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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Distributed deep reinforcement learning for simulation control

Abstract Several applications in the scientific simulation of physical systems can be formulated as control/optimization problems. The computational models for such systems generally contain hyperparameters, which control solution fidelity and computational expense. The tuning of these parameters is non-trivial and the general approach is to manually ‘spot-check’ for good combinations. This is because optimal hyperparameter configuration search becomes intractable when the parameter space is large and when they may vary dynamically. To address this issue, we present a framework based on deep reinforcement learning (RL) to train a deep neural network agent that controls a model solve by varying parameters dynamically. First, we validate our RL framework for the problem of controlling chaos in chaotic systems by dynamically changing the parameters of the system. Subsequently, we illustrate the capabilities of our framework for accelerating the convergence of a steady-state computational fluid dynamics solver by automatically adjusting the relaxation factors of the discretized Navier–Stokes equations during run-time. The results indicate that the run-time control of the relaxation factors by the learned policy leads to a significant reduction in the number of iterations for convergence compared to the random selection of the relaxation factors. Our results point to potential benefits for learning adaptive hyperparameter learning strategies across different geometries and boundary conditions with implications for reduced computational campaign expenses 4 4 Data and codes available at https://github.com/Romit-Maulik/PAR-RL . .

42 ENGINEERING↗
DOE OSTI2020

RL-HEMS: Reinforcement Learning Based Home Energy Management System for HVAC Energy Optimization

Heating, ventilation, and air conditioning (HVAC) is one of the major energy consumers in the residential sector. It is important to be able to monitor and control the energy consumed to provide utility services such as load shaping while satisfying the comfort and economic constraints of the homeowner. The objective of this work is to create the optimal schedule for HVAC operation to reduce the cost while satisfying the home-owner and equipment’s constraints using a model-free Reinforcement Learning (RL)-based optimization. The specific goal is to find the right balance between reducing energy cost, consumption, and customer comfort level. Our research effort addresses this optimization problem using multiple components: the development of initial learning test-bed and implementation of RL techniques on a real home. This will enable the rapid evaluation of the RL techniques and provide an early baseline to train before implementation on site. The RL algorithm is designed to learn the energy use patterns and generate the optimized schedule for HVAC within an acceptable time-interval to satisfy the homeowner’s comfort and minimize the energy usage. Our preliminary results are promising and we have observed a 17% reduction in the total cost and a 15% reduction in the power utilization using our RL-based HVAC model—RL-HEMS.

Kotevska, Olivera↗
DOE OSTI2020

RLScheduler: An Automated HPC Batch Job Scheduler Using Reinforcement Learning

Today’s high-performance computing (HPC) platforms are still dominated by batch jobs. Accordingly, effective batch job scheduling is crucial to obtain high system efficiency. Existing HPC batch job schedulers typically leverage heuristic priority functions to prioritize and schedule jobs. But, once configured and deployed by the experts, such priority functions can hardly adapt to the changes of job loads, optimization goals, or system settings, potentially leading to degraded system efficiency when changes occur. To address this fundamental issue, we present RLScheduler, an automated HPC batch job scheduler built on reinforcement learning. RLScheduler relies on minimal manual interventions or expert knowledge, but can learn high-quality scheduling policies via its own continuous ‘trial and error’. We introduce a new kernel-based neural network structure and trajectory filtering mechanism in RLScheduler to improve and stabilize the learning process. Through extensive evaluations, we confirm that RLScheduler can learn high-quality scheduling policies towards various workloads and various optimization goals with relatively low computation cost. Moreover, we show that the learned models perform stably even when applied to unseen workloads, making them practical for production use.

Zhang, Di↗
DOE OSTI2020

Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system’s resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in cyber-physical systems (CPS) with complex dynamics, vulnerabilities, and operational uncertainties. In this paper, we develop an automated, domain-aware approach to adversary emulation for CPS. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph with cyber (discrete) and physical (continuous) components and related physical dynamics. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion. As a baseline, we also develop a greedy attack algorithm and compare it with the RL procedures. We summarize our findings through a numerical study on sensor deception attacks in buildings to compare the performance and solution quality of the proposed algorithms.

