SEARCH · Engineering Papers

Results for “agent based model”

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 415 records · Page 23

All sources NASA NTRS DOE OSTI

NASA NTRS2003

Advantages of Brahms for Specifying and Implementing a Multiagent Human-Robotic Exploration System

We have developed a model-based, distributed architecture that integrates diverse components in a system designed for lunar and planetary surface operations: an astronaut's space suit, cameras, all-terrain vehicles, robotic assistant, crew in a local habitat, and mission support team. Software processes ('agents') implemented in the Brahms language, run on multiple, mobile platforms. These mobile agents interpret and transform available data to help people and robotic systems coordinate their actions to make operations more safe and efficient. The Brahms-based mobile agent architecture (MAA) uses a novel combination of agent types so the software agents may understand and facilitate communications between people and between system components. A state-of-the-art spoken dialogue interface is integrated with Brahms models, supporting a speech-driven field observation record and rover command system. An important aspect of the methodology involves first simulating the entire system in Brahms, then configuring the agents into a runtime system Thus, Brahms provides a language, engine, and system builder's toolkit for specifying and implementing multiagent systems.

Clancey, William J.↗

DOE OSTI2023

Analysis of Building Model Forecasts using Autonomous HVAC Optimization System for Residential Neighborhood

Heating, ventilation, and air conditioning (HVAC) systems account for the highest share of home energy consumption in the United States. Optimized HVAC control can provide thermal improved comfort to the occupants, improve energy efficiency, reduce energy cost, and support grid services. In this paper, we discuss a multi-agent and cloud-based software framework that has been deployed in occupied residential neighborhood. This system enables automatic data collection, learning, optimization, and dispatches signals to neighborhood devices. HVAC optimization is based on model predictive control (MPC). Since the operational performance of MPC depends on model forecasting accuracy, it is crucial to evaluate the model continuously and modify or retrain it as necessary. In this research, we developed an automated workflow to evaluate the performance of temperature and power forecasts based on measured data in the real world. This will provide researchers with a deeper understanding of the model and how it can be improved.

Lebakula, Viswadeep↗

NASA NTRS2014

Model Checking Degrees of Belief in a System of Agents

Reasoning about degrees of belief has been investigated in the past by a number of authors and has a number of practical applications in real life. In this paper we present a unified framework to model and verify degrees of belief in a system of agents. In particular, we describe an extension of the temporal-epistemic logic CTLK and we introduce a semantics based on interpreted systems for this extension. In this way, degrees of beliefs do not need to be provided externally, but can be derived automatically from the possible executions of the system, thereby providing a computationally grounded formalism. We leverage the semantics to (a) construct a model checking algorithm, (b) investigate its complexity, (c) provide a Java implementation of the model checking algorithm, and (d) evaluate our approach using the standard benchmark of the dining cryptographers. Finally, we provide a detailed case study: using our framework and our implementation, we assess and verify the situational awareness of the pilot of Air France 447 flying in off-nominal conditions.

MAS Verification↗

NASA NTRS2010

The Emergence of Agent-Based Technology as an Architectural Component of Serious Games

The evolution of games as an alternative to traditional simulations in the military context has been gathering momentum over the past five years, even though the exploration of their use in the serious sense has been ongoing since the mid-nineties. Much of the focus has been on the aesthetics of the visuals provided by the core game engine as well as the artistry provided by talented development teams to produce not only breathtaking artwork, but highly immersive game play. Consideration of game technology is now so much a part of the modeling and simulation landscape that it is becoming difficult to distinguish traditional simulation solutions from game-based approaches. But games have yet to provide the much needed interactive free play that has been the domain of semi-autonomous forces (SAF). The component-based middleware architecture that game engines provide promises a great deal in terms of options for the integration of agent solutions to support the development of non-player characters that engage the human player without the deterministic nature of scripted behaviors. However, there are a number of hard-learned lessons on the modeling and simulation side of the equation that game developers have yet to learn, such as: correlation of heterogeneous systems, scalability of both terrain and numbers of non-player entities, and the bi-directional nature of simulation to game interaction provided by Distributed Interactive Simulation (DIS) and High Level Architecture (HLA).

