Search NASA⌕ Search

SEARCH · Search NASA

Results for “Stochastic optimization”

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 1,423 records · Page 79

Economic Impact of Harvesting Corn Stover under Time Constraint: The Case of North Dakota

This study examines the impact of stochastic harvest field time on profit maximizing potential of corn cob/stover collection in North Dakota. Three harvest options are analyzed using mathematical programming models. Our findings show that under the first corn grain only harvest option, farmers are able to complete harvesting corn grain and achieve maximum net income in a fairly short amount of time with existing combine technology. However, under the second simultaneous corn grain and cob (one-pass) harvest option, farmers generate lower net income compared to the net income of the first option. This is due to the slowdown in combine harvest capacity as a consequence of harvesting corn cobs. Under the third option of separate corn grain and stover (two-pass) harvest option, time allocation is the main challenge and our evidence shows that with limited harvest field time available, farmers find it optimal to allocate most of their time harvesting grain and then proceed to harvest and bale stover if time permits at the end of harvest season. The overall findings suggest is that it would be more economically efficient to allow a firm that is specialized in collecting biomass feedstock to participate in cob/stover harvest business.

Maung, Thein A.↗

Simulating Impacts of Extreme Events on Grids with High Penetrations of Wind Power Resources: Preprint

As extreme weather events become more frequent and intense, the demand for connecting grid operation and infrastructure planning with extreme event models will increase as well. We present a methodology for creating damage contingencies and scenarios for electric transmission grids during a hurricane strike. Included is an example case study: Hurricane Dolly damaging a synthetic 2000 bus test system during its landing in Southern Texas. Using WIND Toolkit meteorological data in conjunction with fragility curves for various electric grid elements, we generate stochastic damage scenarios that can be used for short- and long-term planning problems including emergency asset management. We perform statistical analysis of damages and quantify topological effects on example synthetic grid. Also, we investigate loss-of-load events during two-day economic dispatch experiment. Finally, we point out various shortcomings of our method and suggest how it can be improved.

contingencies↗

A Feature-Based Stochastic Permeability of Shale: Part 2–Predicting Field-Scale Permeability

We report that in a recent numerical study, it was demonstrated that characterizing reservoir permeability in terms of rock’s quality, as observed in lab and field, is the most important step before implementing an enhanced oil recovery operation or drilling a new well in a tight formation. In that study, it was shown that permeable features in shale-like organic matter (OM) and fractures were the only regions that allowed some reasonable movement of fluid, whereas inorganic matter (iOM) that occupies larger pore volume with significant saturation of hydrocarbons has extremely low permeability that did not allow any reasonable fluid movement to affect production. That study demonstrated the importance of characterizing reservoir heterogeneity in shale in order to economically exploit the shale resource. This study proposes a method to predict spatially heterogeneous field-scale permeability of shale in terms of natural fractures, and matrix (iOM and OM). The method developed in Part 1 is combined with a history-matching process that uses only readily available information from lab-scale and outcrop (information from geologists) to predict field-scale permeability. The method also ensures consistency between the underlying fracture distribution and optimally matched fracture lengths and their apertures, in addition to accounting for random distribution of fractures and their abundance. Optimized parameters of fracture distribution are used to generate multiple realizations of geological model, and the “best-fitting” (most-likely) permeability scenario is chosen by generating production response of each realization of the geological model and comparing them against the observed field production history. Finally, the novelty of the proposed to predict field-scale permeability is that it uses only readily available information while also ensuring consistency between the underlying fracture distribution and optimally matched fracture lengths and their apertures, in addition to accounting for random distribution of fractures and their abundance.

