Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ITERATIVE NETWORK”

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 379 records · Page 21

Convergence Analysis of Fixed Point Chance Constrained Optimal Power Flow Problems

For optimal power flow problems with chance constraints, a particularly effective method is based on a fixed point iteration applied to a sequence of deterministic power flow problems. However, a priori, the convergence of such an approach is not necessarily guaranteed. Here this article analyses the convergence conditions for this fixed point approach, and reports numerical experiments including for large IEEE networks.

24 POWER TRANSMISSION AND DISTRIBUTION↗

GANpiler

Focal Area(s): Rather than augment or replace physical models with machine learning, we instead preserve the existing models and augment the underlying code with faster surrogate models created by generative adversarial networks (GAN). To leverage the performance optimization, we also propose a runtime system and user interfaces that allow prediction and tracking of accumulated error as well as dynamic, per-process decision making as to which model (if any) to use for each iteration. Science Challenge: This proposal sits at the nexus of two hard problems. First, climate models based on machine learning will be, by their nature, difficult to trust once their predictions begin diverging from the consensus. Second, compilers and hardware have been making only incremental performance gains for decades. GPGPUs have provided a welcome performance boost for codes that can take advantage of them, but there is no similar technology on the horizon to provide the next performance leap.

54 ENVIRONMENTAL SCIENCES↗

Evaluating pulse-shaping capabilities of next-generation pulsed power architectures

This project evaluated the pulse shaping capabilities of next-generation pulsed power (NGPP) architectures. NGPP architectures share several common attributes including multiple independent pulse-generation lines, a radial water-insulated impedance transformer, and a central vacuum insulated load region. A multi-module circuit model was developed, incorporating independent pulse-generation lines and a 2-D transmission line mesh of the radial impedance transformer to assess the effects of azimuthal asymmetry in pulse-shaped experiments. Circuit model simulations demonstrated that NGPP architectures are able to produce the the desired current pulse shapes for exemplar NGPP experiments. Additionally, the project explored automated methods for experiment design, including derivative -ree optimization and machine learning. Pulse-shaped experiments require designers to determine machine parameters that reliably produce the desired current pulse at the load, a process that typically relies on expert knowledge and iterative adjustments using the Z circuit model. Given the increased complexity of NGPP systems, this manual approach may be impractical. While the evaluated methods do not eliminate the need for manual iteration, they can reduce the time required for experiment design. Derivative-free optimization automates much of the trial-and-error process, providing a close starting point for manual adjustments or making small modifications to near-final designs. Meanwhile, deep neural network methods can generate a good qualitative match to the desired current pulse in under one second without requiring circuit model simulations.

42 ENGINEERING↗

Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data

Here, we present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems. The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation. The summary network encodes raw observations into a fixed-size vector of summary features, while the inference network generates samples of the approximate posterior distribution of the model parameters based on these summary features. The posterior samples are produced in a deep generative fashion by sampling from a latent Gaussian distribution and passing these samples through an invertible transformation. We construct this invertible transformation by sequentially alternating conditional invertible neural network and conditional neural spline flow layers. The summary and inference networks are trained simultaneously. We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations of the system’s hydraulic head responses. The conductivity field is represented with 706 degrees of freedom in the considered problem. Comparison with the likelihood-based iterative ensemble smoother PEST-IES method demonstrates that the proposed method accurately estimates the parameter posterior distribution and the observations’ predictive posterior distribution at a fraction of the inference time of PEST-IES.

conditional invertible neural network↗

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

FPGA remote update for nuclear environments

The Instituto de Plasmas e Fusao Nuclear (IPFN) has developed dedicated re-configurable modules based on field programmable gate array (FPGA) devices for several nuclear fusion machines worldwide. Moreover, new Advanced Telecommunication Computing Architecture (ATCA) based modules developed by IPFN are already included in the ITER catalogue. One of the requirements for re-configurable modules operating in future nuclear environments including ITER is the remote update capability. Accordingly, this work presents an alternative method for FPGA remote programing to be implemented in new ATCA based re-configurable modules. FPGAs are volatile devices and their programming code is usually stored in dedicated flash memories for properly configuration during module power-on. The presented method is capable to store new FPGA codes in Serial Peripheral Interface (SPI) flash memories using the PCIexpress (PCIe) network established on the ATCA back-plane, linking data acquisition endpoints and the data switch blades. The method is based on the Xilinx Quick Boot application note, adapted to PCIe protocol and ATCA based modules. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Progress and plan of KSTAR plasma control system upgrade

