Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network solutions”

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 1,765 records · Page 98

Preliminary Work for Examining the Scalability of Reinforcement Learning

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Clouse, Jeff↗

Crystal Structures of the GCaMP Calcium Sensor Reveal the Mechanism of Fluorescence Signal Change and Aid Rational Design

The genetically encoded calcium indicator GCaMP2 shows promise for neural network activity imaging, but is currently limited by low signal-to-noise ratio. We describe x-ray crystal structures as well as solution biophysical and spectroscopic characterization of GCaMP2 in the calcium-free dark state, and in two calcium-bound bright states: a monomeric form that dominates at intracellular concentrations observed during imaging experiments and an unexpected domain-swapped dimer with decreased fluorescence. This series of structures provides insight into the mechanism of Ca{sup 2+}-induced fluorescence change. Upon calcium binding, the calmodulin (CaM) domain wraps around the M13 peptide, creating a new domain interface between CaM and the circularly permuted enhanced green fluorescent protein domain. Residues from CaM alter the chemical environment of the circularly permuted enhanced green fluorescent protein chromophore and, together with flexible inter-domain linkers, block solvent access to the chromophore. Guided by the crystal structures, we engineered a series of GCaMP2 point mutants to probe the mechanism of GCaMP2 function and characterized one mutant with significantly improved signal-to-noise. The mutation is located at a domain interface and its effect on sensor function could not have been predicted in the absence of structural data.

36 MATERIALS SCIENCE↗

Demonstration of acoustic monitoring for structural health of microreactors: Through use of neural networks and resonant ultrasound spectroscopy

Nuclear microreactors prioritize modularity and portability and are intended to be a cost-effective technology for non-conventional nuclear markets. As such, the development of microreactors into a safe and feasible solution for energy security applications will necessitate the development of non-destructive technologies to monitor the integrity of inaccessible reactors components during operation. This demonstration applies linear and nonlinear acoustic techniques, in combination with machine learning, to detect and classify mechanical changes (stress and damage) in a test article which are broadly representative of potential operating challenges within a functioning microreactor. All necessary data has been collected for this demonstration, with minor experimental issues identified that can be addressed in follow-on work. Motivated by the expected conditions within a functioning microreactor, we have demonstrated our monitoring techniques on a core-block-like test article using an unstructured excitation source that approximates the noisy acoustic environment expected during reactor operation. At all stress states mechanically applied to the test article, a machine learning model using an artificial neural network was able to classify with 100% accuracy whether a 3D laser vibrometry point measurement was made on an intact or artificially defective test article. Further, model predictions about whether the defect interface was rough or smooth were 95% accurate, indicating the ability of acoustic techniques to recover defect characteristics. Resonant ultrasound spectroscopy (RUS) was also applied to the dataset to provide further quantitative insights about material properties. RUS analysis was ultimately hampered by several minor experimental and data issues, limiting results to certain cases for this demonstration. Last, analysis using nonlinear RUS exhibited sensitivity to changing levels of applied stresses for each intact and defective state. As presented in this demonstration, acoustic monitoring exhibits sensitivity to stress changes, which are of concern due to high thermal gradients expected during startup and operation. Further, our techniques distinguish between measurements made on intact and damaged test articles.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Light fidelity (Li-Fi): An effective solution for data transmission

The rapid advancement in the field of science has led to the development of many technologies, gadgets and equipment which in turn has hold pressure on Wi-Fi, modems, board band connections etc., to lessen this stress new revolution in this field has rooted on termed “LI-FI”. Li-Fi stands for light fidelity i.e. light is used for the transmission of data. The concept of Li-Fi is taking the fiber out of fiber optics sending information through an LED that varies in intensity faster than human eye can follow. Li-Fi offers an entirely new paradigm in wireless technology in term of communication, speed, flexibility, usability etc. The idea of data through illumination is similar to radio waves communication difference lies in the use of LED in LI-Fi, which made it superior than Wi-Fi. Hence Li-Fi is linked to the visible light communication network provision transmission which is looked upon as an advancement. Thus a new class of light with high intensity light source of solid state design bringing clean lighting solution to general and specialty lighting. With energy efficiency, long useful lifetime, full spectrum and dimming. Li-Fi is just not only confined to light and LED indeed it is a platform with versatile advantages and facilities. This paper gives a brief idea about the introduction of Li-Fi, its working, advantages, limitations etc.

