Search NASA⌕ Search

SEARCH · Search NASA

Results for “agent based modeling”

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 OSTI2022

A Micro-Mechanical Constitutive Model to Predict Hygrothermal Aging of Cross-Linked Polymers

Abstract A multi-physics material model is presented to describe the effects of temperature, oxygen, and humidity on the constitutive response of cross-linked polymers. The effect of hygrothermal damage on the mechanical integrity of the polymer matrix can be considered as the result of damage accumulation of two independent aging mechanism namely, i) thermo-oxidative, and ii) hydrolytic aging. In order to capture the mutual effects of thermo-oxidative and hydrolytic aging, an assumption has been made that each of the aging phenomenon can be superposed to each other. In fact, each of them works independently and as a result, they can compete with each other. Utilizing the theory of network decomposition, all phenomena and their correlation were modeled and thus, the strain energy function of the polymer matrix is written with respect to four independent mechanisms, i) the shrinking original matrix that has neither been attacked by water nor oxygen, ii) conversion of the first network to two new network due to the reduction and formation of cross-links, and iii) energy loss from network degradation due to attack of the water molecules to polymer active agents. Moreover, the proposed model is micro-mechanically based and is mainly relevant on thin samples due to our underlying assumption of homogeneous diffusion of oxygen and water throughout the matrix. The model has been validated against extensive data-sets obtained from experiments we specifically designed for concept validation.

Bahrololoumi, Amir↗
DOE OSTI2023

Reinforcement Learning for Load-balanced Parallel Particle Tracing

We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems. Our method combines three novel components: (1) a work donation algorithm, (2) a high-order workload estimation model, and (3) a communication cost model. First, we design an RL-based work donation algorithm. Our algorithm monitors workloads of processes and creates RL agents to donate data blocks and particles from high-workload processes to low-workload processes to minimize program execution time. The agents learn the donation strategy on the fly based on reward and cost functions designed to consider processes' workload changes and data transfer costs of donation actions. Second, we propose a workload estimation model, helping RL agents estimate the workload distribution of processes in future computations. Third, we design a communication cost model that considers both block and particle data exchange costs, helping RL agents make effective decisions with minimized communication costs. We demonstrate that our algorithm adapts to different flow behaviors in large-scale fluid dynamics, ocean, and weather simulation data. Our algorithm improves parallel particle tracing performance in terms of parallel efficiency, load balance, and costs of I/O and communication for evaluations with up to 16,384 processors.

Distributed and parallel particle tracing↗
DOE OSTI2024

Graph-Based Modeling for the Detection and Tracking of Sarin-Surrogate-Induced Neurotoxicity Using a Human-Relevant, In-Vitro Brain Model

Organophosphorus (OP) nerve agents are a chemical threat to the United States, to the civilian population (e.g., pesticides) and historically weaponized (e.g., sarin) as chemical warfare agents. The unprecedented, accelerated process from “bench-to-bedside” during the SARSCov2 pandemic has made it clear that technology and tools need to be readily available for immediate response. Advances in human organ tissue mimetic systems are a promising technology to evaluate the human-relevant response in vitro for basic and applied research and drug screening. In particular, current brain microphysiological systems (MPS) have the capability to monitor and detect changes in engineered human neural circuit activity. However, current data analytics approaches for these systems lack the granularity to functionally detect and distinguish the different mechanisms that occur in the brain following neurotoxicity, injury, and disease. The goal of this project was to advance the computational analytical capabilities of the brain MPS to detect functional changes in neural circuit structure at different stages of Sarin surrogate-induced neurotoxicity. We developed graph-based models to (1) identify the composition of the neural circuit structure; (2) detect and monitor how this structure changes following sarin-induced neurotoxicity; and (3) evaluate the analytical pipeline using known/promising oxime reactivators. Through experiments on the bMPS where in vitro neuronal cultures were exposed to a sarin surrogate, we demonstrated the capabilities of our computational pipeline to identify different responses in the functional networks of brain cells exposed to low and high concentrations of the nerve agent. We identified a biphasic response of human neural network activity following exposure to a sarin-surrogate that had not been reported in the literature before. The graph-based models and software developed in this project can be used for future studies that leverage the brain MPS technology, such as treatment efficacy assessment.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Motion Planning Algorithms for Safety and Quantum Computing Efficiency