Phillips, Mark↗

DOE OSTI2025

An analysis of physics limited dispatch of nuclear renewable integrated energy systems using deep reinforcement learning and dynamic modeling

Previous approaches to dispatching nuclear integrated energy systems (NIES) have focused on the profitability and flexibility of these systems to operate on energy grids with highly variable pricing. However, due to the complexity involved in modeling and designing these systems, there has been less emphasis on ensuring that these dispatch strategies are physically achievable. It is imperative to develop methods that allow the system to remain within the desired NIES operating conditions and perform this based on realistic limited forecasted information. This research employs next generation artificial intelligence, namely deep reinforcement learning (DRL), and a dynamic system model written in Modelica to find a safe and profitable dispatch strategy for a solar nuclear hybrid design. The DRL agent is shown to find a novel dispatch strategy that manages both power ramping and power levels while respecting operational limits. This DRL-based dispatch is compared to other dispatching strategies including an optimal design solution from mixed integer linear programming (MILP). It is found that incorporating the physics of such a tightly coupled NIES limits the profitability of the MILP-based dispatch strategy. As a result, the MILP solution overestimates the design’s generated revenue. In contrast, DRL significantly reduces the number of breaches of safe operational conditions during energy arbitrage while maintaining profitability. Furthermore, this work paves the way for a more detailed assessment of NIES profitability and could be used to aid operator decisions on future NIES projects.