58 GEOSCIENCES↗

Bayesian inferences of electrical current delivered to shocked transmission lines

Small radius Bdot measurements of electrical current delivered by pulsed power devices are routinely compromised by electrode/convolute plasmas endemic to multiterawatt transmission lines. Inferences of delivered current unaffected by these issues have recently been obtained by numerically optimizing consistency between model predictions and local experimental velocimetry data, but these are only unique for shockless velocity profiles. In the paper we describe a more general Bayesian method capable of inferring current despite the presence of shocks. Additionally, we describe uncertainty estimates and use of the technique on experimental data. This technique is the first to provide uncertainty estimates on the full current trace delivered to an inertial confinement fusion target.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

New Methods of Uncertainty Quantification for Mixed Discrete-Continuous Variable Models

The scale and complexity of problems such as designing power grids or planning for climate change is growing rapidly, driving the development of complicated computer models. More complex models have longer run times and incorporate larger numbers of inputs, both continuous and discrete. For example, a detailed physics model may have continuous variables such as temperature, height or pressure along with discrete variables that indicate the choice of a material for a particular piece or the model to be used to calculate air flow. A power grid design model may have continuous variables such as generation capacity, power flow or demand along with discrete variables such as number of generators, number of transmission lines or binary variables to indicate whether or not a node is chosen for generation expansion. A growing awareness of uncertainty and the desire to make risk-informed decisions is causing uncertainty quantification (UQ) to be more routine and often required. UQ provides the underpinnings necessary to establish confidence in models and their use; therefore, much time and effort is being invested in creating efficient approaches for UQ. However, these efforts have been focused on models that take continuous variables as inputs. When discrete inputs are thrown into the mix, the basic approach is to repeat the UQ analysis for each combination of discrete inputs or some subset thereof; this rapidly becomes intractable. Because of the computational complexity inherent in mixed discrete-continuous models, researchers will focus on the uncertainty in their particular problem finding ways to take advantage of symmetries, simplifications or structures. For example, uncertainty propagation in certain dynamical systems can be efficiently carried out after various decomposition steps or uncertainty propagation in stochastic programming is confined to scenario generation. Unfortunately models are not always available for such machinations: models may be embedded in legacy codes, may utilize commercial off the shelf codes or may be created by stringing a series of codes together. It is also time consuming to start each problem from scratch; worse there may not be any simplifications or symmetries to take advantage of. For these situations a UQ method developed for any black box function is necessary. This report documents a new conceptual model for performing UQ for mixed discrete-continuous models which not only applies to any simulator function, but allows the use of the efficient UQ methods that have been developed for continuous inputs only. The conceptual model is presented and an estimation procedure is fleshed out for one class of problems. This is applied to variations of a mixed discrete-continuous optimization test problem. This procedure provides comparable results to a benchmark solution with fewer function evaluations.

Bauman, Lara E.↗

Differentiable Multiphysics Codes: A Breakthrough Technology for Simulation and Computing

