SEARCH · Search NASA

Results for “network dynamics as optimization algorithms”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Networked Microgrid Topology Reconfiguration to Promote Fairness in Proactive Load Shedding

Increasing occurrences of natural disasters and grid emergency events consistently challenge the safe and reliable operations of power systems. During such emergency situations, system operators may proactively shed load to mitigate risks. However, uncoordinated implementation of load shedding may disrupt electricity supply and even lead to cascading failures. Meanwhile, it is crucial to address potential biases affecting different customers when executing load shedding. This paper addresses the dynamic topology reconfiguration problem for networked microgrids with distributed energy resources under emergency conditions. Specifically, we propose a novel rolling-horizon optimization model that integrates fairness-aware constraints into the networked microgrid topology reconfiguration. Unlike existing approaches that focus solely on efficiency or apply fairness considerations in static settings, our method explicitly incorporates temporal fairness constraints to restrict repeated or excessive load curtailment for load blocks. Moreover, the fairness-aware constraints are specifically developed for the context of dynamic networked microgrid topology reconfiguration, and are designed to be convex or amenable to linear reformulations, which offers a more tractable alternative to traditional models with non-convex formulations. Numerical studies on a modified IEEE 13-bus system and a larger-sized SMART-DS networked microgrid system demonstrate the performance of the proposed algorithm towards more fairness-aware networked microgrid topology reconfiguration decision-making.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS1995

A linguistic geometry for 3D strategic planning

This paper is a new step in the development and application of the Linguistic Geometry. This formal theory is intended to discover the inner properties of human expert heuristics, which have been successful in a certain class of complex control systems, and apply them to different systems. In this paper we investigate heuristics extracted in the form of hierarchical networks of planning paths of autonomous agents. Employing Linguistic Geometry tools the dynamic hierarchy of networks is represented as a hierarchy of formal attribute languages. The main ideas of this methodology are shown in this paper on the new pilot example of the solution of the extremely complex 3D optimization problem of strategic planning for the space combat of autonomous vehicles. This example demonstrates deep and highly selective search in comparison with conventional search algorithms.

Stilman, Boris↗

NASA NTRSDate not supplied

Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network

This paper studies the Multiple Sources and Multiple Destinations (MSMD) routing problem in a dynamic Air-to-Air Ad-hoc Network (AAAN). We consider a spectrum limited scenario where multiple links have to share the same frequency channel so that co-channel interference becomes inevitable. As a result, routing decisions and spectrum access are coupled and must be jointly considered. This paper proposes a deep Q-learning based algorithm to find an optimal routing and channel selection strategy that minimizes the end-to-end communication delay. Specifically, under the assumption that only local information is available to every node, the Deep Q-Network (DQN) is trained offline to learn the optimal routing and channel selection strategy. After the trained DQN is implemented in every node, multiple relay nodes can simultaneously determine their next-hop relay and channel selections in real-time. Simulation results demonstrate the efficacy of our proposed algorithm.

AAAN↗

NASA NTRSDate not supplied

Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network

AAAN↗

DOE OSTI2024

Flexible dynamic boundary microgrid operation considering network and load unbalances

Flexible microgrids with dynamic boundaries have recently been introduced in the literature. With the ability to reconfigure the topology of the microgrids dynamically through remotely controlled switches, flexible microgrids with dynamic boundaries can further improve the resiliency and energy efficiency of microgrids with distributed energy resources (DERs). This paper focuses on the optimal operation considering one of the predominant characteristics of microgrids and distribution systems – unbalanced networks and loads. In existing literature, balanced modeling of microgrids is more common due to its attractive simplicity. The three-phase power unbalance has not been considered as a constraint on the generation units in a microgrid. Further, negative sequence constraints have also been neglected. In this article, we propose a set of constraints that is specifically related to the capabilities of inverter interfaced resources to supply unbalanced current/power when the microgrid is islanded from the main distribution grid. We incorporate the new set of constraints into two optimization formulations leveraging two convex relaxations of the three-phase power flow equations: mixed-integer linear programming (MILP) and mixed-integer semidefinite programming (MISDP) that optimize the dispatch of controllable switches and DERs in the microgrid. The algorithms are then extended to networked microgrids with grid-forming sources. We test the algorithms on a realistic community microgrid model in Puerto Rico as well as standardized IEEE distribution test feeders. The testing results demonstrate the performance of the proposed algorithms. The MILP is fast and scalable, and the MISDP enforces the negative sequence voltage constraints.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Search for interacting galaxy clusters from SDSS DR-17 employing optimized friends-of-friends algorithm and multimessenger tracers