14 - SOLAR ENERGY↗

NASA NTRS2013

Dynamics and Control of a Disordered System in Space

In this paper, we present some ideas regarding the modeling, dynamics and control aspects of granular spacecraft. Granular spacecraft are complex multibody systems composed of a spatially disordered distribution of a large number of elements, for instance a cloud of N grains in orbit, with N greater than 10(exp 3). These grains can be large (Cubesat-size) or small (mm-size), and can be active, i.e., a fully equipped vehicle capable sensing their own position and attitude, and enabled with propulsion means, or entirely passive. The ultimate objective would be to study the behavior of the single grains and of large ensembles of grains in orbit and to identify ways to guide and control the shape of a cloud composed of these grains so that it can perform a useful function in space, for instance, as an element of an optical imaging system for astrophysical applications. This concept, in which the aperture does not need to be continuous and monolithic, would increase the aperture size several times compared to large NASA observatories such as ATLAST, allowing for a true Terrestrial Planet Imager that would be able to resolve exo-planet details and do meaningful spectroscopy on distant world. In the paper, we address the modeling and autonomous operation of a distributed assembly (the cloud) of large numbers of highly miniaturized space-borne elements (the grains). A multi-scale, multi-physics model is proposed of the dynamics of the cloud in orbit, as well as a control law for cloud shape maintenance, and preliminary simulation studies yield an estimate of the computational effort, indicating a scale factor of approximately N(exp 1.4) as a function of the number of grains. A granular spacecraft can be defined as a collection of a large number of space-borne elements (in the 1000s) designed and controlled such that a desirable collective behavior emerges, either from the interactions among neighboring grains, and/or between the grains and the environment. In this paper, each grain is considered to be a highly miniaturized spacecraft which has limited size and mass, hence it has limited actuation, limited propulsive capability, limited power, limited sensing, limited communication, limited computational resources, limited range of motion, limited lifetime, and may be expendable. The modeling and dynamics of clouds of vehicles is more challenging than with conventional vehicles because we are faced with a probabilistic vehicle composed of a large number of physically disconnected vehicles. First, different scales of motion occur simultaneously in a cloud: translations and rotations of the cloud as a whole (macro-dynamics), relative rotation and translation of one cloud member with respect to another (meso-dynamics), and individual cloud member dynamics (micro-dynamics). Second, the control design needs to be tolerant of the system complexity, of the system architecture (centralized vs. decentralized large scale system control) as well as robust to un-modeled dynamics and noise sources. Figure 1, top left, shows the kinematic parameters of a 1000 element cloud in orbit. The motion of the system is described with respect to a local vertical-local horizontal (LV-LH) orbiting reference frame (x,y,z)=F(sub ORF) of origin O(sub ORF) which rotates with mean motion omega and orbital semi-major axis R(sub 0). The orbital geometry at the initial time is defined in terms of its six orbital elements, and the orbital dynamics equation for point O(sub ORF) is propagated forward in time under the influence of the gravitational field of the primary and other external perturbations, described below. The origin of this frame coincides with the initial position of the center of mass of the system, and the coordinate axes are z along the local vertical, x toward the flight direction, and y in the orbit normal direction. The assumptions we used to model the dynamics are as follows: 1) The inertial frame is fixed at Earth's center. 2) The orbiting Frame ORF follows Keplerian orbit. 3) the cloud system dynamics is referred to ORF. 4) the attitude of each grain uses the principal body frame as body fixed frame. 5) the atmosphere is assumed to be rigidly rotating with the Earth. Regarding the grains forming the cloud: 1) each grain is modeled as a rigid body; 2) a simple attitude estimator provides attitude estimates, 3) a simple guidance logic commands the position and attitude of each grain, 4) a simple local feedback controller based on PD control of local states is used to stabilize the attitude of the vehicle. Regarding the cloud: 1) the cloud as a whole is modeled as an equivalent rigid body in orbit, and 2) an associated graph establishes agent connectivity and enables coupling between modes of motion at the micro and macro scales; 3) a simple guidance and estimation logic is modeled to estimate and command the attitude of this equivalent rigid body; 4) a cloud shape maintenance controller is based on the dynamics of a stable virtual truss in the orbiting frame. Regarding the environmental perturbations acting on the cloud: 1) a non-spherical gravity field including JO (Earth's spherical field) zonal component, J2 (Earth's oblateness) and J3 zonal components is implemented; 2) atmospheric drag is modeled with an exponential model; 3) solar pressure is modeled assuming the Sun is inertially fixed; and 4) the Earth's magnetic field is model using an equivalent dipole model. The equations of motion are written in a referential system with respect to the origin of the orbiting frame and the state is propagated forward in time using an incremental predictor-corrector scheme. A representative cloud with varying number of grains is simulated to identify the limitations in computation time as the number of grains grows. We derive a control law to track a desired surface in the ORF (equivalently to maintain a reference cloud shape) by defining an error from a desired surface shape, and designing a control law that is exponentially stable and reduces the tracking error to zero. Figure 1 (top right) shows a comparison of various requirements for simulation of single spacecraft vs. granular spacecraft, indicating the high degree of complexity that needs to be taken into consideration. The ORF components of control force required by one of the grains is, for this particular case, in the micro-Newton range. However, no attempt has been made yet to reconfigure (or re-orient) the cloud configuration internally, for which forces in the milli-Newton level are expected, depending on the time required to do the reconfiguration. Figure 1, bottom, shows the computation time as a function of the number of grains, indicating an order N(exp 1.43) scaling on a 8 Gb, 1067 MHz RAM MacOSX computer with a 3.06 GHz Intel Core 2 Duo processor. With this metric, the same simulation for a system of N=1000 grains would take 5.4 hours, and 146 hours (i.e., 6 days) for a system with N=10,000 grains. Therefore, efficient ways to simulate this complex system, where not only the time scales of natural system dynamics, but also the sampling times of the Guidance, Navigation, and Control are included, remain to be explored. Additional details on the cloud modeling, dynamics, and control will be described in the paper.

simulation↗

DOE OSTI2023

Aligning theoretical and empirical representations of soil carbon-to-nitrogen stoichiometry with process-based terrestrial biogeochemistry models

