Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep 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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Cyber-Physical Power Systems Protection: The Byzantine Cybersecurity Framework

Cybersecurity of smart grids have been topic of much interest in recent years. As this critical infrastructure operation increases dependency on automated processes and controls, exposure to cyber-physical threats become inevitable. Considering cyber-physical security of the grid, much focus of attention has been made towards smart grids real-time monitoring solutions, including the state estimation process. Analyzing the relevant literature, one can note though that seldom research has been done on cyber-physical security of smart grids protection systems. Protection systems have intangible value towards grid reliability. This paper presents a cybersecurity framework for smart grids protection systems. A physics-based inspired machine learning solution is at the core process of the framework. Processed relay inputs and outputs are used by a deep predictive coding network. Formal models, a quasi-static state estimator, provides an oracle when low confidence decision is reached. Evolving knowledge is derived through reinforcement learning. Implementation aspects considering the Pacific Northwest National Laboratory Electricity Infrastructure Operations Center are presented. Built as an extra control layer to protection systems, without hard-to-derive parameters, highlights potential aspects towards real-life applications.

Bretas, Arturo Suman↗
DOE OSTI2026

Decentralised Reinforcement Learning for Dynamic Cyberattack Response in Microgrid Networks

Microgrids rely on communication networks for reliable operation, which makes them inherently vulnerable to cyberattacks. Such attacks can destabilise system dynamics and drive states away from their nominal operating trajectories. Although several physics-informed and machine learning-based strategies have been developed to counter these threats, the rapidly evolving cyber landscape enables adversaries to bypass static defences or rules-based mitigation approaches. This paper proposes a dynamic, online-trained and fully decentralised reinforcement learning (RL)-based cyberattack response framework to protect microgrids from evolving cyberattacks. The proposed framework deploys multiple deep Q-networks (DQNs), each associated with a distributed energy resource (DER), to enable localised and adaptive attack mitigation. In this framework, each DQN processes local voltage and frequency measurements—combined with intrusion detection system (IDS) alerts—as observations and rewards to guide decision-making. Extensive simulation studies demonstrate the robustness of the proposed framework under diverse attack scenarios and varying IDS-induced detection delays. Comparative analysis highlights its superiority over existing static or preexisting rules-based mitigation approaches. Finally, we present an analysis that shows the framework's scalability to real-life microgrids with more interacting agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

MARS: Malleable Actor-Critic Reinforcement Learning Scheduler

In this paper, we introduce MARS, a new scheduling system for HPC-cloud infrastructures based on a cost-aware, flexible reinforcement learning approach, which serves as an intermediate layer for next generation HPC-cloud resource manager. MARS ensembles the pre-trained models from heuristic workloads and decides on the most cost-effective strategy for optimization. A whole workflow application would be split into several optimizable dependent sub-tasks, then based on the pre- defined resource management plan, a reward will be generated after executing a scheduled task. Lastly, MARS updates the Deep Neural Network (DNN) model based on the reward. MARS is designed to optimize the existing models through reinforcement mechanisms. MARS adapts to the dynamics of workflow applications, selects the most cost-effective scheduling solution among pre-built scheduling strategies (backfilling, SJF, etc.) and self- learning deep neural network model at run-time. We evaluate MARS with different real-world workflow traces. MARS can achieve 5%-60% increased performance compare to state-of-the- art approaches.

Baheri, Betis↗
DOE OSTI2020

Enforcing constraints for time series prediction in supervised, unsupervised and reinforcement learning

We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in order to accelerate the training of deep neural networks to represent the flow map of the system as well as increase their predictive ability. In particular, we provide ways to enforce constraints during training for all three major modes of learning, namely supervised, unsupervised and reinforcement learning. In general, the dynamic constraints need to include terms which are analogous to memory terms in model reduction formalisms. Such memory terms act as a restoring force which corrects the errors committed by the learned flow map during prediction. For supervised learning, the constraints are added to the objective function. For the case of unsupervised learning, in particular generative adversarial networks, the constraints are introduced by augmenting the input of the discriminator. Finally, for the case of reinforcement learning and in particular actor-critic methods, the constraints are added to the reward function. In addition, for the reinforcement learning case, we present a novel approach based on homotopy of the action-value function in order to stabilize and accelerate training. We use numerical results for the Lorenz system to illustrate the various constructions.