Bhattacharya, Arnab↗
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 OSTI2025

Incentivizing Cooperative Merging Control: Insights from Multi-Agent Deep Reinforcement Learning

Cooperative driving automation enables connected and automated vehicles (CAVs) to devise cooperative merging control, introducing great potentials to alleviate traffic congestion, reduce energy consumption, and enhance safety for highway on-ramp operations. Although numerous CAV cooperative merging algorithms have been developed to improve energy and traffic performance, the agreement-seeking among CAV users and their local benefits have been understudied. This can lead to rejections of cooperative merging plans and jeopardizing CAV performance, as a cooperation may entail certain CAVs to sacrifice their local benefits to achieve a system optimum. To address this issue, the study first leverages multi-agent deep reinforcement learning (MADRL) factoring both local reward and regional reward to demonstrate the discrepancies between CAV users’ local benefits and system optimum. Next, the existence of a correlated equilibrium is proved to characterize the convergence of MADRL training. This further facilitates the incorporation of incentives (computed based on reward discrepancies) to compensate for CAV users’ local benefits and facilitate system-optimal agreements in cooperative merging operations.

Zhou, Anye [ORNL] (ORCID:0000000301455579)↗
DOE OSTI2025

Deep Reinforcement Learning Based Control of Wind Turbines for Fast Frequency Response

In order to fulfill vital auxiliary grid services, such as load regulation, spin and non-spin reserve provision, and frequency support during emergencies, there is often a requirement for certain wind farms to operate in de-loaded modes. Leveraging the swift response capabilities of wind farms, this study demonstrates that reserving power in de-loaded modes can significantly enhance power grid stability and reliability during system contingencies. Controlling wind farms optimally for frequency support is intricate due to the nonlinearity of models and controllers and the complexity of wind farm interactions with power systems. Here, to address this challenge, this paper introduces a novel approach that integrates wind turbines into reinforcement learning-based solutions for frequency response. This innovative methodology utilizes the state-of-the-art reinforcement learning algorithm known as the surrogate-gradient-based evolutionary strategy. The proposed learning-based algorithm provides continuous control of wind farm output to rapidly stabilize system frequency and prevent unnecessary trips of under-frequency load shedding relays. To facilitate efficient training, parallel computing techniques are employed. The proposed methodology is evaluated on a modified IEEE-39 bus system, and simulation results reveal its efficacy in reliably supporting power system frequency and preventing the need for unnecessary load shedding.

Gao, Wei [Argonne National Laboratory (ANL), Argon↗
DOE OSTI2021

Autonomous reinforcement learning agents for improving predictions and observations of extreme climate events

Primary Focus Area: This proposal addresses focus area 2, “Predictive modeling through the use of AI techniques.” Science Challenge: Extreme climate events associated with severe weather, coastal and inland flooding, droughts, heat waves and wildfires are expected to increase in frequency and severity in the future. Due to the complexity and chaotic behavior of the climate system, accurately predicting and observing extreme climate events requires a tremendous amount of human intervention to run predictive climate simulations and deploy measurement systems. Extreme events often unfold very quickly, leaving little time to iterate on simulations or re-position instruments. Through reinforcement learning, autonomous AI agents can be designed to make real-time decisions to characterize extreme climate events more efficiently through adaptive models and targeted observations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Improving Primary Frequency Response in Networked Microgrid Operations using Multilayer Perceptron-Driven Reinforcement Learning

Individual microgrids can improve the reliability of power grids during extreme events, and networked microgrids can further improve efficiency through resource sharing and increase the resilience of critical end-use loads. However, networked microgrid operations are subject to large switching transients, which can cause dynamic instability and lead to system collapse. These transients are especially prevalent in microgrids with high penetrations of inverter-connected renewable energy resources, which do not provide the system inertia needed to mitigate the transients. Existing generator controls can be modified to invoke a drop in terminal voltage in response to a frequency deviation, thereby reducing load and improving frequency response. This paper investigates the use of a reinforcement-learning--based controller trained over several switching transient scenarios to modify generator controls during large frequency deviations. Compared to previously used proportional integral controllers, the proposed controller can improve primary frequency response while adapting to changes in system topologies and events.

