables stakeholders to defend against these stealthy attacks, and we present detection mechanisms that are developed using multiple alerts from intrusion detection systems and network monitoring tools. Our contribution will enable other smart grid security researchers and industry to develop further detection mechanisms for inconspicuous MiTM attacks.

Wlazlo, Patrick↗

DOE OSTI2024

The CXSFIT spectral fitting code: Past, present and future

Magnetically confined plasma experiments generate a wealth of spectroscopic data. The first step toward extracting physical parameters is to fit a spectral model to the often complex spectra. The CXSFIT (Charge eXchange Spectroscopy FITting) spectral fitting code was originally developed for fitting charge exchange spectra on JET from the late 1980s onward and has been further developed over decades to keep up with the needs of the users. The primary use is to efficiently fit a large number of spectra with many constrained Gaussian spectral lines of which the physical parameters can be coupled in a user-friendly manner. More recent additions to the code include time-dependent couplings between parameters, flexible background subtraction, and a non-linear coupling scheme between fit parameters. The latter was a pre-requisite for implementing Zeeman and motional Stark effect multiplets in the library of spectral features. The ability to save and replay “fit recipes,” even when multiple iterations are required, has ensured the traceability of the results and is one of the keys to the longevity and success of the code. The code is also in use on other tokamaks (AUG, ST-40) and to fit data from other spectroscopic diagnostics on JET. In this paper, we document the current capabilities and philosophy behind the structure of the code, including some of the algorithms used to calculate spectral features numerically efficiently. We also provide an outline of how CXSFIT could be transferred into a framework that would be able to meet the spectral fitting requirements of future devices, such as ITER.

Delabie, Ephrem G.↗

DOE OSTI2026

NeuDiff Agent: a governed AI workflow for single-crystal neutron crystallography

Large-scale facilities increasingly face analysis and reporting latency as a limiting step in scientific throughput, particularly for structural studies that require iterative reduction, integration, refinement and validation. To improve the time to result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source. NeuDiff Agent takes instrument data through reduction, integration, refinement and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent coordinates established crystallographic tools under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing and controlled replay. The present benchmark is limited to structural crystallography for periodic structures; magnetic structure analysis and incommensurate or superspace refinement are outside the scope of the current workflow. Performance is assessed using a fixed prompt protocol and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. In a reference-case benchmark, NeuDiff Agent reduces wall time from 435 min (manual) to 86.5 ± 4.7 to 94.4 ± 3.5 min (4.6–5.0× faster) while producing a validated CIF with no checkCIF level A or B alerts. These results establish a practical route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.

Xiao, Zhongcan [ORNL] (ORCID:0000000220761961)↗

DOE OSTI2023

Designing an Intrusion Detection for an Adjustable Speed Drive System Controlling a Critical Process

In this article, we address the cyber-security problem of industrial control systems (ICSs) when their sensor measurements may be compromised due to an attacker who has intercepted those measurements via a network. We introduce a general-purpose method “Dynamic Watermarking (DW)” to detect potential cyber-intrusions on speed sensor measurements within industrial control systems, which deploy an adjustable speed drive (ASD) to control a critical process. The DW method is injecting a random private low-amplitude signal with a zero mean Gaussian distribution, “watermark”, into one of the input phase voltages powering the ASD system. The watermark signal propagates through the system including pulse width modulation (PWM) power conversion stage and motor, then ultimately appears in the speed sensor measurements. By deploying two statistical DW tests with two proper thresholds, the system can detect potential cyber-intrusions or unobservable cyber-attacks such as replay attacks and false data injection attacks (FDIA). The DW method tested on a laboratory-scale ASD system experimentally to protect the system against cyber-intrusions. This system, powered by a commercial PWM drive operating at 208 V, 3-phase, and 3.7 kW, served as our experimental platform.

42 ENGINEERING↗

DOE OSTI2026

PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow With Continual Learning

Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton–Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under contingency conditions with up to two branch outages, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R 2 >0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r=0.38 ; thermal limits: r=0.22 ), and feature importance analysis supports that the model captures established power flow relationships.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

The Artificial Scientist: in-Transit Machine Learning of Plasma Simulations

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

Kelling, Jeffrey [Helmholtz-Zentrum Dresden Rossen↗

DOE OSTI2021

Impact Analysis of Data Integrity Attacks on FACTS-based Wide-Area Voltage Control System

Energy management system (EMS) consists of several wide-area control applications that serve as a backbone for security, stability, and reliability of the power system. Wide-area voltage control system (WAVCS), one of the critical wide-area applications, operates in coordination with local Flexible AC Transmission System (FACTS) devices to provide voltage security and optimal management of active and reactive power resources. Since the WAVCS relies on wide-area communication and data sharing devices, possible cybersecurity vulnerabilities have to be addressed to ensure the closed-loop operation of WAVCS. In this paper, we present a methodology for performing an impact analysis of cyber-attacks in WAVCS cybersecurity. In particular, different types of data integrity attacks, such as malicious tripping, fault replay, and signal altering attacks, are considered, and detailed impact analysis is conducted in a testbed environment using the Kundur's four machine two-area system. For performing an impact analysis, the transient voltage stability of the sensitive bus voltage is studied, followed by the quantitative assessment and severity ranking using the voltage profile index. Our experimental evaluation reveals that the data integrity attacks on control signals exhibit a higher attack severity than on the measurement signals. Further, the severity of these attacks varies with nature (static or dynamic), location, and types of attacks.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

A Novel Authentication Management for the Data Security of Smart Grid

Bidirectional wireless communication is employed in various smart grid components such as smart meters and control and monitoring applications where security is vital. The Trusted Third Party (TTP) and wireless connectivity between the smart meter and the third party in the key management-based encryption techniques for the smart grid are expected to be totally trustworthy and dependable. In a wired/wireless medium, however, a man-in-the-middle may seek to disrupt, monitor and manipulate the network, or simply execute a replay attack, revealing its vulnerability. Recognizing this, this study presents a novel authentication management (model) comprised of two layer security schema. The first layer implements an efficient novel encryption method for secure data exchange between meters and control center with the help of two partially trusted simple servers (constitutes the TTP). In this setting, one server handles the data encryption between the meter and control center/central database, and the other server administers the random sequence of data transmission. The second layer monitors and verifies exchanged data packets among smart meters. It detects abnormal packets from suspicious sources. To implement this node-to-node authentication, One class support vector machine algorithm is proposed which takes advantages of the location information as well as the data transmission history (node identification, packet size, and data transmission frequency). This schema secures data communication, and imposes a comprehensive privacy throughout the system without considerably extending the complexity of the conventional key management scheme.

24 POWER TRANSMISSION AND DISTRIBUTION↗