Soil carbon-nitrogen (C:N) stoichiometry acts as a control over decomposition and soil organic matter formation and loss, making it a key soil property for understanding ecosystem dynamics and projected ecosystems responses to global environmental change. However, the controls of soil C:N and how they respond to increasing pressures from global change agents are not fully understood. The “foundational” controls on soil C:N, namely plant and microbial C:N, have been used to predict soil C:N, but fail to accurately simulate all ecosystems and may be insufficient for predictions under global environmental change. Here we present an “emerging” representation of controls of soil C:N that includes plant-microbe-mineral feedbacks that have been shown to regulate soil C:N. We argue that including representation of these emerging drivers in process-based terrestrial biogeochemistry models, which include biological N fixation, mycorrhizae, priming, root exudation of organic acids, and mineralogy (including soil texture, mineral composition, and aggregation), will improve mechanistic representation of soil C:N and associated processes. Such improvements will produce models that will better simulate a variety of ecological states and predict soil C:N when global changes modify plant-microbe-mineral interactions. Here, we align our empirical understanding of controls of soil C:N with those controls represented in models, identifying contexts where emerging drivers might be particularly important to represent (e.g., priming and root exudation in nutrient-limited conditions) and areas of future work. Additionally, we show that implementing emerging drivers of soil C:N results in different simulated outcomes at steady state and in response to elevated atmospheric CO2. Our review and preliminary simulations support the need to incorporate emerging drivers of soil C:N into process-based terrestrial biogeochemistry models, allowing for both theoretical exploration of mechanisms and potentially more accurate predictions of land biogeochemical responses to global change.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Flexible Reinforcement Learning Framework for Building Control using EnergyPlus-Modelica Energy Models

In recent years, reinforcement learning (RL) methods have been greatly enhanced by leveraging deep learning approaches. RL methods applied to building control have shown potential in many applications due to their ability to complement or replace conventional methods such as model-based or rule-based controls. However, RL-based building control software is likely tailored either to one target building system or to a specific RL method so that significant additional effort would be required to customize the RL-based controller for use in other building systems or with other RL approaches. Also, RL-based building controls usually depend on building energy simulations to train controllers, so emulating building dynamics (i.e., thermal dynamics and control dynamics) and capturing sub-hourly dynamic profiles are crucial to further the development of effective RL-based building control methods. To address these challenges, we present an open source RL-based control software employing a high-fidelity hybrid EnergyPlus-Modelica building energy model which emulates building dynamics at 1-minute resolution. This software consists of decoupled components (environment, building emulator, control agent, and RL algorithm), which allows for quick prototyping and benchmarking of standard RL algorithms in different systems; for example, a single component can be replaced without revising all of the software. To demonstrate this software framework, we conducted a benchmark study using an EnergyPlus-Modelica building energy model for a Chicago office building with an RL-based controller to dynamically control the chilled water temperature setpoint and the air handling unit supply air temperature setpoint on selected floors.

Lee, Joon-Yong↗

DOE OSTI2025

DOE Repository Metadata Profile (DRMP): A Metadata Framework for Advancing Interoperability and AI Readiness Across Scientific Repositories

The Department of Energy (DOE) funds a diverse and distributed ecosystem of repositories that steward scientific data, publications, and software across its research programs, user facilities, and national laboratories. While significant progress has been made in standardizing dataset-level metadata, the metadata describing repositories themselves (their identity, governance, access interfaces, policies, and technical capabilities) remains inconsistent and fragmented across DOE-funded systems. This variability limits discoverability, interoperability, automated validation, and AI-driven analysis, all of which are increasingly essential for modern scientific workflows. To address this gap, the DOE Data Curation Working Group (DCWG) developed the DOE Repository Metadata Profile (DRMP). The DRMP is a practical, community-driven framework that defines how repositories can describe themselves in a consistent, machine-actionable, and scalable manner. The DRMP is not a new metadata schema. Instead, it is a mapping profile and structured element set capturing the essential characteristics of DOE repositories. It harmonizes repository-level metadata across six widely adopted community schemas: RE3Data; DCAT-US v3; Schema.org; Dublin Core; DataCite 4.6; and PREMIS 3.0. This harmonization eliminates reinvention and enables interoperability within DOE and across the broader scientific ecosystem. A core objective of the DRMP is to reduce burden on repositories by allowing them to reuse their existing metadata through a Rosetta-style crosswalk rather than redesigning local implementations. The profile introduces a three-level conformance model that supports incremental adoption: • Level 1 – Minimum Viable Record (MVR): foundational identification elements required for workflows, project registration, and basic repository presence. • Level 2 – Interoperable: structured metadata enabling alignment with national and international discovery systems. • Level 3 – AI-Ready: enhanced provenance, policy transparency, fixity, semantic context, and capabilities that support automated reasoning, model training governance, and machine-assisted curation. To support implementation, the DRMP includes JSON Schema definitions, OpenAPI patterns, and MCP templates that allow repositories to publish machine-readable metadata directly within existing platforms. These resources are modular and lightweight, enabling adoption without major architectural change. Adopting the DRMP enables repositories to: • Enhance discoverability and interoperability by aligning identifiers, classifications, and descriptive elements across widely used schema standards. • Support federated discovery and cross-registration across DOE systems, Data.gov, and international catalogs. • Enable AI agents and workflow orchestration systems to interpret repository-level metadata within the American Science Cloud (AmSC) through Model Context Protocol (MCP)-based context publication. • Demonstrate alignment with DOE’s open science, stewardship, and FAIR data priorities. This guidance represents a community-driven step forward. Through voluntary adoption and continued feedback, the DRMP advances a cohesive, machine-actionable description of DOE repositories that supports FAIR data practices, preparing the infrastructure for AI-enabled research, and strengthening the discoverability and reuse of DOE’s scientific outputs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