The plasma control system (PCS) has been one of essential systems in annual KSTAR plasma campaigns: starting from a single-process version in 2008, extensive upgrades are done through the previous 7 years in order to achieve major goals of KSTAR performance enhancement. Here, major implementations are explained in this paper. In consequences of successive upgrades, the present KSTAR PCS is able to achieve ~48 s of 500 kA plasma pulses with full real-time shaping controls and real-time NB power controls. It has become a huge system capable of dealing with 8 separate categories of algorithms, 26 actuators directly controllable during the shot, and real-time data communication units consisting of +180 analog channels and +600 digital input/outputs through the reflective memory (RFM) network. The next upgrade of the KSTAR PCS is planned in 2015 before the campaign. An overview of the upgrade layout will be given for this paper. The real-time system box is planned to use the CERN MRG-Realtime OS, an ITER-compatible standard operating system. New hardware is developed for faster real-time streaming system for future installations of actuators/diagnostics.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Data-driven models of nonautonomous systems

Nonautonomous dynamical systems are characterized by time-dependent inputs, which complicates the discovery of predictive models describing the spatiotemporal evolution of the state variables of quantities of interest from their temporal snapshots. When dynamic mode decomposition (DMD) is used to infer a linear model, this difficulty manifests itself in the need to approximate the time-dependent Koopman operators. Our approach is to approximate the original nonautonomous system with a modified system derived via a local parameterization of the time-dependent inputs. The modified system comprises a sequence of local parametric systems, which are subsequently approximated by a parametric surrogate model using the DRIPS (dimension reduction and interpolation in parameter space) framework. The offline step of DRIPS relies on DMD to build a linear surrogate model, endowed with reduced-order bases for the observables mapped from training data. The online step interpolates on suitable manifolds to construct a sequence of iterative parametric surrogate models; the target/test parameter points on these manifolds are specified by a local parameterization of the test time-dependent inputs. Here, we use numerical experimentation to demonstrate the robustness of our method and compare its performance with that of deep neural networks.

97 MATHEMATICS AND COMPUTING↗

Quantum adiabatic machine learning by zooming into a region of the energy surface

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. Here, we propose QAML-Z, an algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the receiver operating characteristic curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Iteration-based Linearized Distribution-level Locational Marginal Price for Three-phase Unbalanced Distribution Systems

Distributed energy resources (DERs) are rocking the utilities’ business landscape. It calls for competitive market environments that incentivize DERs to form maximum operating efficiency. Among proposed pricing schemes, distribution-level locational marginal price (DLMP) is effective in signaling the marginal generation cost differences driven by energy losses and network constraints. It can be derived from a distribution-level optimal power flow (OPF) framework, as it essentially presents the sensitivity of optimized generation cost towards incremental loads. However, due to the high resistance-to-inductance ratio and unbalanced characteristics of distribution networks, computational affordable DLMPs are highly challenged. This article provides a linear-approximated DLMP that can be solved efficiently and generalized to account for reactive power flow, three-phase unbalanced loads and meshed network structure. The successive linear programming technique is introduced to enhance the model accuracy. Case studies on an IEEE 123-Bus system validate its accuracy against a nonlinear benchmark and capability in offering proper incentives.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with convergence rate, where is the number of iterations.

reinforcement learning, structured learning, conve↗

The Necessity for Iteration in the Application of Numerical Simulation to EGS: Examples from the EGS Collab Test Bed 1