Radhakrishnan, Nikitha↗
DOE OSTI2023

Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks

With the increasing penetration of distributed energy resources in distribution networks, Volt-VAR control and optimization (VVC/VVO) have become very important to ensure an acceptable quality of service to all customers. System operators can rely on slow-responding utility devices, including capacitor banks and on-load tap changing transformers, along with fast-responding battery and photovoltaic (PV) inverters for the VVC/VVO implementation. Because of variations in response time of these two classes of devices, and different control actions (discrete versus continuous), coordinated and optimal scheduling and operation have become of utmost importance. Here, this paper develops a look-ahead deep reinforcement learning (DRL)-based multi-objective VVO technique to improve the voltage profile of active distribution networks, decrease network and inverter power loss, and save the operational cost of the grid. It proposes a deep deterministic policy gradient (DDPG)-based approach to schedule the optimal reactive and/or active power set-points of fast-responding inverters, and a deep Q-network (DQN)-based DRL agent to schedule the discrete decisions variables of slow-responding assets. The reactive power output of PV and battery smart inverters are scheduled at 30-minute intervals and the capacitors’ commitment status is scheduled with several hour intervals. The proposed framework is validated on the modified IEEE 34-bus and 123-bus test cases with embedded PV and PV-plus-storage. To validate the efficacy of the proposed VVO, it is compared with several scenarios, including the base case without VVO, localized droop control of DERs, DDPG-only, and twin delayed DDPG (TD3) agent-based DRL techniques. The results justify the superior performance of the proposed method to improve the voltage profile, reduce network power loss, and minimize the look-ahead grid operational cost while minimizing the undesirable power losses in inverters as a result of power factor adjustments.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2021

Scheduling the NASA Deep Space Network with Deep Reinforcement Learning

With three complexes spread evenly across the Earth, NASA’s Deep Space Network (DSN) is the primary means of communications as well as a significant scientific instrument for dozens of active missions around the world. A rapidly rising number of spacecraft and increasingly complex scientific instruments with higher bandwidth requirements have resulted in demand that exceeds the network’s capacity across its 12 antennae. The existing DSN scheduling process operates on a rolling weekly basis and is time-consuming; for a given week, generation of the final baseline schedule of spacecraft tracking passes takes roughly 5 months from the initial requirements submission deadline, with several weeks of peer-to-peer negotiations in between. This paper proposes a deep reinforcement learning (RL) approach to generate candidate DSN schedules from mission requests and spacecraft ephemeris data with demonstrated capability to address real-world operational constraints. A deep RL agent is developed that takes mission requests for a given week as input, and interacts with a DSN scheduling environment to allocate tracks such that its reward signal is maximized. A comparison is made between an agent trained using Proximal Policy Optimization and its random, untrained counterpart. The results represent a proof-of-concept that, given a well-shaped reward signal, a deep RL agent can learn the complex heuristics used by experts to schedule the DSN. A trained agent can potentially be used to generate candidate schedules to bootstrap the scheduling process and thus reduce the turnaround cycle for DSN scheduling.

Wilson, Brian↗
DOE OSTI2019

In Situ Quality Monitoring in AM Using Acoustic Emission: A Reinforcement Learning Approach

Additive manufacturing (AM) has attracted considerable attention in recent years. This technology overcomes the geometrical limits of workpieces produced with the traditional subtractive methods and so gives the opportunity to manufacture highly complex shapes. Unfortunately, the repeatability of the manufacturing process and the monitoring of quality are not reliable enough to be utilized in mass production. The quality monitoring of AM processes in commercial equipment has been largely based on temperature measurements of the process zone or high-resolution imaging of the layers. However, both techniques lack information about the physical phenomena taking place in the depth of the materials medium and this limits their reliability in real-life applications. To overcome those restrictions, we propose to combine acoustic emission and reinforcement learning. The former captures the information about the subsurface dynamics of the process. The latter is a branch of machine learning that allows interpreting the received data in terms of quality. The combination of both is an original method for in situ and real-time quality monitoring. Acoustic data were collected during a real process using a commercial AM machine. The process parameters were selected to achieve three levels of quality in terms of porosity concentration while manufacturing a stainless steel 316L cuboid shape. Using our method, we demonstrated that each level of quality produced unique acoustic signatures during the build that were recognized by the classifier. The classification accuracy reached in this work proves that the proposed method has high potential to be used as in situ and real-time monitoring of AM quality.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