42 ENGINEERING↗

TwinMe4AD: WGAN-based Digital Twins for Anomaly Detection

SAND2024-08373O TwinMe4AD is a Python-based software tool designed for anomaly detection using digital twins that closely mimic real, wearable healthcare datasets. The tool is invaluable for scenarios where collecting data is either expensive or impractical, serving as a privacy-preserving solution. Sensitive information is protected by training deep learning models on synthetic data derived from real datasets. One of TwinMe4AD's key features is its anomaly detection capability, which is based on fourth-order moments of parameters. This versatile approach can be applied across a range of datasets, from univariate to multivariate, making it compatible with various types of data. It also generates synthetic twins using Wasserstein Generative Adversarial Networks (WGANs), allowing users to create a small cohort of a population similar to that of a village population. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Poorey, Kunal↗

Adaptive digital beamforming for a CDMA mobile communications payload

In recent years, Spread-Spectrum Code Division Multiple Access (CDMA) has become a very popular access scheme for mobile communications due to a variety of reasons: excellent performance in multipath environments, high scope for frequency reuse, graceful degradation near saturation, etc. In this way, a CDMA system can support simultaneous digital communication among a large community of relatively uncoordinated users sharing a given frequency band. Nevertheless, there are also important problems associated with the use of CDMA. First, in a conventional CDMA scheme, the signature sequences of asynchronous users are not orthogonal and, as the number of active users increases, the self-noise generated by the mutual interference between users considerably degrades the performance, particularly in the return link. Furthermore, when there is a large disparity in received powers - due to differences in slant range or atmospheric attenuation - the non-zero cross-correlation between the signals gives rise to the so-called near-far problem. This leads to an inefficient utilization of the satellite resources and, consequently, to a drastic reduction in capacity. Several techniques were proposed to overcome this problem, such as Synchronized CDMA - in which the signature sequences of the different users are quasi-orthogonal - and power control. At the expense of increased network complexity and user coordination, these techniques enable the system capacity to be restored by equitably sharing the satellite resources among the users. An alternative solution is presented based upon the use of time-reference adaptive digital beamforming on board the satellite. This technique enables a high number of independently steered beams to be generated from a single phased array antenna, which automatically track the desired user signal and null the unwanted interference source. In order to use a time-reference adaptive antenna in a communications system, the main challenge is to obtain a reference signal highly correlated with the desired user signal and uncorrelated with the interferences. CDMA lends itself very easily to the generation of such a reference signal, thanks to the a priori knowledge of the user's signature sequence. First, the integration of an adaptive antenna in an asynchronous CDMA system is analyzed. The adaptive antenna system can provide increased interference rejection - much higher than that afforded by the code alone - and, since CDMA is mainly interference limited, any reduction in interference converts directly and linearly into an increase in capacity. Analyses and computer simulations are presented that show how an asynchronous CDMA system incorporating adaptive beamforming can provide at least as much capacity as a synchronous system. More importantly, the proposed concept allows the near-far effect to be mitigated without requiring a tight coordination of the users in terms of transmitted power control or network synchronization. The system is extremely robust to the near-far effect because the signals reaching the satellite from directions other than that of the desired user - which are likely to have different power levels - are adaptively canceled by the antenna. Finally, a payload architecture is presented that illustrates the practical implementation of this concept. This digital payload architecture demonstrates that with the advent of high performance CMOS digital processing, the on-board implementation of complex DSP techniques - in particular Digital Beamforming - has become possible, being most attractive for Mobile Satellite Communications.

Munoz-Garcia, Samuel G.↗

Solving differential equations using deep neural networks

Recent work on solving partial differential equations (PDEs) with deep neural networks (DNNs) is presented. The paper reviews and extends some of these methods while carefully analyzing a fundamental feature in numerical PDEs and nonlinear analysis: irregular solutions. First, the Sod shock tube solution to the compressible Euler equations is discussed and analyzed. This analysis includes a comparison of a DNN-based approach with conventional finite element and finite volume methods, and demonstrates that the DNN is competitive in terms of degrees of freedom required for a given accuracy. Further, the DNN-based approach is extended to consider performance improvements and simultaneous parameter space exploration. Next, a shock solution to compressible magnetohydrodynamics (MHD) is solved for, and used in a scenario where experimental data is utilized to enhance a PDE system that is a priori insufficient to validate against the observed/experimental data. This is accomplished by enriching the model PDE system with source terms that are then inferred via supervised training with synthetic experimental data. The resulting DNN framework for PDEs enables straightforward system prototyping and natural integration of large data sets (be they synthetic or experimental), all while simultaneously enabling single-pass exploration of an entire parameter space.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Neural Networks-Based Inverter Control: Modeling and Adaptive Optimization for Smart Distribution Networks