Stinis, Panagiotis↗
DOE OSTI2023

Efficient Reinforcement Learning for Real-Time Hardware-Based Energy System Experiments: Preprint

In the context of urgent climate challenges and the pressing need for rapid technology development, Reinforcement Learning (RL) stands as a compelling data-driven method for controlling real-world physical systems. However, RL implementation often entails time-consuming and computationally intensive data collection and training processes, rendering them inefficient for real-time applications that lack non-real-time models. To address these limitations, real-time emulation techniques have emerged as valuable tools for the lab-scale rapid prototyping of intricate energy systems. While emulated systems offer a bridge between simulation and reality, they too face constraints, hindering comprehensive characterization, testing, and development. In this research, we construct a surrogate model using limited data from simulated systems, enabling an efficient and effective training process for a Double Deep Q-Network (DDQN) agent for future deployment. Our approach is illustrated through a hydropower application, demonstrating the practical impact of our approach on climate-related technology development.

deep Q-learning↗
DOE OSTI2025

Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls

Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.

Kasparian, Armen [Thomas Jefferson National Accele↗
NASA NTRS2020

Using Reinforcement Learning to Design Missed Thrust Resilient Trajectories

From ion thrusters to solar sails, spacecraft continue to adopt new and more efficient forms of propulsion. As these low-thrust propulsion meth- ods have become more prevalent, new challenges have arisen. Depending on the mission, low-thrust propulsion elements may need to thrust con- tinuously for days/months. During these thrusting periods, external fac- tors, such as a micro-meteoroid impact or a software glitch, may cause the spacecraft to prematurely cease its thrust stage. Half of all deep space missions enter a safe mode where they cannot thrust every four months. These missed thrust events can result in the complete loss of a space- craft for time-dependent trajectories like planetary rendezvous. This paper demonstrates how neural networks, trained using reinforcement learning, can autonomously correct for missed thrust events during an interplanetary trajectory.

Laipert, Frank E.↗
DOE OSTI2023

Hybrid Attack Graph Generation with Graph Convolutional Deep-Q Learning

Critical infrastructures such as power grids have become increasingly complex, connected, and vulnerable to adverse scenarios, including cyber and physical attacks and faults. Effective risk mitigation for such cyber-physical energy systems (CPES), requires preemptive knowledge of likely adversarial attack scenarios. Hybrid Attack Graph (HAG) is a structured way to represent an adversarial scenario as an attack sequence using a threat model. However, the scarcity of documented attack sequences hinders analysts and CPES planners’ ability to identify credible attack scenarios for a given CPES. We propose a data-driven Graph Convolutional Deep-Q Network (GCDQ) to address this data challenge through generating HAGs. By leveraging limited real-world observations from the MITRE ATT&CK knowledge base, our GCDQ model synthesizes realistic graphs with the targeted attribute of minimum detectability via reinforcement learning. This generative model is the first step in creating a tool to substantially boost the attack sequence dataset and enhance the performance of CPS defense-related tasks by providing insights into likely attack sequences with given attributes.

deep learning, artificial intelligence↗
DOE OSTI2021

Comparative analysis of model-free and model-based HVAC control for residential demand response

In this paper, we present a comparative analysis of model-free reinforcement learning (RL) and model predictive control (MPC) approaches for intelligent control of heating, ventilation, and air-conditioning (HVAC). Deep-Q-network (DQN) is used as a candidate for model-free RL algorithm. The two control strategies were developed for residential demand-response (DR) HVAC system. We considered MPC as our golden standard to compare DQN's performance. The question we tried to answer through this work was, What % of MPC's performance can be achieved by model-free RL approach for intelligent HVAC control?. Based on our test result, RL achieved an average of ≈ 62% daily cost saving of MPC. Considering the pure optimization and model-based nature of MPC methods, the RL showed very promising performance. We believe that the interpretations derived from this comparative analysis provide useful insights to choose from various DR approaches and further enhance the performance of the RL-based methods for building energy managements.

Kurte, Kuldeep↗
DOE OSTI2021

Tribal Revegetation Project Final Project Report: 92-Acre Area, Area 5 Radioactive Waste Management Complex, Nevada National Security Site, Nevada

