Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Deep Learning Explicit Differentiable Predictive Control Laws for Buildings

We present a differentiable predictive control (DPC) methodology for learning constrained control laws for unknown nonlinear systems. DPC poses an approximate solution to multiparametric programming problems emerging from explicit nonlinear model predictive control (MPC). Contrary to approximate MPC, DPC does not require supervision by an expert controller. Instead, a system dynamics model is learned from a small dataset of recorded observations of the perturbed system's dynamics and the control law is optimized offline by interaction with the learned system model. The DPC method is based on two sequential steps, i) system identification using a constrained neural state-space model, and ii) optimization of an explicit control law parametrized by another neural network in closed-loop simulation with the identified neural state-space model. The combination of a differentiable closed-loop system and penalty methods for constraint handling of system outputs and inputs allows us to optimize the control law's parameters directly by backpropagating economic MPC loss through the learned system model. By incorporating domain knowledge and leveraging established techniques from optimal control, our method leverages deep neural networks as nonlinear function approximators for system identification and control while avoiding concomitant costs of intractably large datasets, and computationally expensive over-parametrized models. The scalability, data efficiency, and constrained optimal control capability of the proposed DPC method are demonstrated in simulation using a multi-zone building emulator.

Drgona, Jan↗
DOE OSTI2021

Decentralized Voltage Control of Large-Scale Distribution System with PVs Based on MADRL

This paper proposes a model-free decentralized control framework for the voltage regulation of large-scale distribution systems through the coordinated control of PV inverters. This is achieved by developing a novel interaction mechanism between the surrogate model and the centralized training and decentralized execution multiagent deep reinforcement learning framework. Specifically, the sparse Gaussian processes regression method is first utilized to develop the surrogate model of the original distribution system for reward calculation during the training stage, where each agent represents a sub-region in the centralized fashion for coordination strategy learning. After that, the learned control rules are used to inform controllers within each sub-region for real-time decisions with only local measurements. Comparative tests among various methods on the EPRI Ckt5 test system demonstrate the effectiveness of the proposed method.

distribution system↗
DOE OSTI2022

Grid-Interactive Building Control Via Reinforcement Learning

In this work, we present the proposed two-stage reinforcement learning approach for training building controllers to help buildings to participate in DR events. The original conference paper for this research idea can be found at https://www.nrel.gov/docs/fy21osti/78000.pdf.

building control↗
DOE OSTI2020

Electricity Pricing aware Deep Reinforcement Learning based Intelligent HVAC Control

Recently, deep reinforcement learning (DRL) based intelligent control of Heating, Ventilation, and Air Conditioning (HVAC) has gained a lot of attention due to DRL's ability to optimally control HVAC for minimizing operational cost while maintaining resident's comfort. The success of such DRL-based techniques largely depends on the articulation of the problem in terms of states, actions, and reward function. Inclusion of the electricity pricing information in the problem formulation can play an important role in saving the cost of HVAC operation. However, less attention has been given in the literature on formulating well-crafted state features based on electricity pricing. In this work, we propose an approach for training the DRL model with a specific focus on feature engineering based on electricity pricing. During training, we generate random but sufficiently realistic electricity price signals so that the pre-trained DRL model is robust and adaptive to the dynamic and variable electricity prices. The validation results are encouraging and show the potential of ≈12%-15% savings in the one day cost of HVAC operation, proving the usefulness of including electricity pricing related features as state features.

Kurte, Kuldeep↗
DOE OSTI2019

A Supervised Machine Learning Approach to Control Energy Storage Devices

This paper introduces a supervised machine learning approach to predict and schedule the real-time operation mode of the next operation interval for residential PV/Battery systems controlled by mode-based controllers. The performance of the mode-based economic model-predictive control (EMPC) approach is used as the benchmark. The residential load and PV data used in the paper are 1-minute data downloaded from the the Pecan Street Project website. The optimal operation mode for each control interval is first derived from the historical data used as the training set. Then, four machine learning algorithms (i.e. neural network, support vector machine, logistic regression, and random forest algorithms) are applied. We compared the performance of the four algorithms when using different number of features and length of the training sets extracted from different months of the year. Simulation results show that using the machine learning approach can effectively improve the performance of the mode-based control system and reduce the computation effort of local controllers because the training can be completed on a cloud-based Machine Learning engine. Furthermore, the work presented in this paper paves the way for using a shared-learning platform to design controllers of residential PV/storage systems. This may significantly reduce the cost for implementing such systems.