The optimal voltage control of inverter-based resources, especially under the high penetration of solar photovoltaics, is critical to the stability of the distribution power system. However, the computational complexity as well as the coordinated operation performance of the voltage control optimization in the distribution power system limits the real-time applications. To mitigate this issue, a model-free based adaptive optimal control scheme for the smart inverter is proposed to maximize the active power generation, minimize the power loss, and maintain the bus voltages in smart distribution networks. An inverter-based optimization model for coordinated operation is first established, considering the uncertainties of renewable power generation. Subsequently, by collecting the data and control strategies, the neural networks (NNs) based algorithm is proposed to efficiently predict the best possible control strategy. The main objective of this scheme is to accurately predict candidate optimal solutions with near-negligible feasibility and optimization gaps, with the advantage of avoiding complicated iteration-based numerical algorithms. Thereafter, the co-simulation among OpenDSS, MATLAB, and Python is set up to fully take advantage of the three individual software. Experiments are conducted based on different control parameter characteristics and structures of NNs. Finally, the results reveal that an average mean squared error of 0.013 and 1 ms response time are achieved, which is lower than some state-of-the-art methods.

42 ENGINEERING↗

OASIS: Offsetting Active Reconstruction Attacks in Federated Learning

Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from health care to industrial engineering, especially where data cannot be easily exchanged due to sensitive information or privacy laws. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification of global model parameters, allowing the server to obtain a verbatim copy of users' private data by inverting their gradient updates. Tackling this class of attack remains a crucial challenge due to the strong threat model. In this paper, we propose a defense mechanism, namely OASIS, based on image augmentation that effectively counteracts active reconstruction attacks while preserving model performance. We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies. We then construct our defense with image augmentation showing that it can undermine the attack principle. Comprehensive evaluations demonstrate the efficacy of the defense mechanism highlighting its feasibility as a solution.

deep neural networks↗

Separation-Compliant, Optimal Routing and Control of Scheduled Arrivals in a Terminal Airspace

We address the problem of navigating a set (fleet) of aircraft in an aerial route network so as to bring each aircraft to its destination at a specified time and with minimal distance separation assured between all aircraft at all times. The speed range, initial position, required destination, and required time of arrival at destination for each aircraft are assumed provided. Each aircraft's movement is governed by a controlled differential equation (state equation). The problem consists in choosing for each aircraft a path in the route network and a control strategy so as to meet the constraints and reach the destination at the required time. The main contribution of the paper is a model that allows to recast this problem as a decoupled collection of problems in classical optimal control and is easily generalized to the case when inertia cannot be neglected. Some qualitative insight into solution behavior is obtained using the Pontryagin Maximum Principle. Sample numerical solutions are computed using a numerical optimal control solver. The proposed model is first step toward increasing the fidelity of continuous time control models of air traffic in a terminal airspace. The Pontryagin Maximum Principle implies the polygonal shape of those portions of the state trajectories away from those states in which one or more aircraft pair are at minimal separation. The model also confirms the intuition that, the narrower the allowed speed ranges of the aircraft, the smaller the space of optimal solutions, and that an instance of the optimal control problem may not have a solution at all (i.e., no control strategy that meets the separation requirement and other constraints).

transportation network↗

End-to-end optimization for battery materials and molecules by combining graph neural networks and reinforcement learning