This document summarizes the findings of a strategic planning exercise commissioned by the Weapons Simulation and Computing, Computational Physics (WSC/CP) program at the Lawrence Livermore National Laboratory (LLNL) in FY24. During the year, the committee met with multiple stakeholder communities to gather input, opinions, suggestions and concerns which have been incorporated throughout this document. The key findings from this exercise are summarized: • The development of multiphysics modelling and simulation (mod/sim) codes and software technologies, their deployment on exascale compute platforms, and their broad adoption across the NNSA is a major success of the Advanced Simulation and Computing (ASC) program and the Exascale Computing Project (ECP). Sustained investment in these core technologies is essential. • Today’s state of the art involves running ensembles of O(100K) simulations to perform uncertainty quantification (UQ) and design studies using multiple statistical methods such as Bayesian optimization to understand sensitivities of our models and explore parameterized design spaces. Even with exascale computing, we are practically limited to O(10) parameters in these studies since the number of simulations required to sample the space scales exponentially with the number of design parameters. • The data from these simulation ensembles is increasingly being used to train machine learned (ML) surrogates (or reduced order models, ROMs) which can then be used for optimization or real time design exploration. However, the trained surrogates are still limited in the number of parameters they can represent due to the sampling limitations previously noted. • Augmenting our suite of integrated multiphysics simulation codes, both current and emerging, with the ability to compute gradients (solution derivatives) of arbitrary simulation outputs with respect to (some or all) simulation inputs would be a breakthrough technology, opening the door to a new era of efficient and automated inverse design based on verified and validated mod/sim capabilities. • This capability, which we refer to as differentiable multiphysics codes (DMCs), would revolutionize both UQ and optimization studies by breaking the curse of dimensionality that presently limits our “gradient-free” ensemble based computing approach. A similar breakthrough occurred in the AI/ML community once the ability to compute gradients of arbitrary loss functions using back-propagation became commonplace. Gradient information from the multiphysics codes can also be used to dramatically improve the efficiency and scale of training of ML/ROM surrogates for rapid assessments. • Achieving this in our suite of codes will be a grand challenge, similar to the amount of effort that was required to transition from CPU to GPU computing. It will require buy-in from the entire WSC/CP program and beyond, including all integrated codes, physics and engineering models, third-party library dependencies and performance portability abstractions. It will also require investment in research and development of numerical methods for computing adjoints of coupled physics across multiple adaptively refined moving meshes and of stochastic (Monte Carlo) and mesh free (SPH) methods. • New software and numerical techniques, largely pioneered by the AI/ML community, make this feasible. Chief among these is automatic differentiation (AD), the ability to employ AD at point-wise locations in a physics calculation (instead of traditional black-box approaches) and the ability to perform “back-propagation in time” (or reverse mode AD) for non-linear partial differential equations (PDEs). Fundamentally, the conclusion of this strategic planning exercise is that the time is right to undertake a large scale effort in WSC, centered on the existing integrated codes, to continue the natural evolution of mod/sim in the age of AI/ML. Instead of attempting to replace mod/sim with purely data driven AI/ML models, we believe the key to success is to integrate AI/ML by building on top of the decades of hard-won knowledge and the verified/validated multiphysics modelling capability that is the hallmark of the ASC program.

97 MATHEMATICS AND COMPUTING↗

Towards real-time forecasting of natural gas production by harnessing graph theory for stochastic discrete fracture networks

In this work, we compare hydrocarbon production curves obtained from a graph-based reduced-order model with the high-fidelity Discrete Fracture Network (DFN) predictions for a fracture network created using data from a real shale site. We observe that the bounds for the high fidelity DFN model lie within the bounds for the reduced order model, implying that the reduced-order model provides a conservative estimate. Moreover, we found that except for first-passage times and late arriving mass, the production curves from the reduced-order model predict transport accurately. However, it is to be noted that the results are inspite of trading a three-dimensional geometry for a reduced system in the form of a graph, one that is 500–1000 times faster in terms of computational efficiency (for this particular application). In addition, we also compare the production curves for large drawdown and small drawdown using our graph approach. The reduced-order model is successful in showing that the long term productivity is higher in case of small drawdown although the initial productivity is higher for large drawdown. Thus, this reduced-order model offers great potential in uncertainty quantification for production, as well as in providing operators with information to make real-time decisions for optimal production.

03 NATURAL GAS↗

Enhancing Distribution System Resilience: A First-Order Meta-RL Algorithm for Critical Load Restoration

The increasing frequency of extreme events and the integration of distributed energy resources (DERs) into modern grids have elevated the need for resilient and efficient critical load restoration strategies in distribution systems. However, the stochastic nature of renewable DERs, limited energy resource availability and the intricate nonlinearities inherent in complex grid control problem make the problem challenging. Although reinforcement learning (RL) and warm-start RL methods have shown promising results, their performance often falls short in rapidly adapting to new, unseen situations and typically requires exhaustive problem-specific tuning. To address these gaps, we propose a First-Order Meta-based RL (FOM-RL) algorithm within an online framework for adaptive and robust critical load restoration. By harnessing local DERs as the enabling technology, FOM-RL allows the RL agent to swiftly adapt to new unseen scenarios by leveraging previously acquired knowledge of different tasks. Experimental results provide evidence that proposed algorithm learns more efficiently and showcases generalization capabilities across diverse set of operational scenarios. Moreover, a rigorous theoretical analysis yields a tight sublinear regret bound, sensitive to temporal variability, with a task-averaged optimality gap bounded by O(VM+D*/(Tsquare root(M))). These results suggest that optimality improves with task similarity and an increased number of tasks M, reaffirming the efficacy and scalability of the proposed approach in addressing the complexities of critical load restoration in distribution systems.