The United States Department of Energy, Geothermal Technologies Office (GTO) is funding a collaborative investigation of enhanced geothermal systems (EGS) processes at the meso-scale. This study, referred to as the EGS Collab project, is a unique opportunity for scientists and engineers to investigate the creation of fracture networks and circulation of fluids across those networks under in-situ stress conditions. The EGS Collab project is envisioned to comprise three experiments and the site for the first experiment is on the 4850 Level in phyllite of the Precambrian Poorman formation, at the Sanford Underground Research Facility, located at the former Homestake Gold Mine, in Lead, South Dakota. Principal objectives of the project are to develop a number of intermediate-scale field sites and to conduct well-controlled in situ experiments focused on rock fracture behavior and permeability enhancement. Data generated during these experiments will be compared against predictions of a suite of computer codes specifically designed to solve problems involving coupled thermal, hydrological, geomechanical, and geochemical processes. Comparisons between experimental and numerical simulation results will provide code developers with direction for improvements and verification of process models, build confidence in the suite of available numerical tools, and ultimately identify critical future development needs for the geothermal modeling community. Moreover, conducting thorough comparisons of models, modelling approaches, measurement approaches and measured data, via the EGS Collab project, will serve to identify techniques that are most likely to succeed at the Frontier Observatory for Research in Geothermal Energy (FORGE), the GTO's flagship EGS research effort. As noted, outcomes from the EGS Collab project experiments will serve as benchmarks for computer code verification, but numerical simulation additionally plays an essential role in designing these meso-scale experiments. This paper reviews specific numerical simulations supporting the design of experiments within Test Bed 1, a volume of phyllite rock under in-situ stress conditions off the western side of the West Access Drift on the 4850 Level, near Governor's Corner. Numerical simulations were executed prior to the start of hydraulic stimulation activities within Test Bed 1 following standard practices, using best estimates of principal stress conditions, thermal conditions, and the rock petrophysical properties, including geomechanical properties. These simulations indicated notching of the borehole would promote the initiation of transverse fractures, seismic magnitudes during the hydraulic stimulation would be below 0.1 magnitude on the Richter scale, a rock thermal conductivity of 5.0 W/m K yielded agreement with kISMET borehole temperature logs, back pressure on the production borehole would increase circulation across the test bed, and the production borehole would serve to halt propagation of the hydraulic fracture to the drift. Pre-existing natural fractures, heterogeneities in the rock properties, monitoring boreholes, and overlooked mine elements have prompted a second look at numerically modeling stimulation, fluid circulation, tracer migration, and thermal breakthrough. Numerical simulation is an invaluable tool for providing insight and understanding to complex physical processes. The success of simulations, however, often depends on including all of the salient features of the system in the founding conceptual model. This paper takes a retrospective look at examples where the conceptual model and simulation was sufficient to provide accurate forecasts and those where elements were missing, necessitating rethinking of the simulation.

15 GEOTHERMAL ENERGY↗

The Necessity for Iteration in the Application of Numerical Simulation to EGS: Examples from the EGS Collab Test Bed 1

The United States Department of Energy, Geothermal Technologies Office (GTO) is funding a collaborative investigation of enhanced geothermal systems (EGS) processes at the meso-scale. This study, referred to as the EGS Collab project, is a unique opportunity for scientists and engineers to investigate the creation of fracture networks and circulation of fluids across those networks under in-situ stress conditions. The EGS Collab project is envisioned to comprise three experiments and the site for the first experiment is on the 4850 Level in phyllite of the Precambrian Poorman formation, at the Sanford Underground Research Facility, located at the former Homestake Gold Mine, in Lead, South Dakota. Principal objectives of the project are to develop a number of intermediate-scale field sites and to conduct well-controlled in situ experiments focused on rock fracture behavior and permeability enhancement. Data generated during these experiments will be compared against predictions of a suite of computer codes specifically designed to solve problems involving coupled thermal, hydrological, geomechanical, and geochemical processes. Comparisons between experimental and numerical simulation results will provide code developers with direction for improvements and verification of process models, build confidence in the suite of available numerical tools, and ultimately identify critical future development needs for the geothermal modeling community. Moreover, conducting thorough comparisons of models, modelling approaches, measurement approaches and measured data, via the EGS Collab project, will serve to identify techniques that are most likely to succeed at the Frontier Observatory for Research in Geothermal Energy (FORGE), the GTO’s flagship EGS research effort. As noted, outcomes from the EGS Collab project experiments will serve as benchmarks for computer code verification, but numerical simulation additionally plays an essential role in designing these meso-scale experiments. This paper reviews specific numerical simulations supporting the design of experiments within Test Bed 1, a volume of phyllite rock under in-situ stress conditions off the western side of the West Access Drift on the 4850 Level, near Governor’s Corner. Numerical simulations were executed prior to the start of hydraulic stimulation activities within Test Bed 1 following standard practices, using best estimates of principal stress conditions, thermal conditions, and the rock petrophysical properties, including geomechanical properties. These simulations indicated notching of the borehole would promote the initiation of transverse fractures, seismic magnitudes during the hydraulic stimulation would be below 0.1 magnitude on the Richter scale, a rock thermal conductivity of 5.0 W/m K yielded agreement with kISMET borehole temperature logs, back pressure on the production borehole would increase circulation across the test bed, and the production borehole would serve to halt propagation of the hydraulic fracture to the drift. Pre-existing natural fractures, heterogeneities in the rock properties, monitoring boreholes, and overlooked mine elements have prompted a second look at numerically modeling stimulation, fluid circulation, tracer migration, and thermal breakthrough. Numerical simulation is an invaluable tool for providing insight and understanding to complex physical processes. The success of simulations, however, often depends on including all of the salient features of the system in the founding conceptual model. This paper takes a retrospective look at examples where the conceptual model and simulation was sufficient to provide accurate forecasts and those where elements were missing, necessitating rethinking of the simulation.