The National Renewable Energy Laboratory (NREL), together with the Colorado School of Mines (CSM) and Colorado State University (CSU), has developed a machine learning-enhanced approach to design new battery materials. Currently, such materials are designed in part via numerous expensive high-fidelity computational simulations that predict the performance of a given composition. Even with computational screening tools, the vast landscape of possible molecular or crystal structures exceeds current and future computational capacity. Improving the efficiency by which new materials can be optimized will therefore disrupt the cost, risk, and time required to bring new energy solutions to the marketplace. Predicting the properties of an organic molecule or periodic crystalline material given its structure has grown increasingly common. These approaches leverage large-scale computational and experimental databases and ML approaches such as graph neural networks. The inverse design problem of finding a material that possesses desired properties is substantially more challenging, since enumerating all valid material structures is not feasible. In this project, we leveraged recent success in reinforcement learning to efficiently navigate this high-dimensional search space. Just as algorithms can find the optimal chess moves from nearly limitless options, we train an approach to evolve a simple starting structure into a complex structure that possess the desired properties. Our solution has been demonstrated by applying it to two related design application tasks for short- and long-term energy storage, respectively: (1) the design of solid-state ion conductors and (2) the design of organic redox-active materials. The project has resulted an open-source software library for material design, documented examples of applying the library to both organic and inorganic material optimization, and peer-reviewed publications detailing the data, computational models, and resulting candidate materials.

25 ENERGY STORAGE↗

Optimal Network Topology for Node-Breaker Representations With AC Power Flow Constraints

It has been demonstrated that network topology optimization (NTO) may change the topology of power system networks, and consequently, provide additional flexibility to reduce network congestion and violations. Most NTO problems are formulated based on the bus-branch model in which it is challenging to represent a realistic picture of all substation configurations. In this paper, we explore advantages of substation reconfiguration modeling based on node-breaker representations for NTO problem with full nonlinear alternating current power flow. It also proposes a tailored solution algorithm to solve this nonconvex mixed-integer nonlinear programming through the outer approximation method. The proposed solution approach iterates between a mixed-integer linear programming and a nonlinear subproblem. Additional enhancements to further accelerate the iteration process are illustrated. Numerical case studies demonstrate the relative economic and operational impact of optimal network topology with node-breaker representations.

42 ENGINEERING↗

Scalable optimal Bayesian classification of single-cell trajectories under regulatory model uncertainty

Single-cell gene expression measurements offer opportunities in deriving mechanistic understanding of complex diseases, including cancer. However, due to the complex regulatory machinery of the cell, gene regulatory network (GRN) model inference based on such data still manifests significant uncertainty. The goal of this paper is to develop optimal classification of single-cell trajectories accounting for potential model uncertainty. Partially-observed Boolean dynamical systems (POBDS) are used for modeling gene regulatory networks observed through noisy gene-expression data. We derive the exact optimal Bayesian classifier (OBC) for binary classification of single-cell trajectories. The application of the OBC becomes impractical for large GRNs, due to computational and memory requirements. To address this, we introduce a particle-based single-cell classification method that is highly scalable for large GRNs with much lower complexity than the optimal solution. The performance of the proposed particle-based method is demonstrated through numerical experiments using a POBDS model of the well-known T-cell large granular lymphocyte (T-LGL) leukemia network with noisy time-series gene-expression data.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluating Transactive Controls of Integrated Transmission and Distribution Systems using the Framework for Network Co-Simulation

With an ever-evolving power grid, concerns regarding how to maintain system stability, efficiency, and reliability remain constant because of increasing uncertainties and decreasing rotating inertia. To alleviate some of these concerns, demand response represents a viable solution and is virtually an untapped resource in the current power grid. This work describes a hierarchical control framework that allows coordination between distributed energy resources and demand response. This control framework is composed of two control layers: a coordination layer that ensures aggregations of resources are coordinated to achieve system objectives and a device layer that controls individual resources to assure the predetermined power profile is tracked in real time. Large-scale simulations are executed to study the hierarchical control, requiring advancements in simulation capabilities. Technical advancements necessary to investigate and answer control interaction questions, including the Framework for Network Co-Simulation platform and Arion modeling capability, are detailed. Insights into the interdependencies of controls across a complex system and how they must be tuned, as well as validation of the effectiveness of the proposed control framework, are yielded using a large-scale integrated transmission system model coupled with multiple distribution systems.