complexity theory↗

On the marginal value of electricity storage

We investigate the problem of characterizing the economic value of energy storage capacity to a wind power producer (WPP) that sells its energy in a conventional two-settlement electricity market. The WPP can offer a forward contract to supply power in the day-ahead market, subject to financial penalties for imbalances between the contracted power and the power that is delivered in real-time. We consider the setting in which the WPP has access to a co-located energy storage system, and can thus reshape its wind power production subject to its storage capacity constraints. Modeling wind power as a random process, we show that the problem of determining optimal forward contract offerings—given recourse with storage—is convex. We further establish that the maximum expected profit is concave and non-decreasing in the energy storage capacity, which reveals that the greatest marginal benefit from energy storage is derived from initial investment in small storage capacity. We provide a characterization of the marginal value of small energy storage capacity to the WPP. The formulae we derive shed light on the relationship between the value of storage and certain statistical measures of variability in the underlying wind power process.

25 ENERGY STORAGE↗

A multi-echelon supply chain model for municipal solid waste management system

In this paper, a multi-echelon multi-period solid waste management system (MSWM) was developed by inoculating with multi-echelon supply chain. Waste managers, suppliers, industries and distributors could be engaged in joint strategic planning and operational execution. The principal of MSWM system is interactive planning of transportation and inventory for each organization in waste collection, delivery and disposal. An efficient inventory management plan for MSWM would lead to optimized productivity levels under available capacities (e.g., transportation and operational capacities). The applicability of the proposed system was illustrated by a case with three cities, one distribution and two waste disposal facilities. Solutions of the decision variable values under different significant levels indicate a consistent trend. With an increased significant level, the total generated waste would be decreased, and the total transported waste through distribution center to waste to energy and landfill would be decreased as well.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

U.S. emissions of HFC-134a derived for 2008-2012 from an extensive flask-air sampling network: US emissions of HFC-134a

U.S. national and regional emissions of HFC-134a are derived for 2008-2012 based on atmospheric observations from ground and aircraft sites across the U.S. and a newly developed regional inverse model. Synthetic data experiments were first conducted to optimize the model assimilation design and to assess model-data mismatch errors and prior flux error covariances computed using a maximumlikelihood estimation technique. The synthetic data experiments also tested the sensitivity of derived national and regional emissions to a range of assumed prior emissions, with the goal of designing a system that was minimally reliant on the prior. We then explored the influence of additional sources of error in inversions with actual observations, such as those associated with background mole fractions and transport uncertainties. Estimated emissions of HFC-134a range from 52 to 61 Gg yr -1 for the contiguous U.S. during 2008-2012 for inversions using air transport from Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model driven by the 12km resolution meteorogical data from North American Mesoscale Forecast System (NAM12) and all tested combinations of prior emissions and background mole fractions. Estimated emissions for 2008-2010 were 20% lower when specifying alternative transport from Stochastic Time-Inverted Lagrangian Transport (STILT) model driven by the Weather Research and Forecasting (WRF) meteorology. Our estimates (for HYSPLIT-NAM12) are consistent with annual emissions reported by U.S. Environmental Protection Agency for the full study interval. The results suggest a 10-20% drop in U.S. national HFC-134a emission in 2009 coincident with a reduction in transportation-related fossil fuel CO 2 emissions, perhaps related to the economic recession. All inversions show seasonal variation in national HFC-134a emissions in all years, with summer emissions greater than winter emissions by 20-50%.

