Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “graph 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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2022

A resilient network recovery framework against cascading failures with deep graph learning

Because of the increasing importance and dependencies of infrastructure networks and the potential for massive cascading failures in real-world network systems, maintenance optimization to effectively reduce system performance loss caused by diverse disruptions is of significant interest among researchers and practitioners. In this work, a new recovery framework was developed to rapidly identify important system components for maintenance to improve network resilience against cascading failures. Here this work provides distinct advantages to determine an optimal maintenance priority by combining real-time network structure importance with other maintenance prioritization based on customer preference. This approach adopts structural graph embedding and deep reinforcement learning to extract real-time network topology information (such as minimum vertex cover) to update the maintenance priority during the recovery process. Based on the case studies on synthetic networks and a US airport network, the proposed recovery framework with real-time network topology awareness shows better performance than other maintenance prioritization strategies regarding resilience enhancement. This work improves the understanding of how the changing network structure influences maintenance effects. It also provides insights of the practical usefulness of advanced deep learning on helping optimal maintenance prioritization to effectively reduce the intensity and extent of cascading failures.

42 ENGINEERING↗
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 OSTI2023

Code for Value Decomposition Graph Network and environment for AMR on linear advection

This is the code for the paper [Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement](https://arxiv.org/abs/2211.00801), published at AAMAS 2023. It contains the implementation of a new algorithm, called Value Decomposition Graph Network (VDGN), for applying multi-agent reinforcement learning to the problem of adaptive mesh refinement (AMR). It also contains the implementation of a multi-agent environment for AMR on a linear advection problem. VDGN is the first learning algorithm to display anticipatory refinement behavior in AMR, and it outperforms local error threshold-based heuristic strategies.

Yang, Jiachen↗
DOE OSTI2025

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗
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 OSTI2023

Postdisaster Routing of Movable Energy Resources for Enhanced Distribution System Resilience: A Deep Reinforcement Learning-Based Approach

The deployment of movable energy resources (MERs) can be an effective strategy to restore critical loads to enhance power system resilience when no other energy sources are available after the occurrence of an extreme event. Since the optimal locations of MERs following an extreme event are dependent on system operating states (e.g., the loads at each node, on/off status of system branches, and so on), existing analytical and population-based approaches must repeat the entire analysis and calculation when the system operating states change. On the contrary, if deep reinforcement learning (DRL)-based algorithms are sufficiently trained with a wide range of scenarios, they can quickly find optimal or near-optimal locations irrespective of changes in system states. A deep Q-learning-based approach is proposed for optimal MER deployment to enhance power system resilience. MERs can be also utilized to complement other types of resources, if available. The proposed approach operates in two stages after the occurrence of extreme events. In the first stage, the distribution network is represented as a graph, and the network is then reconfigured using tie switches by using Kruskal’s spanning forest search algorithm (KSFSA). To maximize critical load recovery, the optimal or near-optimal locations of MERs are chosen in the second stage. Further, case studies on a 33-node distribution system and a modified IEEE 123-node system demonstrate the effectiveness of the proposed approach for postdisaster routing of MERs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Accelerating matrix-centric graph processing on GPUs through bit-level optimizations

Even though it is well known that binary values are common in graph applications (e.g., adjacency matrix), how to leverage the phenomenon for efficiency has not yet been adequately explored. This paper presents a systematic study on how to unlock the potential of the bit-level optimizations of graph computations that involve binary values. It proposes a two-level representation named Bit-Block Compressed Sparse Row (B2SR) and presents a series of optimizations to the graph operations on B2SR by the intrinsics of modern GPUs. It additionally introduces Deep Reinforcement Learning (DRL) as an efficient way to best configure the bit-level optimizations on the fly. Additionally, the DQN-based adaptive tile size selector with dedicated model training can reach 68% prediction accuracy. Evaluations on NVIDIA Pascal and Volta GPUs show that the optimizations bring up to 40× and 6555× for essential GraphBLAS kernels SpMV and SpGEMM, respectively, making GraphBLAS-based BFS accelerate up to 433×, SSSP, PR, and CC up to 35×, and TC up to 52×.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2017