25 ENERGY STORAGE↗
DOE OSTI2024

ReLIC: Full-Scale Realization of Reinforcement Learning for Infrastructure Control

Prior efforts have shown that deep reinforcement learning (DRL) may provide a new method for controlling networked power systems. Though successful, prior approaches have not yet demonstrated their behavior on systems of realistic scale. This effort examined multiple theoretical and technical approaches to allow a DRL model to operate over a system of 2,000 buses or more. We find that allowing the DRL models to run training episodes in parallel provides near limitless efficiency gains, allowing us to train successful agents to behave on our Kuramoto transmission model of up to 4,000 buses. We further show that we can expand our PowerWorld DRL implementation to systems of up to 25 buses but struggle to go beyond this limit due to PowerWorld’s inability to run multiple instances at once. Finally, we examine a multi-agent approach and find that it performs as well if not better than our existing centralized approach.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Telerobotic control of a mobile coordinated robotic server, executive summary

This interim report continues with the research effort on advanced adaptive controls for space robotics systems. In particular, previous results developed by the principle investigator and his research team centered around fuzzy logic control (FLC) in which the lack of knowledge of the robotic system as well as the uncertainties of the environment are compensated for by a rule base structure which interacts with varying degrees of belief of control action using system measurements. An on-line adaptive algorithm was developed using a single parameter tuning scheme. In the effort presented, the methodology is further developed to include on-line scaling factor tuning and self-learning control as well as extended to the multi-input, multi-output (MIMO) case. Classical fuzzy logic control requires tuning input scale factors off-line through trial and error techniques. This is time-consuming and cannot adapt to new changes in the process. The new adaptive FLC includes a self-tuning scheme for choosing the scaling factors on-line. Further the rule base in classical FLC is usually produced by soliciting knowledge from human operators as to what is good control action for given circumstances. This usually requires full knowledge and experience of the process and operating conditions, which limits applicability. A self-learning scheme is developed which adaptively forms the rule base with very limited knowledge of the process. Finally, a MIMO method is presented employing optimization techniques. This is required for application to space robotics in which several degrees-of-freedom links are commonly used. Simulation examples are presented for terminal control - typical of robotic problems in which a desired terminal point is to be reached for each link. Future activities will be to implement the MIMO adaptive FLC on an INTEL microcontroller-based circuit and to test the algorithm on a robotic system at the Mars Mission Research Center at North Carolina State University.

Lee, Gordon↗
NASA NTRS1994

Refining fuzzy logic controllers with machine learning

In this paper, we describe the GARIC (Generalized Approximate Reasoning-Based Intelligent Control) architecture, which learns from its past performance and modifies the labels in the fuzzy rules to improve performance. It uses fuzzy reinforcement learning which is a hybrid method of fuzzy logic and reinforcement learning. This technology can simplify and automate the application of fuzzy logic control to a variety of systems. GARIC has been applied in simulation studies of the Space Shuttle rendezvous and docking experiments. It has the potential of being applied in other aerospace systems as well as in consumer products such as appliances, cameras, and cars.

Berenji, Hamid R.↗
DOE OSTI2025

Topology-Aware Reinforcement Learning for Voltage Control: Centralized and Decentralized Strategies

Volt-VAR control (VVC) methods based on deep reinforcement learning (DRL) can effectively control distribution grid voltage and minimize power loss by implementing corrective and preventive control measures on the reactive power output of inverter-based distributed energy resources (DERs). However, model-free DRL-based VVC approaches usually cannot capture the important topological feature of the power system since they use a fully-connected network (FCN) to deliver the action. Therefore, this paper proposes a graph convolutional network (GCN)-based DRL approach that can employ the topological information of the network to take better control action for regulating the voltage. Our implementation allows for both centralized and decentralized configurations, utilizing a single agent and multiple agents respectively. Although the centralized GCN-based DRL approach has its advantages of minimizing voltage fluctuation and power loss, it is not suitable for large scale power systems due to its challenges in terms of scalability, computation speed and potential single points of failure. Therefore, these problems can be resolved using the decentralized GCN-based DRL approach. Moreover, to ensure the safe operation of the model, our proposed approach incorporates an exponential barrier function while formulating the reward function for each agent. To validate performance of the proposed approaches, the proposed model is tested on modified IEEE test systems and the performances are measured in terms on voltage fluctuation reduction, minimization of power loss and computational speed. Finally, the results show that the proposed topology-aware approach outperforms the FCN-based DRL approach in terms of reducing voltage fluctuation and minimizing power loss of the network. Moreover, it is shown that the decentralized GCN-based DRL has faster computational speed than other approaches.

42 ENGINEERING↗
DOE OSTI2021

Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search

In this paper, we develop a grid-interactive multi-zone building controller based on a deep reinforcement learning (RL) approach. The controller is designed to facilitate building operation during normal conditions and demand response events, while ensuring occupants comfort and energy efficiency. We leverage a continuous action space RL formulation, and devise a two-stage global-local RL training framework. In the first stage, a global fast policy search is performed using a gradient-free RL algorithm. In the second stage, a local fine-tuning is conducted using a policy gradient method. In contrast to the state-of-the-art model predictive control (MPC) approach, the proposed RL controller does not require complex computation during real-time operation and can adapt to nonlinear building models. We illustrate the controller performance numerically using a five-zone commercial building.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2026

Data-Driven Voltage Regulation of Distribution Grid Using Nonlinear Autoregressive Model with Exogenous Inputs (NARX)

This article proposes data-driven control via a nonlinear autoregressive model with exogenous inputs (NARX) for real-time voltage regulation of a modified feeder using reactive power sources. Traditional voltage control strategies rely on rule-based heuristics or optimization techniques, which often require detailed system models and extensive computational resources. The NARX-based controller learns system dynamics from historical data and predicts optimal reactive power dispatch in real-time for voltage correction. The proposed approach is evaluated on a power system feeder model under varying load and network conditions. Simulation results demonstrate that the NARX-based controller achieves improved voltage regulation, offering higher adaptability to system fluctuations. This study highlights the potential of data-driven control for enhancing the reliability of power distribution networks.