numerical simulation, EGS Collab, enhanced geother↗

Distribution Optimal Power Flow With Real-Time Price Elasticity

This letter investigates a new class of optimal power flow problem for distribution systems, where elastic loads respond to real-time nodal prices by adjusting their demands. A fixed point iteration algorithm is suggested to identify an equilibrium. A concise criterion is devised to judge convergence.

demand response↗

Model Cortical Association Fields Account for the Time Course and Dependence on Target Complexity of Human Contour Perception

Can lateral connectivity in the primary visual cortex account for the time dependence and intrinsic task difficulty of human contour detection? To answer this question, we created a synthetic image set that prevents sole reliance on either low-level visual features or high-level context for the detection of target objects. Rendered images consist of smoothly varying, globally aligned contour fragments (amoebas) distributed among groups of randomly rotated fragments (clutter). The time course and accuracy of amoeba detection by humans was measured using a two-alternative forced choice protocol with self-reported confidence and variable image presentation time (20-200 ms), followed by an image mask optimized so as to interrupt visual processing. Measured psychometric functions were well fit by sigmoidal functions with exponential time constants of 30-91 ms, depending on amoeba complexity. Key aspects of the psychophysical experiments were accounted for by a computational network model, in which simulated responses across retinotopic arrays of orientation-selective elements were modulated by cortical association fields, represented as multiplicative kernels computed from the differences in pairwise edge statistics between target and distractor images. Comparing the experimental and the computational results suggests that each iteration of the lateral interactions takes at least 37.5 ms of cortical processing time. Our results provide evidence that cortical association fields between orientation selective elements in early visual areas can account for important temporal and task-dependent aspects of the psychometric curves characterizing human contour perception, with the remaining discrepancies postulated to arise from the influence of higher cortical areas.

59 BASIC BIOLOGICAL SCIENCES↗

Approximate Inverse Chain Preconditioner: Iteration Count Case Study for Spectral Support Solvers

As the growing availability of computational power slows, there has been an increasing reliance on algorithmic advances. However, faster algorithms alone will not necessarily bridge the gap in allowing computational scientists to study problems at the edge of scientific discovery in the next several decades. Often, it is necessary to simplify or precondition solvers to accelerate the study of large systems of linear equations commonly seen in a number of scientific fields. Preconditioning a problem to increase efficiency is often seen as the best approach; yet, preconditioners which are fast, smart, and efficient do not always exist. Following the progress of [1], we present a new preconditioner for symmetric diagonally dominant (SDD) systems of linear equations. These systems are common in certain PDEs, network science, and supervised learning among others. Based on spectral support graph theory, this new preconditioner builds off of the work of [2], computing and applying a V-cycle chain of approximate inverse matrices. This preconditioner approach is both algebraic in nature as well as hierarchically-constrained depending on the condition number of the system to be solved. Due to its generation of an Approximate Inverse Chain of matrices, we refer to this as the AIC preconditioner. We further accelerate the AIC preconditioner by utilizing precomputations to simplify setup and multiplications in the con-text of an iterative Krylov-subspace solver. While these iterative solvers can greatly reduce solution time, the number of iterations can grow large quickly in the absence of good preconditioners. Initial results for the AIC preconditioner have shown a very large reduction in iteration counts for SDD systems as compared to standard preconditioners such as Incomplete Cholesky (ICC) and Multigrid (MG). We further show significant reduction in iteration counts against the more advanced Combinatorial Multigrid (CMG) preconditioner. We have further developed no-fill sparsification techniques to ensure that the computational cost of applying the AIC preconditioner does not grow prohibitively large as the depth of the V-cycle grows for systems with larger condition numbers. Our numerical results have shown that these sparsifiers maintain the sparsity structure of our system while also displaying significant reductions in iteration counts.1 2