A Machine Learning Concept for DTN Routing

This paper discusses the concept and architecture of a machine learning based router for delay tolerant space networks. The techniques of reinforcement learning and Bayesian learning are used to supplement the routing decisions of the popular Contact Graph Routing algorithm. An introduction to the concepts of Contact Graph Routing, Q-routing and Naive Bayes classification are given. The development of an architecture for a cross-layer feedback framework for DTN (Delay-Tolerant Networking) protocols is discussed. Finally, initial simulation setup and results are given.

Delay Tolerant Networks↗
DOE OSTI2023

Automated Adversary-in-the-Loop Cyber-Physical Defense Planning

Security of cyber-physical systems (CPS) continues to pose new challenges due to the tight integration and operational complexity of the cyber and physical components. To address these challenges, this article presents a domain-aware, optimization-based approach to determine an effective defense strategy for CPS in an automated fashion—by emulating a strategic adversary in the loop that exploits system vulnerabilities, interconnection of the CPS, and the dynamics of the physical components. Our approach builds on an adversarial decision-making model based on a Markov Decision Process (MDP) that determines the optimal cyber (discrete) and physical (continuous) attack actions over a CPS attack graph. The defense planning problem is modeled as a non-zero-sum game between the adversary and defender. We use a model-free reinforcement learning method to solve the adversary’s problem as a function of the defense strategy. We then employ Bayesian optimization (BO) to find an approximate best-response for the defender to harden the network against the resulting adversary policy. This process is iterated multiple times to improve the strategy for both players. We demonstrate the effectiveness of our approach on a ransomware-inspired graph with a smart building system as the physical process. Numerical studies show that our method converges to a Nash equilibrium for various defender-specific costs of network hardening.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Inverse Reinforcement Learning based Bayesian Goal Inference Method for Early Nuclear Proliferation Detection

Traditional methods for detection of nuclear proliferation indicators are usually applied after nuclear proliferation has already occurred. There is a need to advance these methods to perform early detection of nuclear proliferation indicators. In this project, we formulated an early detection problem as a sequential, decision-making, goal inference problem based on research publications of authors, to determine whether it is possible to infer whether an author will publish on a research activity before it has occurred. To develop and test our approach, we selected a civil nuclear activity for our case study. We constructed a state-action-state transition graph from publications of authors associated with the activity and the co-authors of their publications, using titles, abstracts, and author publication sequences. We then used inverse reinforcement learning to model the goal-directed behavior of authors in trajectories that terminate at selected goal states. Using a Bayesian formulation, we computed the probability that authors would reach each selected state from partially observed trajectories of their state transitions in their research topic space. The state with the highest probability was selected as the most probable goal state. Based on our results, we found that 60% of the times we can infer the correct goal state early; sometimes the inference is either delayed, or multiple states could be inferred as goal states. Overall, our results show that it is possible to perform early detection of research activities of authors in a nuclear technology area. Further research is necessary to establish a more accurate understanding of how topic modeling, topic space grid discretization, and the extent of overlap among trajectories of different goal states, affect the goal inference results. The methods developed in this work may be used to enhance data-driven methods for early detection of nuclear proliferation indicators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Exploring the holographic entropy cone via reinforcement learning

We develop a reinforcement learning algorithm to study the holographic entropy cone. Given a target entropy vector, our algorithm searches for a graph realization whose min-cut entropies match the target vector. If the target vector does not admit such a graph realization, it must lie outside the cone, in which case the algorithm finds a graph whose corresponding entropy vector most nearly approximates the target and allows us to probe the location of the facets. For the N = 3 cone, we confirm that our algorithm successfully rediscovers monogamy of mutual information beginning with a target vector outside the holographic entropy cone. We then apply the algorithm to the N = 6 cone, analyzing the 6 mystery extreme rays of the subadditivity cone from [1] that satisfy all known holographic entropy inequalities yet lacked graph realizations. We found realizations for 3 of them, proving they are genuine extreme rays of the holographic entropy cone, while providing evidence that the remaining 3 are not realizable, implying unknown holographic inequalities exist for N = 6.