54 ENVIRONMENTAL SCIENCES↗

Projective Integral Updates for High-Dimensional Variational Inference

Variational inference is an approximation framework for Bayesian inference that seeks to improve quantified uncertainty in predictions by optimizing a simplified distribution over parameters to stand in for the full posterior. Capturing model variations that remain consistent with training data enables more robust predictions by reducing parameter sensitivity. This work introduces a fixed-point optimization for variational inference that is applicable when every feasible log density can be expressed as a linear combination of functions from a given basis. In such cases, the optimizer becomes a fixed-point of projective integral updates. When the basis spans univariate quadratics in each parameter, the feasible distributions are Gaussian mean-fields and the projective integral updates yield quasi-Newton variational Bayes (QNVB). Other bases and updates are also possible. Since these updates require high-dimensional integration, this work begins by proposing an efficient quasirandom sequence of quadratures for mean-field distributions. Each iterate of the sequence contains two evaluation points that combine to correctly integrate all univariate quadratic functions and, if the mean-field factors are symmetric, all univariate cubics. More importantly, averaging results over short subsequences achieves periodic exactness on a much larger space of multivariate polynomials of quadratic total degree. The corresponding variational updates require four loss evaluations with standard (not second-order) backpropagation to eliminate error terms from over half of all multivariate quadratic basis functions. Furthermore, this integration technique is motivated by first proposing stochastic blocked mean-field quadratures, which may be useful in other contexts. A PyTorch implementation of QNVB allows for better control over model uncertainty during training than competing methods. Experiments demonstrate superior generalizability for multiple learning problems and architectures.

Gaussian mean-field↗

Scalable and Memory-Efficient Algorithms for Controlling Networked Epidemic Processes Using Multiplicative Weights Update Method

We study the problem of designing scalable algorithms to find effective intervention strategies for controlling stochastic epidemic processes on networks. This is a common problem arising in agent based models for epidemic spread. Previous approaches to this problem focus on either heuristics with no guarantees or approximation algorithms that scale only to networks corresponding to county-sized populations, typically, with less than a million nodes. In particular, the mathematical-programming based approaches need to solve the Linear Program (LP) relaxation of the problem using an LP solver, which restricts the scalability of this approach. In this work, we overcome this restriction by designing an algorithm that adapts the multiplicative weights update (MWU) framework, along with the sample average approximation (SAA) technique, to approximately solve the linear program (LP) relaxation for the problem. To scale this approach further, we provide a memory-efficient algorithm that enables scaling to large networks, corresponding to country-size populations, with over 300 million nodes and 30 billion edges. Furthermore, we show that this approach provides near-optimal solutions to the LP in practice.

Sambaturu, Prathyush↗

Benchmarking quantum trial wavefunctions for phaseless auxiliary-field quantum Monte Carlo

The phaseless auxiliary-field quantum Monte Carlo (ph-AFQMC) method is a stochastic imaginary-time projection technique for computing ground-state properties of strongly correlated quantum systems, with accuracy that depends critically on the choice of trial wavefunction. Here, we investigate ph-AFQMC with trial states prepared using parameterized quantum circuits. In this work, we present a comprehensive benchmarking study of quantum trial wavefunctions spanning unitary coupled-cluster, Hamiltonian-informed, Jastrow-inspired, and adaptively constructed ansatze. The benchmarking evaluates accuracy, expressibility, and scalability of these ansatze within the QC-AFQMC framework. We test these ansatze on linear hydrogen chains under bond stretching and find that several ansatz families produce chemically accurate ph-AFQMC energies across the dissociation curve. We have performed simulations using the CUDA-Q quantum development platform on the GPU partition of the Perlmutter supercomputer. When comparing ansatze at similar numbers of variational parameters, we find that different ansatz families yield comparable ph-AFQMC results despite exhibiting substantially different variational energies, optimization costs, and circuit depths. Our results indicate that the variational energy of an ansatz is not always a reliable indicator of its quality for ph-AFQMC and reveal instances of over-parameterization. In the strongly correlated regime, trial wavefunctions obtained from adaptive ansatze, exemplified here by ADAPT-VQE with the UCCSD operator pool, can outperform their fixed-ansatz counterparts (UCCSD) in terms of projected energies while using substantially more compact circuits, providing a flexible route to optimize quantum resources within the ph-AFQMC framework.

