Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “reinforcement Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 901 records · Page 50
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with convergence rate, where is the number of iterations.

reinforcement learning, structured learning, conve↗
DOE OSTI2025

Solving high-dimensional partial integral differential equations: The finite expression method

Partial integro-differential equations (PIDEs) have broad applications in the sciences, from electro-magnetism to options pricing. Here, in this paper, we introduce a new finite expression method (FEX) to solve PIDEs. This approach builds upon the original FEX and its inherent advantages with new advances: 1) A novel method of parameter grouping is proposed to reduce the number of coefficients in high-dimensional function approximation; 2) A Taylor series approximation method is implemented to significantly improve the computational efficiency and accuracy of the evaluation of the integral terms of PIDEs. The new FEX based method, denoted FEX-PG to indicate the addition of the parameter grouping (PG) step to the algorithm, provides both high accuracy and interpretable numerical solutions, with the outcome being an explicit equation that facilitates intuitive understanding of the underlying solution structures. These features are often absent in traditional methods, such as finite element methods (FEM) and finite difference methods, as well as in deep learning-based approaches. To benchmark our method against recent advances, we apply the new FEX-PG to solve benchmark PIDEs in the literature. In high-dimensional settings, FEX-PG exhibits strong and robust performance, achieving relative errors on the order of single precision machine epsilon, significantly outperforming existing approaches based on neural networks.

Combinatorial optimization↗
DOE OSTI2022

Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data

Autonomous vehicle-based traffic smoothing con- trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I-24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4’s and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Artificial Intelligence for Energy Systems Cybersecurity

Artificial intelligence and machine learning systems have the potential to influence the future design and implementation of cybersecurity systems for the power grid. These systems may enhance the overall operation of the power system by leveraging and making sense of massive amounts of data. However, we must also understand how AI/ML will need to be protected from cyber threat actors. We discuss the existing insights the NREL team has developed using AI/ML systems and then present resources including ESIF and the Cyber Energy Emulation Platform that can be used to generate training data and insights. We end by offering suggestions on priority research paths for AI in cybersecurity.

artificial intelligence↗
NASA NTRS2021

Towards the Development of a Multi-Agent Cognitive Networking System for the Lunar Environment

This paper details the development of a multi-agent cognitive system intended to optimize networking performance in the lunar environment. NASA’s current concept of the future of lunar communication, LunaNet [1], outlines a complex network of networks. Challenges such as scalability, interoperability and reliability must first be addressed to successfully fulfill this vision. Machine intelligence can greatly reduce the reliance on human operators and enable efficient operations for tasks such as scheduling and network management. The application of machine learning, artificial intelligence, and other automated decision-making techniques can be used to allow network nodes to intelligently sense and adapt to changes in the environment such as link disruptions, new nodes joining the network, and support for a diverse range of protocols. Cognitive networking seeks to evolve these technologies into an autonomous system with improved science data return, reliability, and scalability. In this paper, we study three main areas a means to further develop cognitive networking capabilities: networking and flight software development, analysis of wireless data for modeling and simulation, and development of algorithms for a multi-agent system.

Cognitive Networking↗
DOE OSTI2024

Towards intelligent emergency control for large-scale power systems: Convergence of learning, physics, computing and control

Here, this paper has delved into the pressing need for intelligent emergency control in large-scale power systems, which are experiencing significant transformations and are operating closer to their limits with more uncertainties. Learning-based control methods are promising and have shown effectiveness for intelligent power system control. However, when they are applied to large-scale power systems, there are multifaceted challenges such as scalability, adaptiveness, and security posed by the complex power system landscape, which demand comprehensive solutions. The paper first proposes and instantiates a convergence framework for integrating power systems physics, machine learning, advanced computing, and grid control to realize intelligent grid control at a large scale. Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56 000 scenarios. Our work achieved a 26% reduction in load shedding on average and outperformed existing rule-based control in 99.7% of the test scenarios. The results demonstrated the potential of the proposed convergence framework and DRL-based intelligent control for the future grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2022