ABSTRACT In the theoretical framework of hierarchical structure formation, galaxy clusters evolve through continuous accretion and mergers of substructures. Cosmological simulations have revealed the best picture of the universe as a 3D filamentary network of dark-matter distribution called the cosmic web. Galaxy clusters are found to form at the nodes of this network and are the regions of high merging activity. Such mergers being highly energetic, contain a wealth of information about the dynamical evolution of structures in the Universe. Observational validation of this scenario needs a colossal effort to identify numerous events from all-sky surveys. Therefore, such efforts are sparse in literature and tend to focus on individual systems. In this work, we present an improved search algorithm for identifying interacting galaxy clusters and have successfully produced a comprehensive list of systems from SDSS DR-17. By proposing a set of physically motivated criteria, we classified these interacting clusters into two broad classes, ‘merging’ and ‘pre-merging/postmerging’ systems. Interestingly, as predicted by simulations, we found that most cases show cluster interaction along the prominent cosmic filaments of galaxy distribution (i.e. the proxy for dark matter filaments), with the most violent ones at their nodes. Moreover, we traced the imprint of interactions through multiband signatures, such as diffuse cluster emissions in radio or X-rays. Although we could not find direct evidence of diffuse emission from connecting filaments and ridges; our catalogue of interacting clusters will ease locating such faintest emissions as data from sensitive telescopes such as eROSITA or SKA, becomes accessible.

Oak, Tejas↗

NASA NTRS2003

Neural Flight Control System

The Neural Flight Control System (NFCS) was developed to address the need for control systems that can be produced and tested at lower cost, easily adapted to prototype vehicles and for flight systems that can accommodate damaged control surfaces or changes to aircraft stability and control characteristics resulting from failures or accidents. NFCS utilizes on a neural network-based flight control algorithm which automatically compensates for a broad spectrum of unanticipated damage or failures of an aircraft in flight. Pilot stick and rudder pedal inputs are fed into a reference model which produces pitch, roll and yaw rate commands. The reference model frequencies and gains can be set to provide handling quality characteristics suitable for the aircraft of interest. The rate commands are used in conjunction with estimates of the aircraft s stability and control (S&C) derivatives by a simplified Dynamic Inverse controller to produce virtual elevator, aileron and rudder commands. These virtual surface deflection commands are optimally distributed across the aircraft s available control surfaces using linear programming theory. Sensor data is compared with the reference model rate commands to produce an error signal. A Proportional/Integral (PI) error controller "winds up" on the error signal and adds an augmented command to the reference model output with the effect of zeroing the error signal. In order to provide more consistent handling qualities for the pilot, neural networks learn the behavior of the error controller and add in the augmented command before the integrator winds up. In the case of damage sufficient to affect the handling qualities of the aircraft, an Adaptive Critic is utilized to reduce the reference model frequencies and gains to stay within a flyable envelope of the aircraft.

Gundy-Burlet, Karen↗

DOE OSTI2023

Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II

Deep neural network (DNN) potentials are an emerging tool for simulation of dynamical atomistic systems, with the promise of quantum mechanical accuracy at speedups of 10000$\times$. As with other DNN methods, hyperparameters used during training can make a substantial difference in model accuracy, and optimal settings vary with dataset. To enable rapid tuning of hyperparameters for DNN potential training, we developed a scalable multiobjective optimization evolutionary algorithm for supercomputers and tested it on the Summit system at the Oak Ridge Leadership Computing Facility (OLCF). The multiobjective approach is required due to the coupling of two learned values defining the potential: the energy and force. Using a large-scale implementation of the NSGA-II algorithm adapted for training DNN potentials, we discovered several optimal multiobjective combinations, including best choices of activation functions, learning rate scaling scheme, and pairing of the two radial cutoffs used in the three dimensional descriptor function.

Coletti, Mark↗

DOE OSTI2020

Modeling and Control Using Stochastic Distribution Control Theory for Intersection Traffic Flow

In this work, we investigated stochastic distribution control theory-based traffic signal optimization to achieve a smooth and uniform flow of vehicles through signalized intersections. In this context, the static and linear dynamic stochastic distribution models were developed to express the relationship between the signal timing and the traffic queue length together with its probability density function. Two stochastic distribution control algorithms were designed to control the signal timing at intersections such that the probability density function of the traffic queue of each intersection road segment is made as narrow and as small as possible. Also, a recursive input-output traffic queue estimation model was proposed, which is data-driven and dynamic in nature, to calculate real-time traffic queue length using traffic signal timings and loop-detector data. The control algorithms were evaluated for a one-signal corridor, two-signal corridor, and 2 x 2 network of signalized intersections. MATLAB simulation examples are provided to demonstrate the use of the proposed algorithms and comparison to the existing widely-used semi-actuated control has been made. Desired results were obtained.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Traffic Signal Control With Adaptive Online-Learning Scheme Using Multiple-Model Neural Networks