PWR loading pattern optimization with reinforcement learning

The core loading pattern optimization problem belongs to the class of combinatorial optimization problem and has been studied since the dawn of commercial nuclear energy industry. It is characterized by multiple objectives and constraints, with a very high number of candidate patterns, which makes it impossible to solve explicitly. Stochastic optimization methodologies including Genetic Algorithms and Simulated Annealing are used by different nuclear utilities and vendors to perform fuel cycle reload design. Nevertheless, hand-designed solutions continue to be the prevalent method in the industry. To improve the state-of-the-art core reload patterns, we aim to create a method as scalable as possible, that agrees with the designer's goal of performance and safety. To help in this task Deep Reinforcement Learning (DRL), in particular Proximal Policy Optimization is leveraged. DRL has recently experienced a strong impetus from its successes applied to games, sometimes even reaching 'super-human' performances. This paper lays out the foundation of this method and proposes to study the behavior of several hyper-parameters that influence the DRL algorithm. The algorithm is highly dependent on multiple factors such as an exploration/exploitation trade-off that manifests through different parameters such as the number of loading patterns seen and the number of samples collected before a policy update, but also the shape of the objective function derived for the core design. Experimental results also demonstrate the effectiveness of the method in finding high-quality solutions from scratch within a reasonable amount of time. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2024

Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation

Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic deep learning architectures executed on large datasets. Although such large architectures lead to increased accuracy, this is usually accompanied by a larger increase in computation and memory requirements during inference. While this is a non-issue in traditional machine learning (ML) pipelines, the recent confluence of machine learning and fields like the Internet of Things (IoT) has rendered such large architectures infeasible for execution in low-resource settings. For some datasets, large monolithic pipelines may be overkill for simpler inputs. To address this problem, previous efforts have proposed decision cascades where inputs are passed through models of increasing complexity until the desired performance is achieved. However, we argue that cascaded prediction leads to sub-optimal throughput and increased computational cost due to wasteful intermediate computations. To address this, we propose PaSeR (Parsimonious Segmentation with Reinforcement Learning) a non-cascading, cost-aware learning pipeline as an efficient alternative to cascaded decision architectures. Through experimental evaluation on both real-world and standard datasets, we demonstrate that PaSeR achieves better accuracy while minimizing computational cost relative to cascaded models. Further, we introduce a new metric IoU/GigaFlop to evaluate the balance between cost and performance. On the real-world task of battery material phase segmentation, PaSeR yields 179% improvement over SOTA MatPhase model and a 196% improvement over IDK Cascades under the IoU/GigaFlop metric. We also demonstrate PaSeR’s adaptability to complementary models trained on a noisy MNIST dataset, where it outperforms all baselines on IoU/GigaFlop by an average of 44%.

Srikshan, Bharat↗
NASA NTRSDate not supplied

Joint Communication Resource Allocation and Velocity Selection in Urban Air Mobility via Multi-agent Reinforcement Learning

With traffic congestion problems becoming more severe in urban areas, the National Aeronautics and Space Administration promotes the Urban Air Mobility (UAM) concept, which envisages a safe and efficient air transportation system. However, the increased communication demands in UAM can exacerbate the spectrum scarcity. Therefore, a new communication resource allocation solution is necessary. In this paper, we focus on uplink UAM communications, where multiple aerial vehicles (AV) perform cargo/passenger delivery tasks. With predefined flight paths, AVs make decisions on communication resource allocation and velocity selection to complete their missions under safety constraints. Accordingly, we formulate a joint optimization problem to minimize the weighted sum of the total travel time and communication outage time. We first model the optimization problem as a Markov game and propose a multi-agent reinforcement learning based solution. Simulation results corroborate the effectiveness of the proposed solution.

Ruixuan Han↗
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.↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learning↗