Towards the Development of a Multi-Agent Cognitive Networking System for the Lunar Environment

This paper details the development of a multi-agent cognitive system intended to optimize networking performance in the lunar environment. One concept of the future of lunar communication, LunaNet, outlines a complex network of networks. Challenges such as scalability, interoperability, and reliability must first be addressed to successfully fulfill this vision. Machine intelligence can greatly reduce the reliance on human operators and enable efficient operations for tasks such as scheduling and network management. Machine learning, artificial intelligence, and other automated decision-making techniques can be used to allow network nodes to intelligently sense and adapt to changes in the environment such as link disruptions, new nodes joining the network, and support for a diverse range of protocols. Cognitive networking seeks to evolve these technologies into an autonomous system with improved science data return, reliability, and scalability. In this paper, we study four main areas as a means to further develop cognitive networking capabilities: networking protocol development, analysis of wireless data for modeling and simulation, development of algorithms for a multi-agent system, and spectrum sensing technology.

cognitive networking↗
DOE OSTI2025

Foveal vision reduces neural resources in agent-based game learning

Efficient processing of information is crucial for the optimization of neural resources in both biological and artificial visual systems. In this paper, we study the efficiency that may be obtained via the use of a fovea. Using biologically-motivated agents, we study visual information processing, learning, and decision making in a controlled artificial environment, namely the Atari Pong video game. We compare the resources necessary to play Pong between agents with and without a fovea. Our study shows that a fovea can significantly reduce the neural resources, in the form of number of neurons, number of synapses, and number of computations, while at the same time maintaining performance at playing Pong. To our knowledge, this is the first study in which an agent must simultaneously optimize its visual system, along with its decision making and action generation capabilities. That is, the visual system is integral to a complete agent.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗
DOE OSTI2022

Investigating uncertainties in human adaptation and their impacts on water scarcity in the Colorado river Basin, United States

The Colorado River Basin (CRB) supports the water supply for seven states and forty million people in the Western United States (US) and has been suffering an extensive drought for more than two decades. As climate change continues to reshape water resources distribution in the CRB, its impact can differ in intensity and location, resulting in variations in human adaptation behaviors. The feedback from human systems in response to the environmental changes and the associated uncertainty is critical to water resources management, especially for water-stressed basins. This paper investigates how human adaptation affects water scarcity uncertainty in the CRB and highlights the uncertainties in human behavior modeling. Our focus is on agricultural water consumption, as approximately 80% of the water consumption in the CRB is used in agriculture. We adopted a coupled agent-based and water resources modeling approach for exploring human-water system dynamics, in which an agent is a human behavior model that simulates a farmer’s water consumption decisions. We examined uncertainties at the system, agent, and parameter levels through uncertainty, clustering, and sensitivity analyses. The uncertainty analysis results suggest that the CRB water system may experience 13 to 30 years of water shortage during the 2019–2060 simulation period, depending on the paths of farmers’ adaptation. The clustering analysis identified three decision-making classes: bold, prudent, and forward-looking, and quantified the probabilities of an agent belonging to each class. The sensitivity analysis results indicated agents whose decision-making models require further investigation and the parameters with the higher uncertainty reduction potentials. Here, by conducting numerical experiments with the coupled model, this paper presents quantitative and qualitative information about farmers’ adaptation, water scarcity uncertainties, and future research directions for improving human behavior modeling.

Agent-based modeling↗
DOE OSTI2023

Variational actor-critic algorithms,

We introduce a class of variational actor-critic algorithms based on a variational formulation over both the value function and the policy. The objective function of the variational formulation consists of two parts: one for maximizing the value function and the other for minimizing the Bellman residual. Besides the vanilla gradient descent with both the value function and the policy updates, we propose two variants, the clipping method and the flipping method, in order to speed up the convergence. We also prove that, when the prefactor of the Bellman residual is sufficiently large, the fixed point of the algorithm is close to the optimal policy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Multi-scale planning model for robust urban drought response