This article proposes a new traffic signal control algorithm to deal with unknown-traffic-system uncertainties and reduce delays in vehicle travel time. Unknown-traffic-system dynamics are approximated using a recurrent neural network (NN). To accurately identify the traffic system model, an online-learning scheme is developed to switch among a set of candidate NNs (i.e., multiple-model NNs) based on their estimation errors. Then, a bank of optimal signal-timing controllers is designed based on the online identification of the traffic system. Simulation studies have been carried out for the obtained control strategies using multiple-model NNs, and the desired results have been obtained. Moreover, compared with the widely used actuated traffic signal control schemes, it is shown that the proposed method can reduce vehicle travel delays and improve traffic system robustness.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2020

A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence

In the present study, we investigate different data-driven parameterizations for large eddy simulation of two-dimensional turbulence in the a priori settings. These models utilize resolved flow field variables on the coarser grid to estimate the subgrid-scale stresses. We use data-driven closure models based on localized learning that employs a multilayer feedforward artificial neural network with point-to-point mapping and neighboring stencil data mapping, and convolutional neural network fed by data snapshots of the whole domain. The performance of these data-driven closure models is measured through a probability density function and is compared with the dynamic Smagorinksy model (DSM). The quantitative performance is evaluated using the cross-correlation coefficient between the true and predicted stresses. We analyze different frameworks in terms of the amount of training data, selection of input and output features, their characteristics in modeling with accuracy, and training and deployment computational time. We also demonstrate computational gain that can be achieved using the intelligent eddy viscosity model that learns eddy viscosity computed by the DSM instead of subgrid-scale stresses. Here, we detail the hyperparameters optimization of these models using the grid search algorithm.

42 ENGINEERING↗

DOE OSTI2025

Inference of response functions with the help of machine-learning algorithms

Response functions are a key quantity to describe the near-equilibrium dynamics of strongly interacting many-body systems. Recent techniques that attempt to overcome the challenges of calculating these ab initio have employed expansions in terms of orthogonal polynomials. We employ a neural network prediction algorithm to reconstruct a response function 𝑆⁡(𝜔) defined over a range in frequencies 𝜔. Here, we represent the calculated response function as a truncated Chebyshev series whose coefficients can be optimized to reduce the representation error. We compare the quality of response functions obtained using coefficients calculated using a neural network (NN) algorithm with those computed using the Gaussian integral transform (GIT) method. In the regime where only a small number of terms in the Chebyshev series are retained, we find that the NN scheme outperforms the GIT method.

Kurkcuoglu, Doga Murat [Fermi National Accelerator↗

NASA NTRS1977

The navigation system of the JPL robot

The control structure of the JPL research robot and the operations of the navigation subsystem are discussed. The robot functions as a network of interacting concurrent processes distributed among several computers and coordinated by a central executive. The results of scene analysis are used to create a segmented terrain model in which surface regions are classified by traversibility. The model is used by a path planning algorithm, PATH, which uses tree search methods to find the optimal path to a goal. In PATH, the search space is defined dynamically as a consequence of node testing. Maze-solving and the use of an associative data base for context dependent node generation are also discussed. Execution of a planned path is accomplished by a feedback guidance process with automatic error recovery.

Thompson, A. M.↗

DOE OSTI2020

Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks

Here we propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope-based slope recovery term is added in the loss function, which further accelerates convergence, thereby reducing the training cost. On the theoretical side, we prove that in the proposed method, the gradient descent algorithms are not attracted to sub-optimal critical points or local minima under practical conditions on the initialization and learning rate, and that the gradient dynamics of the proposed method is not achievable by base methods with any (adaptive) learning rates. We further show that the adaptive activation methods accelerate the convergence by implicitly multiplying conditioning matrices to the gradient of the base method without any explicit computation of the conditioning matrix and the matrix–vector product. The different adaptive activation functions are shown to induce different implicit conditioning matrices. Furthermore, the proposed methods with the slope recovery are shown to accelerate the training process.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2004