97 MATHEMATICS AND COMPUTING↗

Approximate Inverse Chain Preconditioner: Iteration Count Case Study for Spectral Support Solvers

As the growing availability of computational power slows, there has been an increasing reliance on algorithmic advances. However, faster algorithms alone will not necessarily bridge the gap in allowing computational scientists to study problems at the edge of scientific discovery in the next several decades. Often, it is necessary to simplify or precondition solvers to accelerate the study of large systems of linear equations commonly seen in a number of scientific fields. Preconditioning a problem to increase efficiency is often seen as the best approach; yet, preconditioners which are fast, smart, and efficient do not always exist. Following the progress of [1], we present a new preconditioner for symmetric diagonally dominant (SDD) systems of linear equations. These systems are common in certain PDEs, network science, and supervised learning among others. Based on spectral support graph theory, this new preconditioner builds off of the work of [2], computing and applying a V-cycle chain of approximate inverse matrices. This preconditioner approach is both algebraic in nature as well as hierarchically-constrained depending on the condition number of the system to be solved. Due to its generation of an Approximate Inverse Chain of matrices, we refer to this as the AIC preconditioner. We further accelerate the AIC preconditioner by utilizing precomputations to simplify setup and multiplications in the con-text of an iterative Krylov-subspace solver. While these iterative solvers can greatly reduce solution time, the number of iterations can grow large quickly in the absence of good preconditioners. Initial results for the AIC preconditioner have shown a very large reduction in iteration counts for SDD systems as compared to standard preconditioners such as Incomplete Cholesky (ICC) and Multigrid (MG). We further show significant reduction in iteration counts against the more advanced Combinatorial Multigrid (CMG) preconditioner. We have further developed no-fill sparsification techniques to ensure that the computational cost of applying the AIC preconditioner does not grow prohibitively large as the depth of the V-cycle grows for systems with larger condition numbers. Our numerical results have shown that these sparsifiers maintain the sparsity structure of our system while also displaying significant reductions in iteration counts.1 2

97 MATHEMATICS AND COMPUTING↗

MPI-FAUN: An MPI-Based Framework for Alternating-Updating Nonnegative Matrix Factorization

Non-negative matrix factorization (NMF) is the problem of determining two non-negative low rank factors W and H, for the given input matrix A, such that A≈WH. NMF is a useful tool for many applications in different domains such as topic modeling in text mining, background separation in video analysis, and community detection in social networks. Despite its popularity in the data mining community, there is a lack of efficient parallel algorithms to solve the problem for big data sets. The main contribution of this work is a new, high-performance parallel computational framework for a broad class of NMF algorithms that iteratively solves alternating non-negative least squares (NLS) subproblems for W and H. It maintains the data and factor matrices in memory (distributed across processors), uses MPI for interprocessor communication, and, in the dense case, provably minimizes communication costs (under mild assumptions). The framework is flexible and able to leverage a variety of NMF and NLS algorithms, including Multiplicative Update, Hierarchical Alternating Least Squares, and Block Principal Pivoting. Our implementation allows us to benchmark and compare different algorithms on massive dense and sparse data matrices of size that spans from few hundreds of millions to billions. We demonstrate the scalability of our algorithm and compare it with baseline implementations, showing significant performance improvements. The code and the datasets used for conducting the experiments are available online.

2D↗