NASA NTRS1993

Undecidability in macroeconomics

In this paper we study the difficulty of solving problems in economics. For this purpose, we adopt the notion of undecidability from recursion theory. We show that certain problems in economics are undecidable, i.e., cannot be solved by a Turing Machine, a device that is at least as powerful as any computational device that can be constructed. In particular, we prove that even in finite closed economies subject to a variable initial condition, in which a social planner knows the behavior of every agent in the economy, certain important social planning problems are undecidable. Thus, it may be impossible to make effective policy decisions. Philosophically, this result formally brings into question the Rational Expectations Hypothesis which assumes that each agent is able to determine what it should do if it wishes to maximize its utility. We show that even when an optimal rational forecast exists for each agency (based on the information currently available to it), agents may lack the ability to make these forecasts. For example, Lucas describes economic models as 'mechanical, artificial world(s), populated by ... interacting robots'. Since any mechanical robot can be at most as computationally powerful as a Turing Machine, such economies are vulnerable to the phenomenon of undecidability.

Chandra, Siddharth↗

NASA NTRS1999

Reinforcement Learning in a Nonstationary Environment: The El Farol Problem

This paper examines the performance of simple learning rules in a complex adaptive system based on a coordination problem modeled on the El Farol problem. The key features of the El Farol problem are that it typically involves a medium number of agents and that agents' pay-off functions have a discontinuous response to increased congestion. First we consider a single adaptive agent facing a stationary environment. We demonstrate that the simple learning rules proposed by Roth and Er'ev can be extremely sensitive to small changes in the initial conditions and that events early in a simulation can affect the performance of the rule over a relatively long time horizon. In contrast, a reinforcement learning rule based on standard practice in the computer science literature converges rapidly and robustly. The situation is reversed when multiple adaptive agents interact: the RE algorithms often converge rapidly to a stable average aggregate attendance despite the slow and erratic behavior of individual learners, while the CS based learners frequently over-attend in the early and intermediate terms. The symmetric mixed strategy equilibria is unstable: all three learning rules ultimately tend towards pure strategies or stabilize in the medium term at non-equilibrium probabilities of attendance. The brittleness of the algorithms in different contexts emphasize the importance of thorough and thoughtful examination of simulation-based results.

Bell, Ann Maria↗

DOE OSTI2023

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

Machine learning (ML) methods, especially reinforcement learning (RL), have been widely considered for traffic signal optimization in intelligent transportation systems. Most of these ML methods are centralized, lacking in scalability and adaptability in large traffic networks. Further, it is challenging to train such ML models due to the lack of training platforms and/or the cost of deploying and training in a real traffic networks. This paper presents an approach for the integration of decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin (DT) to optimize traffic signals for the reduction of traffic congestion and network-wide fuel consumption related to stopping. Specifically, the DGMARL agents learn traffic state patterns and make decisions regarding traffic signal control with assistance from a Digital Twin module, which simulates and replicates the traffic behaviors of a real traffic network. The proposed approach was evaluated using PTV-Vissim [1], a microscopic traffic simulation platform. PTV-Vissim is also the simulation engine of the DT, enabling emulation and optimization of the traffic signals on the MLK Smart Corridor in Chattanooga, Tennessee. Compared to an actuated signal control baseline approach, experiment results show that Eco_PI, a developed performance measure capturing the impact of stops on fuel consumption, was reduced by 44.27% in a 24-hour and an average of 29.88% in a PM-peak-hour scenario.