Motion planning remains a fundamental problem in robotics. Sampling-based algorithms use randomization to allow efficient solutions to this complex problem. As mobile robots and autonomous vehicles become more prevalent in everyday life, motion planning must be applied to increasingly challenging scenarios. Safety has become a paramount concern in motion planning for ensuring robotic applications enrich human lives. To date, many motion planning techniques to increase safety in the face of uncertain and dynamic environments have been developed. This dissertation first addresses distributional safety of Rapidly-Exploring Random Trees (RRT) through our algorithm W-Safe RRT. To acknowledge distributional uncertainty and poor modeling, W-Safe RRT uses the Wasserstein metric to provide a probabilistic bound on the distributional distance between a robot and obstacles. Human-interpretable environmental agent classification allows online safety margin adaptation. We propose and analyze an integrating region method for online classification that increases actor labeling accuracy based on behavioral feature values when compared to state of the art methods. The method performs class assignments based on local maximum likelihood in a created behavioral feature-space, allowing a notion of classification uncertainty. Model-based methods with safety guarantees can quickly become computationally in tractable, especially with multiple agents, higher dimensions, and plentiful unknowns. Sampling based algorithms have been parallelized for computation with multi-core computers and GPUs. We consider the use of quantum algorithms and computers for sampling-based motion planning for the first time. Quantum computing performs operations on superpositions of states and can solve certain problems much more efficiently than classical computers, but introduces previously unseen challenges. With Quantum-RRT, we recast the motion planning problem into a database-search structure and use Quantum Amplitude Amplification to find reachable states in the database with a quadratic performance increase over classical methods. We address two error sources with this method: quantum measurement and quantum oracle errors. We then extend this method to Parallel Quantum-RRT, which uses a manager-worker architecture with multiple parallel quantum workers to increase database search efficiency. We compare algorithm architectures and characterize probabilities of multiple workers finding solutions. Lastly, we test in simulation the quantum algorithms against classical versions in a wide variety of scenarios, concluding that a similar parallelization improvement is to be found in the quantum case as was found in the parallelization of classical RRT.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Ringing Artifact Reduction Method for Ultrasound Reconstruction Using Multi-Agent Consensus Equilibrium

Non-destructive characterization of multi-layered structures that can be accessed from only a single side is important for applications such as well-bore integrity inspection. Existing methods related to Synthetic Aperture Focusing Technique (SAFT) rapidly produce acceptable results but with significant artifacts. Recently, ultrasound model-based iterative reconstruction (UMBIR) approaches have shown significant improvements over SAFT. However, even these methods produce ringing artifacts due to the high fractional-bandwidth of the excitation signal.In this paper, we propose a ringing artifact reduction method for ultrasound image reconstruction that uses a multi-agent consensus equilibrium (RARE-MACE) framework. Our approach integrates a physics-based forward model that accounts for the propagation of a collimated ultrasonic beam in multi-layered media, a spatially varying image prior, and a denoiser designed to suppress the ringing artifacts that are characteristic of reconstructions from high-fractional bandwidth ultrasound sensor data. We test our method on simulated and experimental measurements and show substantial improvements in image quality compared to SAFT and UMBIR.

Alanazi, Abdulrahman M↗
DOE OSTI2020

A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience

Here, we study a setting where a group of agents, each receiving partially informative private signals, seek to collaboratively learn the true underlying state of the world (from a finite set of hypotheses) that generates their joint observation profiles. To solve this problem, we propose a distributed learning rule that differs fundamentally from existing approaches, in that it does not employ any form of “belief-averaging”. Instead, agents update their beliefs based on a min-rule. Under standard assumptions on the observation model and the network structure, we establish that each agent learns the truth asymptotically almost surely. As our main contribution, we prove that with probability 1, each false hypothesis is ruled out by every agent exponentially fast, at a network-independent rate that is strictly larger than existing rates. We then develop a computationally-efficient variant of our learning rule that is provably resilient to agents who do not behave as expected (as represented by a Byzantine adversary model) and deliberately try to spread misinformation.

42 ENGINEERING↗
DOE OSTI2020

Evaluating Energy Efficiency Opportunities from Connected and Automated Vehicle Deployments Coupled with Shared Mobility in California

