Search NASA⌕ Search

SEARCH · Search NASA

Results for “Multi-agent 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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

42 ENGINEERING↗
DOE OSTI2024

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

actuated signal control↗
DOE OSTI2024

Self-Aware Local Autonomous and Semi-Cooperative Control for Cross-Layered Resilience (SLAC3R)

The objective of this work is to develop and demonstrate novel, adaptive, lightweight algorithms that enable the decision-making agents in a large cyber-physical network to act both autonomously and in collaborative harmony to enforce assured resilience across spatiotemporal layers, even under unforeseen adversarial scenarios (e.g., high- impact-low-probability events). Towards this end, the proposed solution will serve as minimally invasive add-on layers that bridge the existing (faster, reactive) local myopic controls and (slower, predictive) centralized optimization. Importantly, the proposed algorithms will enable the multi-agent network to autonomously and collaboratively enforce resilient operation under no or limited communication environment typical of severe cyber- physical adversarial events. The expected outcome of this effort is a suite of prototype, open-source, software algorithms for safety-aware local autonomous and semi-cooperative control (SLAC3R), demonstrated on networked microgrids (via RD2C/Thrust-1 OPAL-RT testbed).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Optimization-based approaches to control of connected and automated vehicles: Principles, complexities, applications, challenges, and outlook

Safe and optimal motion control for connected and automated vehicles (CAVs) poses a fundamental optimization challenge at the intersection of system complexity, environmental uncertainty, and stringent real-time constraints. Existing surveys address this challenge in isolation – focusing either on specific control techniques or individual uncertainty sources – without providing a unified framework that characterizes the trade-offs among computational tractability, performance verifiability, and adaptive generalization across paradigms. This review addresses that gap by presenting a cohesive analytical framework concentrated on the decision-making and trajectory optimization layers of the CAV autonomy stack. We systematically analyze three major optimization paradigms – first-principles model-based optimization, data-driven methods, and hybrid synergistic architectures – evaluating each against four core complexity axes: problem formulation, constraint handling, optimality guarantees, and robustness. Key applications including platooning, trajectory planning, collision avoidance, and cooperative control are examined to reveal recurring methodological patterns and critical operational constraints that limit real-world performance. Our synthesis identifies verifiable hybrid architectures, incentive-aligned multi-agent cooperation, and hardware-algorithm co-design as the defining research frontiers, and distills a targeted agenda for developing CAV control systems that are simultaneously safe, computationally efficient, and deployable in the full complexity of real-world traffic environments.

Muzahid, Abu Jafar Md [University of Tennessee, Kn↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
DOE OSTI2023

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

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

Lebakula, Viswadeep↗
DOE OSTI2024

The Transactive Energy Network Template Metamodel

While transactive energy, which is defined as an allocation of electricity based on dynamically discovered values or prices, has been extensively studied, its uptake and use has been slow. This report describes a tool, the transactive network template, which should hasten the creation and uptake of transactive energy networks. Some basic principles of transactive energy are familiar from existing wholesale electricity markets. Locational prices are calculated today for zones within bulk electric transmission systems. Locational prices differ while accounting for the locational costs of electricity generation and the losses and constraints incurred when electricity is transmitted from generators and distributed to consumers. A transactive energy network might include these transmission zones. However, current research strives to apply transactive energy also in electricity distribution circuits, buildings, and even for individual generating and consuming devices. At the same time, researchers explore how to apply transactive energy in real time during increasingly shorter time intervals. Automated computational agents become necessary as transactive energy becomes applied to smaller circuit zones and at faster dynamic timescales. A transactive energy network is an example of a multi-agent system. Each zone in the network is represented by its transactive agent, which makes decisions for and acts on behalf of a business entity that is responsible for and manages one of the circuit regions. A transactive energy network is also an example of a decentralized, distributed control system. Control decisions and responsibilities are distributed among the network’s transactive agents. The transactive agents are independent; that is, there typically is no centralized authority or oversight function. Instead, transactive agents exchange transactive signals and thereby negotiate the prices and quantities of electricity that they will exchange. Initially, the circuit regions and responsibilities of transactive agents appear to be very dissimilar. Each circuit region may comprise transmission, distribution, or building-level circuits. Each has a unique position and electrical connectivity within the transactive energy network. Each possesses unique assets that either generate or consume electricity, and these (e.g., renewable energy generator, diesel generator, aggregate utility load, building load, space conditioning, refrigerator, etc.) may further differ in their price flexibility and in their strategies for responding to dynamic electricity prices. Given such diversity, an implementer’s first inclination might be to start from scratch to define all these devices and to engineer their seemingly unique interactions. Given that each implementer’s perspective may be narrow within a transactive energy network, it is unlikely that uniquely engineered systems would interact well. This is where the transactive network template is applicable. The transactive network template is a metamodel that has been developed to guide implementers as they configure their own transactive agent within a network of such agents. The object-oriented design of the transactive network template provides basic code object types that may be used and extended by implementers to represent each of the assets in their circuit region. These objects further facilitate the transactive agent’s necessary computations, which are divided among responsibilities to schedule power usage, balance electric supply and demand, and coordinate the exchange of electricity with the other transactive agents. This report addresses the conceptual transactive network template design. Implementers are directed to more formal design documents and reference implementations. A Python™-based1 reference implementation of the transactive network template has been coded, and three implementations have been configured to represent a national laboratory and two university campuses. Version 2 of the transactive node template generalizes the market class and its methods to facilitate multiple, and more diverse market coordination mechanisms than were facilitated by and demonstrated using Version 1. Version 3 includes new Appendix B, which addresses the designs of methods that would make dynamic prices track approved electricity rates. In the future, the author wishes to make the transactive network template more generally applicable to networks that require more accurate power flow. Development of the transactive network template is jointly funded by the U.S. Department of Energy (DOE) Energy Efficiency and Renewable Energy and the DOE Office of Electricity. In late 2015, one of the first projects to be funded by the DOE Grid Laboratory Modernization Laboratory Consortium was the Clean Energy and Transactive Campus project, led by Pacific Northwest National Laboratory. DOE funds were matched by an investment by the Washington Department of Commerce through its Clean Energy Fund. The transactive network template was developed to guide the implementation of transactive energy networks within this project’s scope.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Optimizing Traffic Signal Control to Enhance Transportation Efficiency and Maximize Pedestrian Benefits in the Road Network