AdS-CFT correspondence↗
DOE OSTI2022

Post-Disaster Microgrid Formation for Enhanced Distribution System Resilience

This paper proposes a deep reinforcement learning (DRL) based approach for post-disaster critical load restoration in active distribution systems to form microgrids through network reconfiguration to minimize critical load curtailments. Distribution networks are represented as graph networks, and optimal network configurations with microgrids are obtained by searching for the optimal spanning forest. The constraints to the research question being explored are the radial topology and power balance. Unlike existing analytical and population-based approaches, which necessitate the repetition of entire analyses and computation for each outage scenario to find the optimal spanning forest, the proposed approach, once properly trained, can quickly determine the optimal, or near-optimal, spanning forest even when outage scenarios change. When multiple lines fail in the system, the proposed approach forms microgrids with distributed energy resources in active distribution systems to reduce critical load curtailment. The proposed DRL-based model learns the action-value function using the REINFORCE algorithm, which is a model-free reinforcement learning technique based on stochastic policy gradients. A case study was conducted on a 33-node distribution test system, demonstrating the effectiveness of the proposed approach for post-disaster critical load restoration.

active distribution systems↗
DOE OSTI2022

Multi-objective goal-directed optimization of de novo stable organic radicals for aqueous redox flow batteries

Abstract Advances in the field of goal-directed molecular optimization offer the promise of finding feasible candidates for even the most challenging molecular design applications. One example of a fundamental design challenge is the search for novel stable radical scaffolds for an aqueous redox flow battery that simultaneously satisfy redox requirements at the anode and cathode, as relatively few stable organic radicals are known to exist. To meet this challenge, we develop a new open-source molecular optimization framework based on AlphaZero coupled with a fast, machine-learning-derived surrogate objective trained with nearly 100,000 quantum chemistry simulations. The objective function comprises two graph neural networks: one that predicts adiabatic oxidation and reduction potentials and a second that predicts electron density and local three-dimensional environment, previously shown to be correlated with radical persistence and stability. With no hard-coded knowledge of organic chemistry, the reinforcement learning agent finds molecule candidates that satisfy a precise combination of redox, stability and synthesizability requirements defined at the quantum chemistry level, many of which have reasonable predicted retrosynthetic pathways. The optimized molecules show that alternative stable radical scaffolds may offer a unique profile of stability and redox potentials to enable low-cost symmetric aqueous redox flow batteries.

25 ENERGY STORAGE↗
DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗
DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗
DOE OSTI2023

Reinforcement Learning-based Output Structured Feedback for Distributed Multi-Area Power System Frequency Control

Load frequency control (LFC) is a key factor to maintain the stable frequency in multi-area power systems. As the modern power systems evolve from centralized to decentralized paradigm, LFC needs to consider the decentralized scheme that considers limited information from the information-exchange graph for the generator control of each interconnected area. This paper aims to solve a data-driven constrained LQR problem with mean-variance risk constraints and output structured feedback, and applies this framework to solve the LFC problem in multi-area power systems. By reformulating the constrained optimization problem into a minimax problem, the stochastic gradient descent max-oracle (SGDmax) algorithm with zero-order policy gradient (ZOPG) is adopted to find the optimal feedback gain from the learning, while guaranteeing the convergence. In addition, to improve the adaptation of the proposed learning method to new or varying models, we construct an emulator grid that approximates the dynamics of a physical grid and performs training based on this model. Once the feedback gain is obtained from the emulator grid, it is applied to the physical grid with a robustness test to check whether the controller from the approximated emulator applies to the actual system. Numerical tests show that the obtained feedback controller can successfully control the frequency of each area, while mitigating the uncertainty from the loads, with reliable robustness that ensures the adaptability of the obtained feedback gain to the actual physical grid.

Kwon, Kyung-bin↗