Donge, Vrushabh [ORNL] (ORCID:0000000306062803)↗
NASA NTRS1994

Multiresolutional schemata for unsupervised learning of autonomous robots for 3D space operation

This paper describes a novel approach to the development of a learning control system for autonomous space robot (ASR) which presents the ASR as a 'baby' -- that is, a system with no a priori knowledge of the world in which it operates, but with behavior acquisition techniques that allows it to build this knowledge from the experiences of actions within a particular environment (we will call it an Astro-baby). The learning techniques are rooted in the recursive algorithm for inductive generation of nested schemata molded from processes of early cognitive development in humans. The algorithm extracts data from the environment and by means of correlation and abduction, it creates schemata that are used for control. This system is robust enough to deal with a constantly changing environment because such changes provoke the creation of new schemata by generalizing from experiences, while still maintaining minimal computational complexity, thanks to the system's multiresolutional nature.

Lacaze, Alberto↗
DOE OSTI2026

CTRL-STEER: Closed-Loop Neuron Activation Control in Vision-Language-Action Models

Vision-Language-Action (VLA) models enable test-time behavioral steering via neuron-level interventions, but existing methods use fixed strengths and operate in open loop. This static modulation fails under evolving task dynamics, leading to overcorrection, oscillations, and reduced task success—especially for temporal attributes like speed. We propose CTRL-STEER, a control-theoretic framework that casts activation steering as closed-loop feedback with adaptive, time-varying interventions. Instead of assuming neurons encode temporal concepts, we steer along motion-aligned residual directions and regulate intervention magnitude via feedback. We instantiate this with both PID and reinforcement learning controllers that jointly optimize concept adherence and task success. Experiments on fine-tuned OpenVLA policies across four LIBERO suites show improved stability and a better steering–success trade-off over fixed-coefficient baselines, without retraining the base model.

Babu, Abhijith [Florida International University, ↗
DOE OSTI2021

Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search: Preprint

In this paper, we develop a grid-interactive multi-zone building controller based on a deep reinforcement learning (RL) approach. The controller is designed to facilitate building operation during normal conditions and demand response events, while ensuring occupants comfort and energy efficiency. We leverage a continuous action space RL formulation, and devise a two-stage global-local RL training framework. In the first stage, a global fast policy search is performed using a gradient-free RL algorithm. In the second stage, a local fine-tuning is conducted using a policy gradient method. In contrast to the state-of-the-art model predictive control (MPC) approach, the proposed RL controller does not require complex computation during real-time operation and can adapt to non-linear building models. We illustrate the controller performance numerically using a five-zone commercial building.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

CityLearn v2: energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities

As more distributed energy resources become part of the demand-side infrastructure, quantifying their energy flexibility on a community scale is crucial. CityLearn v1 provided an environment for benchmarking control algorithms. However, there is no standardized environment utilizing realistic building-stock datasets for distributed energy resource control benchmarking without co-simulation or third-party frameworks. CityLearn v2 extends CityLearn v1 by providing a stand-alone simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create grid-interactive communities for resilient, multi-agent, and objective control of distributed energy resources with dynamic occupant feedback. While the v1 environment used pre-simulated building thermal loads, the v2 environment uses data-driven thermal dynamics and eliminates the need for co-simulation with building energy performance software. This work details the v2 environment and provides application examples that use reinforcement learning control to manage battery energy storage system, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

Nweye, Kingsley↗
DOE OSTI2021

Virtual Diagnostic Suite for Electron Beam Prediction and Control at FACET-II

We discuss the implementation of a suite of virtual diagnostics at the FACET-II facility currently under commissioning at SLAC National Accelerator Laboratory. The diagnostics will be used for the prediction of the longitudinal phase space along the linac, spectral reconstruction of the bunch profile, and non-destructive inference of transverse beam quality (emittance) while using edge radiation at the injector dogleg and bunch compressor locations. These measurements will be folded into adaptive feedbacks and Machine Learning (ML)-based reinforcement learning controls to improve the stability and optimize the performance of the machine for different experimental configurations. In this paper we describe each of these diagnostics with expected measurement results that are based on simulation data and discuss progress towards implementation in regular operations.

Emma, Claudio (ORCID:0000000247191831)↗