Increasing urban mobility requirements demand efficient transportation system strategies for both vehicular and pedestrian movement. This study enhances the Decentralized Graph-based Multi-Agent Reinforcement Learning (DGMARL) approach, originally tailored for vehicular traffic signal timing, to incorporate pedestrian traffic dynamics. The improved algorithm considers crucial metrics such as Eco_PI, assesses vehicle fuel consumption by factoring in stops and delays, and addresses pedestrian waiting time, crucial for system efficiency while acknowledging driver waiting time impact. Utilizing Digital Twin simulation along the MLK Smart Corridor in Chattanooga, Tennessee, the algorithm's performance is compared for various pedestrian control scenarios. To evaluate the effectiveness of DGMARL, this study compared DGMARL-enabled signal management with automated pedestrian traffic detection and an actuated signal management system (real-word baseline) with pedestrian recall, which predetermingly enforces a pedestrian phase every cycle. Findings indicate substantial improvements with DGMARL, showing a 28.29% enhancement in vehicle Eco_PI, a 60.55 % reduction in pedestrian waiting time, and a 55.74% decrease in driver stop delay, on average, compared to the baseline actuated signal timing plan.

Kumarasamy, Vijayalakshmi K [The University of Ten↗
DOE OSTI2025

Enabling Real-Time Communication in Multi-Agent Systems: A Graph Neural Network Based Approach

Global connectivity enables effective coordination in Multi-Agent Systems (MAS). Solving these connection problems under hardware constraints is an NP-hard non-Euclidean Degree Constrained Minimum Spanning Tree (DCMST) problem. Prior MAS controllers coordinate team movement for task completion and collision avoidance; some considering Line-of-Sight (LOS) maintenance but prioritizing flexibility over guarantees. Evolutionary Algorithms (EA) have been shown to find good solutions for DCMST, but their performance degrades with larger populations required to support a large MAS. We present a method based on edge graph attention networks, trained offline to reduce online computation times. Empirical comparisons with greedy polynomial-time solvers and EA show that our method leverages latent graph information to consistently find constraint-satisfying solutions in less time.

connectivity maintenance↗
DOE OSTI2023

Multi-Agent Reinforcement Learning for Distribution System Critical Load Restoration: Preprint

Grid resilience has become a critical topic recently because of the increasing occurrence of extreme events and the growing integration of intermittent renewable energy sources. To build a resilient distribution system, this paper develops a multi-agent reinforcement learning-based (MARL) method to coordinate distribution energy resources (DERs) dispatch, load pickup, and network reconfiguration for load restoration after a system outage. With the help of two types of control agents, namely critical load restoration (CLR) and coordination (COR) agents, system loads can be restored efficiently, given available resources. The effectiveness and superiority of the proposed algorithm are demonstrated through simulations and comparative studies on a real distribution feeder in Western Colorado.