Connected and Automated Vehicles (CAVs) can be considered to be a disruptive transportation technology, with the potential to significantly improve overall transportation system efficiency; however, CAVs may increase induce vehicle miles traveled (VMT) and bring on greater energy consumption. Further, shared mobility is another disruptive transportation event that is reshaping our travel patterns. The primary goal of this project was to extensively collect data from vehicles and associated infrastructure equipped with CAV technologies from both real-world experiments and simulation studies mainly deployed in California, and develop a comprehensive framework for evaluating energy efficiency opportunities from large-scale (e.g., statewide) introduction of CAVs and a wide deployment of shared mobility systems in a variety of scenarios. To quantify the combined impact of CAV and shared mobility on travel behavior, traffic performance, and energy efficiency, a unique mesoscopic simulation-based model was developed for mobility and energy efficiency evaluation considering these disruptive transportation technologies. As a complement to existing studies on nationwide evaluation of CAVs’ energy impacts, this project was focused on data collection efforts and CAV applications under congested traffic environments that are frequently experienced on a massive scale across the major metropolitan areas in California. Extensive real-world data collection supplemented with simulation studies were conducted to cover a variety of CAV and shared mobility scenarios, particularly on scenarios less-explored in the existing research. Another key component of this project was to consider the interaction between different CAV technologies and shared mobility models, and the compound effect on energy efficiency. A comprehensive modeling suite was developed to quantify the impact of new mobility technologies on travel behavior and traffic performance. The developed modeling framework includes an energy intensity module, mode choice module and activity generation module that are integrated into an agent-based BEAM simulation platform to perform impact analysis based on a variety of scenarios. In addition, the RouteE model has been upgraded to incorporate the impact of CAVs on traffic flow, VMT and energy intensity, using micro-simulation data collected from both freeways and urban arterials. A novel fundamental influencing factor (FIF) mode choice model was developed to link CAV and shared mobility components with travel behaviors, and adapted into the BEAM-centered model framework. A statewide energy inventory was constructed under various CAV technology deployment scenarios by incorporating datasets and models for predicting vehicle market share and vehicle usage, which are tightly associated with the penetration of shared mobility systems. Based applying this modeling suite to a calibrated network in Riverside California, it was found that cooperative automated driving in general will improve mobility, but automated vehicles, even when deployed in a shared autonomous fleet, will likely bring an increase of VMT (up to 36%) due to mode shifts and deadheading. Ride-hailing vehicles typically have better energy efficiency and a higher share of electric vehicles, which helps offset the negative impact from VMT increases when estimating the system-level energy consumption. In general, simulation results show a 6% increase in energy consumption for the scenarios with an increasing shift to ride-hailing modes. The statewide analysis based on the National Household Travel Survey (NHTS) sample data is consistent with the findings from the Riverside network and validate the developed clustering-prediction modeling methodology. The outcomes from this project will help close the knowledge gap on recognizing the potential performance and energy impacts of a broad deployment of CAV and shared mobility technologies across a wide range of roadway infrastructure with varying levels of congestion. Results from this project: 1) will support policymakers in steering CAV development and deployment towards an energy favorable direction; 2) reduce uncertainties in estimating energy saving opportunities from new mobility technologies and services; 3) increase the confidence of CAV technology investors both on the infrastructure side (i.e., transportation agencies) and on the vehicle side (i.e., OEMs); and 4) expedite the deployment of energy-efficient CAV and shared mobility applications.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2021

ADDS-EVS: An agent-based deployment decision-support system for electric vehicle services

Rapid and sustainable development of the electric vehicle (EV) industry places the requirement for the plan of EV deployment. For public EV, existing models mainly focus on the charging facility design and fail to capture the multi-modal scenarios. In this work, we develop an agent-based decision-support system for multi-modal electric transits to locate the optimal combinations of key parameters, including the fleet size, the transit schedule, the charging facility design, and the routing strategy. We demonstrate the utilities of our system by simulating public EV services deployed to serve travel needs related to a transportation hub in New York City. To support the decision of the fleet size, we summarize system-level performances including the total satisfied demand, passengers' waiting time, vehicle idling time. The spatial and temporal patterns are extracted to serve a deeper understanding of system dynamics and service quality. Finally, we investigate the interaction between the fleet size design and the routing strategy. The results suggest a necessity of integrating the operation strategies into the planning phase.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

System Analysis Modeling and Intermodal Transportation for Commercial Spent Nuclear Fuel

The United States Department of Energy (DOE) Office of Nuclear Energy is applying knowledge and understanding in the areas of systems level engineering, analysis, and decision making to better inform the waste management pathways for U.S. spent nuclear fuel (SNF). Currently there are 93 operating and 23 shutdown commercial nuclear reactors in the United States. SNF at most of these locations is being stored in spent fuel pools, dry storage, or both [1, 2]. This paper initially goes over the basics of the agent-based simulation tool known as the Next Generation System Analysis Model (NGSAM) that has the capability to model interaction and movements of individual components or groups like casks, railcars etc. The next section covers some of the methods implemented in the Java Transportation Operations Model (JTOM) to facilitate the movement of assemblies, casks, railcars etc. and the various intermodal transfer options. This section also covers the current cask loading and intermodal transfer times implemented in NGSAM. The last section goes over the proposed values for intermodal transportation, and cask transfer/loading operations.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Learning effective stochastic differential equations from microscopic simulations: Linking stochastic numerics to deep learning