Nuwu (Southern Paiute), Newe (Western Shoshone), and Nuumu (Owens Valley Paiute) are linguistically related, Numic-speaking peoples who are part of the broader Uto-Aztecan language group. Numic peoples view the land as a holistic, living, sentient being with feelings and purpose. The land is personified with human characteristics and it needs to be experienced to be understood through “learning by doing.” Numic peoples do not support ground disturbing activities within their ancestral lands, including activities tied to the storage of low-level radioactive waste or classified materials on the NNSS, which they view as culturally inappropriate. These deep-rooted ancestral connections are the impetus for reinforcing Numic responsibility for healing disturbed areas by integrating respect and patience with consistent Tribal interaction. Tribal Ecological Knowledge (TEK) is the science of describing Tribal approaches for understanding natural resources. Numic TEK is embedded in traditional teachings learned incrementally over time though experience and it evolves through lessons learned and responses to environmental changes over millennia. Therefore, TEK can broaden and enhance Western scientific knowledge associated with revegetation, especially in highly disturbed areas. The project blended TEK with Western scientific ecological methods to create a vegetative cover within test plots on the 92-Acre Area located at the Radioactive Waste Management Complex (RWMC) located in Area 5 on the Nevada National Security Site (NNSS). The vegetated test plots were systematically created for the Department of Energy (DOE) in tandem with the existing Federal Facilities Agreement and Consent Order (FFACO) with the Nevada Department of Environmental Protection (NDEP). Three previous contractor-lead attempts at revegetation, one targeting full cover revegetation and two targeting test plot revegetation, did not achieve the anticipated results at this location. When presented to the 16 American Indian Tribal nations and affiliated groups with cultural and historical ties to the NNSS, the group appointed a Tribal Revegetation Committee (TRC) that included six expert Tribal knowledge holders to collaborate with an ethnoecologist/cultural anthropologist and two biologists. Project design, planning, seed and outplant selection, spiritual land preparation, and methodology were guided by the TRC and an ethnoecologist/cultural anthropologist from Portland State University (PSU) and biologists from Desert Research Institute (DRI). Using TEK, the TRC recommended a specific seed mixture that contained nine native plant species and three species of outplants. The revegetation effort included preparing and planting thirty 10 m × 10 m (32.8 ft × 32.8 ft) seeded plots, twelve of which also included outplants; and eight 10 m × 100 m (32.8 ft × 328 ft) plots that only received outplants, all atop a waste cell cover. The TRC and the project team creatively adapted TEK with Western scientific methods so that the planned revegetation efforts could occur within the safety and security parameters of the RWMC. Test plots were subjected to one of five soil treatments with varying combinations of straw or mulch applications, soil amendment, and/or outplant planting and one of two watering treatments (watered or unwatered). Planting was divided into two events: one in the fall season and another during the subsequent spring season based on TEK and a corresponding recommendation from the TRC. Monitoring and spiritual management was conducted by the TRC to evaluate plant progress on a monthly basis (in conjunction with the biologist and anthropologist) during each respective growing season for a period of three years after planting. This approach allowed Tribal members the opportunity to conduct traditional blessings and other culturally appropriate activities to restore balance to the land in accordance with Tribal protocols. Following TEK-guided methods, successful plant establishment from seed stock and outplants was observed in many plots. Overall, plots planted in the spring, as recommended by the TRC, showed higher rates of outplant survival and native seedling emergence than those planted in the fall. This finding is significant because it is contrary to the original guidance and previous approaches provided for planting in this region. The TRC believes the frequent co-occurrence of native seedlings near surviving outplants indicates an important symbiotic relationship understood by Tribal communities and overlooked by others. Watered outplants displayed much higher survivability than unwatered plants, even after watering was reduced after the plants were established. Soil amendments and mulch created higher densities of native plants from seed. Many native seedlings showed significant delays in germination, which is considered a normal adaptation to desert climates. Some native plants did not germinate until the third growing year, whereas others germinated during the first growing year, which demonstrates the complexity of the desert environment. Evidence of native insects, reptiles, mammals, and birds, as well as native plants that were not part of the planted species, were noted and considered culturally significant. Despite the presence of non-native plants, native outplants continued to thrive and the incidence of native plant germination from seed increased over time. These successful revegetation results where previous efforts were unsuccessful reinforce the importance of integrating regionally appropriate, TEK-guided methodology with Western science to achieve positive results and the necessity of integrating Tribal involvement in all stages of the revegetation effort. Expanded approaches coupled with Tribal knowledge and tools from Western science addressed a complex problem tied to revegetating atop a low-level radioactive waste cell. The level of Tribal participation serves as a progressive model for building collaborative relationships and addressing ecological challenges on the NNSS.

54 ENVIRONMENTAL SCIENCES↗
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 OSTI2021

Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systems

Self-healing capability is a critical factor for a resilient distribution system, which requires intelligent agents to automatically perform service restoration online, including network reconfiguration and reactive power dispatch. Here, the article proposes the imitation learning framework for training such an agent, where the agent will interact with an expert built based on the mixed-integer program to learn its optimal policy, and therefore significantly improve the training efficiency compared with exploration-dominant reinforcement learning (RL) methods. This significantly improved training efficiency makes the training problem under N-k scenarios tractable. A hybrid policy network is proposed to handle tie-line operations and reactive power dispatch simultaneously to further improve the restoration performance. The 33-bus and 119-bus systems with N-k disturbances are employed to conduct the training. The results indicate that the proposed method outperforms traditional RL algorithms such as the deep-Q network.