Increasingly severe droughts are straining municipal water resources and jeopardizing urban water security, but uncertainty in their duration, frequency, and intensity challenges drought planning and response. We develop the Drought Resilient Interscale Portfolio Planning model (DRIPP) to generate optimal planning responses to urban drought. DRIPP is a generalizable multi-scale framework for optimizing dynamic planning strategies of long-term infrastructure deployment and short-term drought response. It integrates climate and hydrological variability with high-fidelity representations of urban water distribution, available technology options, and demand reduction measures to yield robust and cost-effective water supply portfolios that are location-specific. We apply DRIPP in Santa Barbara, California to assess how least cost water supply portfolios vary under different drought scenarios and identify portfolios that are robust across drought scenarios. In Santa Barbara, we find that drought intensity, not duration or frequency, drives cost increases, reliability risk, and regret of overbuilding infrastructure. Under uncertain drought conditions, a diversified technology portfolio that includes both rapidly deployable, decentralized technologies alongside larger centralized technologies minimizes water supply cost while maintaining high robustness to climate uncertainty.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Double Deep Q-Networks for Optimizing Electricity Cost of a Water Heater

Electric water heaters represent 14% of the electricity consumption in the residential buildings and the cost associated with domestic water heating account for a good portion of the household expenses in the United States. In this context, intelligent control of water heaters gained a lot of research attention. In recent years, a significant number of intelligent water heater controllers, with various methods and intended uses, have been proposed. However, existing studies are mostly model-based approaches that require an accurate modelling of the water heater. Towards addressing this research gap, this paper presents a model-free reinforcement learning-based controller for a day-ahead price market. The controller aims to minimize the cost of domestic water heating while maintaining the user comfort. The results showed that the developed controller can help save energy cost while maintaining the temperatures within the desired comfort band.

Amasyali, Kadir↗
DOE OSTI2025

Agentic AI and the Cyber Arms Race

Here, in this article, we examine the implications for cyberwarfare and global politics as agentic artificial intelligence becomes more powerful and enables the broad proliferation of capabilities only available to the most well-resourced actors today.

Cybersecurity↗
DOE OSTI2020

The Heuristic Dynamic Programming Approach in Boost Converters

In this study, a heuristic dynamic programming controller is proposed to control a boost converter. Conventional controllers such as proportional-integral-derivative (PID) or proportional-integral (PI) are designed based on the linearized small-signal model near the operating point. Therefore, the performance of the controller during the start-up, the load change, or the input voltage variation is not optimal since the system model changes by varying the operating point. The heuristic dynamic programming controller optimally controls the boost converter by following the approximate dynamic programming. The advantage of the HDP is that the neural network-based characteristic of the proposed controller enables boost converters to easily cope with large disturbances. An HDP with a well-trained critic and action networks can perform as an optimal controller for the boost converter. To compare the effectiveness of the traditional PI-based and the HDP boost converter, the simulation results are provided.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Decision-making based on Markov decision process in integrated artificial reasoning framework—Part I: Theory

This paper presents a decision-making framework based on an integrated artificial reasoning framework and Markov decision process (MDP). The integrated artificial reasoning framework provides a physics-based approach that converts system information into state transition models, and the analysis result will be represented by the transition probabilities that can be used with an MDP to find a traceable and explainable optimal pathway. A dynamic Bayesian network (DBN) is well suited for representing the structure of an MDP. The causality information among process variables (or among subsystems) is mathematically represented in a DBN by the conditional probabilities of the node’s states provided different probabilities of the parent node’s states. To define node states in a physically understandable manner, we used multilevel flow modeling (MFM). An MFM follows the fundamental energy and mass conservation laws and supports the selection of process variables that represent the system of interest so that causal relations among process variables are properly captured. An MFM-based DBN supports developing state transition models in an MDP to capture the effect of process variables of system having physical relations. The operators of the target system can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from component degradation or random failures. We analyzed a simplified exemplary system to illustrate an optimal operational policy using the suggested approach.

Markov decision process↗