Adaptive Bio-Inspired Wireless Network Routing for Planetary Surface Exploration

Wireless mobile networks suffer connectivity loss when used in a terrain that has hills, and valleys when line of sight is interrupted or range is exceeded. To resolve this problem and achieve acceptable network performance, we have designed an adaptive, configurable, hybrid system to automatically route network packets along the best path between multiple geographically dispersed modules. This is very useful in planetary surface exploration, especially for ad-hoc mobile networks, where computational devices take an active part in creating a network infrastructure, and can actually be used to route data dynamically and even store data for later transmission between networks. Using inspiration from biological systems, this research proposes to use ant trail algorithms with multi-layered information maps (topographic maps, RF coverage maps) to determine the best route through ad-hoc network at real time. The determination of best route is a complex one, and requires research into the appropriate metrics, best method to identify the best path, optimizing traffic capacity, network performance, reliability, processing capabilities and cost. Real ants are capable of finding the shortest path from their nest to a food source without visual sensing through the use of pheromones. They are also able to adapt to changes in the environment using subtle clues. To use ant trail algorithms, we need to define the probability function. The artificial ant is, in this case, a software agent that moves from node to node on a network graph. The function to calculate the fitness (evaluate the better path) includes: length of the network edge, the coverage index, topology graph index, and pheromone trail left behind by other ant agents. Each agent modifies the environment in two different ways: 1) Local trail updating: As the ant moves between nodes it updates the amount of pheromone on the edge; and 2) Global trail updating: When all ants have completed a tour the ant that found the shortest route updates the edges in its path.

Alena, Richard I.↗

DOE OSTI2024

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗

DOE OSTI2022

Optimizing radar scan strategies for tracking isolated deep convection using observing system simulation experiments

Abstract. Optimizing radar observation strategies is one of the most important considerations in pre-field campaign periods. This is especially true for isolated convective clouds that typically evolve faster than the observations captured by operational radar networks. This study investigates uncertainties in radar observations of the evolution of the microphysical and dynamical properties of isolated deep convective clouds developing in clean and polluted environments. It aims to optimize the radar observation strategy for deep convection through the use of high-spatiotemporal cloud-resolving model simulations, which resolve the evolution of individual convective cells every 1 min, coupled with a radar simulator and a cell tracking algorithm. The radar simulation settings are based on the Tracking Aerosol Convection Interactions ExpeRiment (TRACER) and Experiment of Sea Breeze Convection, Aerosols, Precipitation and Environment (ESCAPE) field campaigns held in the Houston, TX, area but are generalizable to other field campaigns focusing on isolated deep convection. Our analysis produces the following four outcomes. First, a 5–7 m s−1 median difference in maximum updrafts of tracked cells is shown between the clean and polluted simulations in the early stages of the cloud lifetimes. This demonstrates the importance of obtaining accurate estimates of vertical velocity from observations if aerosol impacts are to be properly resolved. Second, tracking of individual cells and using vertical cross section scanning every minute capture the evolution of precipitation particle number concentration and size represented by polarimetric observables better than the operational radar observations that update the volume scan every 5 min. This approach also improves multi-Doppler radar updraft retrievals above 5 km above ground level for regions with updraft velocities greater than 10 m s−1. Third, we propose an optimized strategy composed of cell tracking by quick (1–2 min) vertical cross section scans from more than one radar in addition to the operational volume scans. We also propose the use of a single-RHI (range height indicator) updraft retrieval technique for cells close to the radars, for which multi-Doppler radar retrievals are still challenging. Finally, increasing the number of deep convective cells sampled by such observations better represents the median maximum updraft evolution with sample sizes of more than 10 deep cells, which decreases the error associated with sampling the true population to less than 3 m s−1.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

GenomeFace v1.0

GenomeFace is meta-genome binning software. Metagenomic binning, the process of grouping DNA sequences into taxonomic units, is critical for understanding the functions, interactions, and evolutionary dynamics of microbial communities. We propose a deep learning approach to binning using two neural networks, one based on composition and another on environmental abundance, dynamically weighting the contribution of each based on characteristics of the input data. Trained on over 43,000 prokaryotic genomes, our network for composition-based binning is inspired by metric learning techniques used for facial recognition. Using a task-specific, multi-GPU accelerated algorithm to cluster the embeddings produced by our network, our binner leverages marker genes observed to be universally present in nearly all taxa to grade and select optimal clusters of sequences from a hierarchy of candidates. We evaluate our approach on four simulated datasets with known ground truth. Our linear time integration of marker genes recovers more near complete genomes than state of the art but computationally infeasible solutions using them, while being over an order of magnitude faster. Finally, we demonstrate the scalability and acuity of our approach by testing it on three of the largest metagenome assemblies ever performed. Compared to other binners, we produced 47%-183% more near complete genomes. From these datasets, we find over the genomes of over 3000 new candidate species which have never been previously cataloged, representing a potential 4% expansion of the known bacterial tree of life.

Lettich, Richard [Lawrence Berkeley National Labor↗