42 ENGINEERING↗
DOE OSTI2022

Robotic Planning under Uncertainty in Spatiotemporal Environments in Expeditionary Science

In the expeditionary sciences, spatiotemporally varying environments -- hydrothermal plumes, algal blooms, lava flows, or animal migrations -- are ubiquitous. Mobile robots are uniquely well-suited to study these dynamic, mesoscale natural environments. We formalize expeditionary science as a sequential decision-making problem, modeled using the language of partially-observable Markov decision processes (POMDPs). Solving the expeditionary science POMDP under real-world constraints requires efficient probabilistic modeling and decision-making in problems with complex dynamics and observational models. Previous work in informative path planning, adaptive sampling, and experimental design have shown compelling results, largely in static environments, using data-driven models and information-based rewards. However, these methodologies do not trivially extend to expeditionary science in spatiotemporal environments: they generally do not make use of scientific knowledge such as equations of state dynamics, they focus on information gathering as opposed to scientific task execution, and they make use of decision-making approaches that scale poorly to large, continuous problems with long planning horizons and real-time operational constraints. In this work, we discuss these and other challenges related to probabilistic modeling and decision-making in expeditionary science, and present some of our preliminary work that addresses these gaps. We ground our results in a real expeditionary science deployment of an autonomous underwater vehicle (AUV) in the deep ocean for hydrothermal vent discovery and characterization. Our concluding thoughts highlight remaining work to be done, and the challenges that merit consideration by the reinforcement learning and decision-making community.

Preston, Victoria↗
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 OSTI2019

Deep Symbolic Regression

Symbolic regression is the task of finding tractable mathematical expressions that best fit an input dataset. Deep symbolic regression (DSR) searches the space of tractable mathematical expressions by using a recurrent neural network that generates mathematical expressions. The network is trained using reinforcement learning.

Petersen, BrendenK↗
DOE OSTI2023

Bayesian sequential optimal experimental design for nonlinear models using policy gradient reinforcement learning

We present a mathematical framework and computational methods for optimally designing a finite sequence of experiments. This sequential optimal experimental design (sOED) problem is formulated as a finite-horizon partially observable Markov decision process (POMDP) under a Bayesian setting and with information-theoretic utilities. The formulation is general and may accommodate continuous random variables, non-Gaussian posteriors, and nonlinear forward models. The sOED design policy incorporates elements of feedback and lookahead simultaneously, and we show it to generalize the commonly-used batch and greedy design strategies. We solve for the sOED policy using the policy gradient (PG) method from reinforcement learning, and provide a derivation for the PG expression in the sOED context. Adopting an actor-critic approach, the policy and value functions are parameterized using deep neural networks and improved via PG estimates produced from simulated episodes of designs and observations. The new PG-sOED algorithm is first validated on a linear-Gaussian benchmark, and then compared against other design baselines on a sensor movement problem for contaminant source inversion in a convection-diffusion field. As a result, we provide explanation for the policy behaviors using knowledge of the underlying physical process.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Learning-based framework for sensor fault-tolerant building HVAC control with model-assisted learning

As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption. These HVAC systems in smart buildings rely 'on real-time sensor readings, which in practice often suffer from various faults and could also be vulnerable to malicious attacks. Such faulty sensor inputs may lead to the violation of indoor environment requirements (e.g., temperature, humidity, etc.) and the increase of energy consumption. While many model-based approaches have been proposed in the literature for building HVAC control, it is costly to develop accurate physical models for ensuring their performance and even more challenging to address the impact of sensor faults. In this work, we present a novel learning-based framework for sensor fault-tolerant HVAC control, which includes three deep learning based components for 1) generating temperature proposals with the consideration of possible sensor faults, 2) selecting one of the proposals based on the assessment of their accuracy, and 3) applying reinforcement learning with the selected temperature proposal. Moreover, to address the challenge of training data insufficiency in building-related tasks, we propose a model-assisted learning method leveraging an abstract model of building physical dynamics. Through extensive experiments, we demonstrate that the proposed fault-tolerant HVAC control framework can significantly reduce building temperature violations under a variety of sensor fault patterns while maintaining energy efficiency.

Xu, Shichao↗