Multi-Agent Reinforcement Learning, Digital Twin, ↗

DOE OSTI2022

Metabolic flux modeling of Gluconobacter oxydans enables improved production of bioleaching organic acids

Bioleaching with organic acids is an option for recovery of rare earth elements (REE) and or other valuable metals from consumer or industrial wastes. Biohydrometallurgy can play an economically and environmentally sustainable role in REE recycling, particularly if agriculture or food wastes are used as the carbon substrates for production of the bioleaching agents. A challenge for organic acid based REE bioleaching is the incomplete conversion of the carbon substrate to an optimal organic acid mixture with high REE extraction capability. To help meet this challenge a metabolic flux model was developed for Gluconobacter oxydans to identify options for improving sugar conversion to chelating organic acids. Here, model predictions were consistent with laboratory data for the microbial consumption of glucose and production of gluconic acid and suggested that providing growth conditions with relatively high carbon to nitrogen molar ratios could result in production of lower pH biolixiviant and thus improve REE bioleaching yields.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2004

Meeting the Deadline: Why, When and How

A normative system is defined as any set of interacting agents whose behavior can usefully be regarded as norm-directed. Most organizations, and more specifically institutions, fall under this definition. Interactions in these normative systems are regulated by normative templates that describe desired behavior in terms of deontic concepts (obligations, prohibitions and permissions), deadlines, violations and sanctions. Agreements between agents, and between an agent and the society, can then be specified by means of contracts. Contracts provide flexible but verifiable means to integrate society requirements and agent autonomy. and are an adequate means for the explicit specification of interactions. From the society perspective, it is important that these contracts adhere to the specifications described in the model of the organization. If we want to automate such verifications, we have to formalize the languages used for contracts and for the specification of organizations. The logic LCR is based on deontic temporal logic. LCR is an expressive language for describing interaction in multi-agent systems, including obligations with deadlines. Deadlines are important norms in most interactions between agents. Intuitively, a deadline states that an agent should perform an action before a certain point in time. The obligation to perform the action starts at the moment the deadline becomes active. E.g. when a contract is signed or approved. If the action is not performed in time a violation of the deadline occurs. It can be specified independently what measure has to be taken in this case. In this paper we investigate the deadline concept in more detail. The paper is organized as follows. Section 2 defines the variant of CTL we use. In section 3, we discuss the basic intuitions of deadlines. Section 4 presents a first intuitive formalization for deadlines. In section 5, we look at a more complex model for deadlines trying to catch some more practical aspects. Finally, in section 6 we present issues for future work and our conciusions.

Dignum, Frank↗

DOE OSTI2025

From clutter to clarity: Emergent neural operators via questionnaire metrics

Real-world datasets in chemical engineering and bioengineering processes—such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials—can often be unlabeled or disorganized, rendering the training of existing supervised learning models ineffective at learning the underlying dynamics. To salvage these datasets for decision-making, we first seek to obtain clarity from the cluttered data. Here, we present a framework for developing “structural” generative models, discovering emergent equations, and constructing efficient emulators from scrambled datasets by integrating unsupervised organizational learning techniques (Questionnaires) with advanced deep learning architectures (Deep Hidden Physics Models and Deep Operator Networks). Our approach is demonstrated on two illustrative model systems: (a) a 1D advection–diffusion partial differential equation representing a winding underground pipe and (b) an ensemble of Stuart–Landau oscillators, an agent-based system of coupled ordinary differential equations. In both cases, we successfully reconstruct meaningful spatial, temporal, and parameter embeddings from scrambled data, enabling good predictions of system dynamics. As a result, we highlight the framework’s potential for broader applications, enabling data-driven system identification in fields with inherently disorganized or hidden parameter spaces.