demand response↗

Distribution Grid Modeling Using Smart Meter Data

The knowledge of distribution grid models, including topologies and line impedances, is essential for grid monitoring, control and protection. However, such information is often unavailable, incomplete or outdated. The increasing deployment of smart meters (SMs) provides a unique opportunity to tackle this issue. This paper proposes a two-stage framework for distribution grid modeling using SM data. In the first stage, the network topology is identified by reconstructing a weighted Laplacian matrix of distribution networks. In the second stage, a least absolute deviations (LAD) regression model is developed for estimating line impedance of a single branch based on the nonlinear (inverse) power flow model, wherein a conductor library is leveraged to narrow down the solution space. The LAD regression model is originally a mixed-integer nonlinear program whose continuous relaxation is still non-convex. Furthermore, we specially address its convex relaxation and discuss the exactness. The modified regression model is then embedded within a bottom-up sweep algorithm to achieve the identification across the network in a branch-wise manner. Numerical results on the IEEE 13-bus, 37-bus and 69-bus test feeders validate the effectiveness of the proposed methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Essential SpaceWire Hardware Capabilities for a Robust Network

The Geostationary Operational Environmental Satellite R-Series Program (GOES-R) mission is a joint program between National Oceanic & Atmospheric Administration (NOAA) and National Aeronautics & Space Administration (NASA) Goddard Space Flight Center (GSFC). GOES-R project selected SpaceWire as the best solution to satisfy the desire for simple and flexible instrument to spacecraft command and telemetry communications. GOES-R development and integration is complete and the observatory is scheduled for launch October 2016. The spacecraft design was required to support redundant SpaceWire links for each instrument side, as well as to route the fewest number of connections through a Slip Ring Assembly necessary to support Solar pointing instruments. The final design utilized two different router designs. The SpaceWire standard alone does not ensure the most practical or reliable network. On GOES-R a few key hardware capabilities were identified that merit serious consideration for future designs. Primarily these capabilities address persistent port stalls and the prevention of receive buffer overflows. Workarounds were necessary to overcome shortcomings that could be avoided in future designs if they utilize the capabilities, discussed in this paper, above and beyond the requirements of the SpaceWire standard.

SpaceWire↗

Real-time hierarchically distributed processing network interaction simulation

The Telerobot Testbed is a hierarchically distributed processing system which is linked together through a standard, commercial Ethernet. Standard Ethernet systems are primarily designed to manage non-real-time information transfer. Therefore, collisions on the net (i.e., two or more sources attempting to send data at the same time) are managed by randomly rescheduling one of the sources to retransmit at a later time interval. Although acceptable for transmitting noncritical data such as mail, this particular feature is unacceptable for real-time hierarchical command and control systems such as the Telerobot. Data transfer and scheduling simulations, such as token ring, offer solutions to collision management, but do not appropriately characterize real-time data transfer/interactions for robotic systems. Therefore, models like these do not provide a viable simulation environment for understanding real-time network loading. A real-time network loading model is being developed which allows processor-to-processor interactions to be simulated, collisions (and respective probabilities) to be logged, collision-prone areas to be identified, and network control variable adjustments to be reentered as a means of examining and reducing collision-prone regimes that occur in the process of simulating a complete task sequence.

Zimmerman, W. F.↗

Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations

Advection-dispersion equations (ADEs) are commonly used to describe transport phenomena in porous media. Even though mature discretization-based numerical methods for ADEs exist, some challenges still remain, especially when it comes to solving advection-dominated forward ADEs and diffusion-dominated backward ADEs. The latter problem usually arises in the source identification context and leads to numerically unstable grid-based solutions that require a form of regularization or should be treated as an inverse problem that is computationally more expensive because it requires solving the forward problem multiple times. In this study, we propose a discretization-free approach based on the physics-informed neural network (PINN) method for solving coupled ADE and Darcy flow equations with space-dependent hydraulic conductivity. In this approach, the hydraulic conductivity, hydraulic head, and concentration fields are approximated with deep neural networks (DNNs). We assume that the conductivity field is given by its values on a grid, and we use these values to train the conductivity DNN. The head and concentration DNNs are trained by minimizing the residuals of the flow equation and ADE and using the initial and boundary conditions as additional constraints. The PINN method is applied to one- and two-dimensional forward ADE problems, where its performance for various P\'{e}clet numbers ($Pe$) is compared with the analytical and numerical solutions. We find that the PINN method is accurate with errors of less than 1\% and outperforms some conventional discretization-based methods for $Pe$ larger that 100. Next, we demonstrate that the PINN method remains accurate for the backward ADEs, with the relative errors in most cases staying under 5\% compared to the reference concentration field. Finally, we show that when available, the concentration measurements can be easily incorporated in the PINN method and significantly improve (by more than 50\% in the considered cases) the accuracy of the PINN solution of the backward ADE.

He, Qizhi↗