distribution system↗
DOE OSTI2023

Multi-Agent Reinforcement Learning for Distribution System Critical Load Restoration

Grid resilience has become a critical topic recently because of the increasing occurrence of extreme events and the growing integration of intermittent renewable energy sources. To build a resilient distribution system, this paper develops a multiagent reinforcement learning-based (MARL) method to coordinate distribution energy resources (DERs) dispatch, load pickup, and network reconfiguration for load restoration after a system outage. With the help of two types of control agents, namely critical load restoration (CLR) and coordination (COR) agents, system loads can be restored efficiently, given available resources. The effectiveness and superiority of the proposed algorithm are demonstrated through simulations and comparative studies on a real distribution feeder in Western Colorado.

distribution system↗
DOE OSTI2023

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

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

Multi-Agent Reinforcement Learning, Digital Twin, ↗
DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗
DOE OSTI2024

Buyers Collusion in Incentivized Forwarding Networks: A Multi-Agent Reinforcement Learning Study

We present the issue of monetarily incentivized forwarding in a multi-hop mesh network architecture from an economic perspective. It is anticipated that credit-incentivized forwarding and relaying will be a simple method of exchanging transmission power and spectrum for connectivity. However, gateways and forwarding nodes, like any other free market, may create an oligopolistic market for the users they serve. In this study, a coalition scheme between buyers aims to address price control by gateways or nodes closer to gateways. In a Stackelberg competition game, buyer agents (users) and sellers (gateways) make decisions using reinforcement learning (RL), with decentralized Deep Q-Networks to buy and sell forwarding resources. We allow communication links between the buyers with a limited messaging space, without defining a collusion mechanism. The idea is to demonstrate that through messaging, and RL tacit collusion can emerge between agents in a decentralized setup. The multi-agent reinforcement learning (MARL) system is presented and analyzed from a machine-learning perspective. Moreover, MARL dynamics are discussed via mean field analysis to better understand divergence causes and make implementation recommendations for such systems. Finally, the simulation results show the results of coordination among the users.

42 ENGINEERING↗
DOE OSTI2023

Resilient Design of Continuous-time Distributed Optimization Algorithm in the Presence of Cyber-attacks

This paper presents a continuous-time resilient distributed optimization algorithm based on competitive interaction design method on connected graphs in the presence of adversaries. Here, the competitive interaction method allows us to design a network that protects the multi-agent systems from adversaries without requiring high network connectivity. In addition, the proposed algorithm does not require the global information about the number of adversaries. First, we show that the proposed distributed algorithm solves the resilient distributed optimization problem with no attack on the communication links. Second, we show that the proposed continuous-time distributed optimization algorithm on connected graphs converges to the small neighborhood of the optimal solution in the presence of cyber-attacks onto the communication channel. Simulations are presented to illustrate our theoretical results.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning

This paper presents a novel federated reinforcement learning (Fed-RL) methodology to inject sufficient resiliency into the operations of the network of microgrids. We consider adversarial actions to the voltage and power control loop reference signals at the grid forming (GFM) inverters in the microgrids which are essential to integrate renewable resources. Therefore, we formulate a resilient reinforcement learning training setup that uses these adversarial injections to generate episodic trajectories and train the RL agents to alleviate their impact on performance. To circumvent the concerns about data-sharing and privacy for different owners of the microgrids in the networked setting, we bring in the aspects of the federated operation to propose novel Fed-RL algorithms. As the dynamics of each microgrid are coupled due to electrical interlinks, the conventional federated RL approaches using decoupled independent environments are not applicable, which leads us to propose a multi-agent vertically federated variation of actor-critic algorithms, namely federated soft actor-critic (FedSAC). We have performed numerical simulations on an IEEE 123-bus benchmark test feeder with three microgrids by creating a customized simulation setup by encapsulating the microgrid dynamic simulations in GridLAB-D/HELICS co-simulation platform with the OpenAI Gym environment and validated the proposed resilient and secured learning methodology.

Artificial Intelligence (AI), reinforcement learni↗
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↗
DOE OSTI2024

A Distributed Model Identification Algorithm for Multi-Agent Systems: Preprint

In this study, we investigate agent-based approach for system model identification with emphasis on power distribution system applications. Departing from conventional practices of relying on historical data for offline model identification, we adopt online update approach utilizing real-time data by employing the latest data points for gradient computation. This methodology offers advantages including a large reduction in the communication network's bandwidth requirements by minimizing the data exchanged at each iteration and enabling the model to adapt in real-time to disturbances. Furthermore, we extend our model identification process from linear frameworks to more complex non-linear convex models. This extension is validated through numerical studies demonstrating improved control performance for a synthetic IEEE test case.

data-driven control↗