42 ENGINEERING↗

DOE OSTI2021

A Novel Multiagent Resource Sharing Algorithm for Control of Advanced Energy Systems

This paper implements a novel resource sharing control strategy on a fuel cell–gas turbine hybrid power system at the National Energy Technology Laboratory’s Hybrid Performance Facility (Hyper). In a fuel cell–gas turbine hybrid power system, the simultaneous interaction of the gas turbine and the fuel cell creates a tightly coupled environment characterized by conflicting dynamics. In this paper, a model-free control approach is applied to solve the tightly coupled control problem posed by this challenging environment. Specifically, this control problem is presented as a resource sharing problem that can be solved using a resource sharing algorithm that is defined based on the distribution construction concept. This algorithm creates computational agents and solves the problem through the distribution and redistribution of shared resources defined as blocks. Furthermore, two agents were created; the first agent (agent 1) controls the gas turbine speed by adjusting the electric load, and the second agent (agent 2) controls the cathode mass flow through the fuel cell using the cold-air bypass valve. A parametric study was performed over the course of 15 experimental tests for both agents 1 and 2 through an evaluation of the responses based on setpoint changes. The algorithm was shown to have behavior comparable to a previously implemented multi-input multioutput state-space controller, which was designed through a model-based control approach. The resource sharing algorithm was able to find stable performance during run-time operations without any prior system knowledge identification on the power plant and without creating models used in traditional control strategies.

25 ENERGY STORAGE↗

DOE OSTI2022

A Q-Learning-Based Approach for Distributed Beam Scheduling in mmWave Networks

We consider the problem of distributed downlink beam scheduling and power allocation for millimeter-Wave (mmWave) cellular networks where multiple base stations (BSs) belonging to different service operators share the same unlicensed spectrum with no centralized control or explicit coordination among them. Our goal is to design efficient distributed beam scheduling and power allocation schemes such that the network-level payoff, defined as the weighted sum of the total throughput and a power penalization term, can be maximized. To this end, we propose a distributed scheduling approach to power allocation and adaptation for efficient interference management over the shared spectrum by modeling each BS as an independent Q-learning agent. As a baseline, we compare the proposed approach to the state-of-the-art non-cooperative game-based approach which was previously developed for the same problem. We conduct extensive experiments under various scenarios to verify the effect of multiple factors on the performance of both approaches. Experiment results show that the proposed approach adapts well to different interference conditions by learning from experience and thus can achieve higher payoff than the game-based approach. The proposed approach can also be integrated into our previously developed Lyapunov stochastic optimization framework for the purpose of network utility maximization with optimality guarantee. As a result, the weights in the payoff function can be automatically and optimally determined by the virtual queue values from the sub-problems derived from the Lyapunov optimization framework.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2024

Reinforcement learning for block decomposition of planar CAD models

Abstract The problem of hexahedral mesh generation of general CAD models has vexed researchers for over 3 decades and analysts often spend more than 50% of the design-analysis cycle time decomposing complex models into simpler blocks meshable by existing techniques. The decomposed blocks are required for generating good quality meshes (tilings of quadrilaterals or hexahedra) suitable for numerical simulations of physical systems governed by conservation laws. We present a novel AI-assisted method for decomposing (segmenting) planar CAD (computer-aided design) models into well shaped rectangular blocks. Even though the simple examples presented here can also be meshed using many conventional methods, we believe this work is proof-of-principle of a AI-based decomposition method that can eventually be generalized to complex 2D and 3D CAD models. Our method uses reinforcement learning to train an agent to perform a series of optimal cuts on the CAD model that result in a good quality block decomposition. We show that the agent quickly learns an effective strategy for picking the location and direction of the cuts and maximizing its rewards. This paper is the first successful demonstration of an agent autonomously learning how to perform this block decomposition task effectively, thereby holding the promise of a viable method to automate this challenging process for more complex cases.

97 MATHEMATICS AND COMPUTING↗