We identify effective stochastic differential equations (SDEs) for coarse observables of fine-grained particle- or agent-based simulations; these SDEs then provide useful coarse surrogate models of the fine scale dynamics. We approximate the drift and diffusivity functions in these effective SDEs through neural networks, which can be thought of as effective stochastic ResNets. The loss function is inspired by, and embodies, the structure of established stochastic numerical integrators (here, Euler–Maruyama and Milstein); our approximations can thus benefit from backward error analysis of these underlying numerical schemes. They also lend themselves naturally to “physics-informed” gray-box identification when approximate coarse models, such as mean field equations, are available. Existing numerical integration schemes for Langevin-type equations and for stochastic partial differential equations can also be used for training; we demonstrate this on a stochastically forced oscillator and the stochastic wave equation. Our approach does not require long trajectories, works on scattered snapshot data, and is designed to naturally handle different time steps per snapshot. We consider both the case where the coarse collective observables are known in advance, as well as the case where they must be found in a data-driven manner.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

CACTUS

CACTUS is an innovative LLM‐based agent that combines the cognitive capabilities of large language models with domain‐specific tools. By integrating cheminformatics tools, CACTUS assists researchers in tasks such as molecular property prediction, similarity searching, and drug‐likeness assessment.

Kumar, Neeraj↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
DOE OSTI2026

An agentic artificially intelligent X-ray scientist

Executing experimental tasks in both normal research laboratories and large-scale scientific facilities often requires extensive human supervision and remains a key challenge on the path to fully autonomous, artificial intelligence (AI)-driven science. Here we demonstrate a large language model-driven agent that autonomously performs X-ray sample alignment on a synchrotron beamline by planning actions, executing instrumental commands, interpreting observations and iterating towards experimental goals. Based on existing large language models with structured tool-use via the model context protocol, our AI X-ray scientist was guided and tested using an in-house-built virtual experimental setup that mirrors a six-circle diffractometer at an operational synchrotron beamline. The agentic workflow developed in the virtual environment was directly deployed on a real beamline, where it correctly identified reference reflections and determined the orientation matrix, an essential first step in any type of single-crystal scattering experiment. Our AI X-ray scientist responded effectively to unexpected experimental conditions, demonstrating adaptive problem-solving and readiness for addressing practical experimental situations. Our study provides a step towards autonomous operation across diverse experimental environments at large-scale scattering facilities.

Chen, Zhantao (ORCID:0000000319543868)↗
DOE OSTI2023

Reinforcement-Learning-Based Smart Water Heater Control: An Actual Deployment

Utilizing smart control algorithms for electric water heaters (EWHs) is essential for fully harnessing the demand response (DR) potential of EWHs. For this reason, the use of reinforcement learning (RL) algorithms for EWHs has received increasing attention in recent years. However, existing RL approaches are either simulation-based or use pretrained RL agents. To this end, this paper presents the real-world deployment of a set of model-free RL approaches that aim to minimize the electricity cost of a EWH under a time-of-use electricity pricing policy using standard DR commands (e.g., shed, load up). The experiment results showed that the RL agents can help save electricity cost in the range of 11% to 14% compared to the baseline operation. This study demonstrated that RL-based EWH controllers can be deployed in real world without any prior training and can still save electricity cost.

deep learning↗
DOE OSTI2021

Deep Reinforcement Learning Enabled Physical-Model-Free Two-Timescale Voltage Control Method for Active Distribution Systems

Active distribution networks are being challenged by frequent and rapid voltage violations due to renewable energy integration. Conventional model-based voltage control methods rely on accurate parameters of the distribution networks, which are difficult to achieve in practice. This paper proposes a novel physical-model-free two-timescale voltage control framework for active distribution systems. To achieve fast control of PV inverters, the whole network is first partitioned into several subnetworks using voltage-reactive power sensitivity. Then, the scheduling of PV inverters in the multiple sub-networks is formulated as Markov games and solved by a multi-agent soft actor-critic (MASAC) algorithm, where each subnetwork is modeled as an intelligent agent. All agents are trained in a centralized manner to learn a coordinated strategy while being executed based on only local information for fast response. For the slower time-scale control, OLTCs and switched capacitors are coordinated by a single agent-based SAC algorithm using the global information with considering control behaviors of the inverters. Particularly, the two-level agents are trained concurrently with information exchange according to the reward signal calculated from the data-driven surrogate model. Comparative tests with different benchmark methods on IEEE 33-and 123-bus systems and 342-node low voltage distribution system demonstrate that the proposed method can effectively mitigate the fast voltage violations and achieve systematical coordination of different voltage regulation assets without the knowledge of accurate system model.

24 POWER TRANSMISSION AND DISTRIBUTION↗