Rofougaran, Rod [LBNL, Berkeley; Columbia U.; PNL,↗

Resilient Observer Design for Cyber-Physical Systems with Data-Driven Measurement Pruning

Resilient observer design for Cyber-Physical Systems (CPS) in the presence of adversarial false data injection attacks (FDIA) is an active area of research. The existing state-of-the-art algorithms tend to break down as more and more knowledge of the system is built into the attack model; also as the percentage of attacked nodes increases. From the view of optimization theory, the problem is often cast as a classical error correction problem for which a theoretical limit of has been established as the maximum percentage attacked nodes for which state recovery is guaranteed. Beyond this limit, the performance of -minimization based schemes, for instance, deteriorates rapidly. Similar performance degradation occurs for other types of resilient observers beyond certain percentages of attacked nodes. In order to increase the corresponding percentage of attacked nodes for which state recoveries can be guaranteed, researchers have begun to incorporate prior information into the underlying resilient observer design framework. For the most pragmatic cases, this prior information is often obtained through a data-driven machine learning process. Existing results have shown a strong positive correlation between the maximum attacked percentages that can be tolerated and the accuracy of the data-driven model. Motivated by these results, this chapter examines the case for pruning algorithms designed to improve the Positive Prediction Value (PPV) of the resulting prior information, given stochastic uncertainty characteristics of the underlying machine learning model. Theoretical quantification of the achievable improvement is given. Simulation results show that the pruning algorithm significantly increases the maximum correctable percentage of attacked nodes, even for machine learning model whose prediction power is comparable to the random flip of a coin.

Resilient Observer, Cyber-physical Systems, Data-D↗

Reconfiguring Power Systems to Minimize Cascading Failures: Models and Algorithms

The main goal of this project was to develop new scientific tools, based on optimization techniques, with the purpose of controlling and modeling cascading failures of electrical power transmission systems. We have developed a high-quality tool for simulating cascading failures. The problem of how to control a cascade was addressed, with the aim of stopping the cascade with a minimum of load lost. Yet another aspect of cascade is the investigation of which events would trigger a cascade, or more appropriately the computation of the most harmful initiating event given some constraint on the severity of the event. One common feature of the cascade models described (indeed, of several of the cascade models found in the literature) is that we study thermally-induced line tripping. We have produced a study that accounts for exogenous randomness (e.g. wind and ambient temperature) that could affect the thermal behavior of a line, with a focus on controlling the power flow of the line while maintaining safe probability of line overload. This was done by means of a rigorous analysis of a stochastic version of the heat equation. We incorporated a model of randomness in the behavior of wind power output; again modeling an OPF-like problem that uses chance-constraints to maintain low probability of line overloads; this work has been continued so as to account for generator dynamics as well.

24 POWER TRANSMISSION AND DISTRIBUTION↗

On Maximal Hard-Core Thinnings of Stationary Particle Processes

The present paper studies existence and distributional uniqueness of subclasses of stationary hard-core particle systems arising as thinnings of stationary particle processes. These subclasses are defined by natural maximality criteria. We investigate two specific criteria, one related to the intensity of the hard-core particle process, the other one being a local optimality criterion on the level of realizations. In fact, the criteria are equivalent under suitable moment conditions. We show that stationary hard-core thinnings satisfying such criteria exist and are frequently distributionally unique. More precisely, distributional uniqueness holds in subcritical and barely supercritical regimes of continuum percolation. Additionally, based on the analysis of a specific example, we argue that fluctuations in grain sizes can play an important role for establishing distributional uniqueness at high intensities. Finally, we provide a family of algorithmically constructible approximations whose volume fractions are arbitrarily close to the maximum.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

An Online Dynamic Amplitude-Correcting Gradient Estimation Technique to Align X-ray Focusing Optics

High-brightness X-ray pulses, as generated at synchrotrons and X-ray free electron lasers (XFELs), are used in a variety of scientific experiments. At these facilities, measurements often require optical equipment, e.g Compound Refractive Lenses (CRLs) to be precisely aligned and focused. The lateral alignment of CRLs to a beamline requires precise positioning along four axes: two translational, and the two rotational. At a synchrotron, alignment is often accomplished manually. However, XFEL beamlines present a beam brightness that fluctuates stochastically, making manual alignment a time-consuming endeavor. Automation using simplex or classic stochastic descent often fails, given the errant gradient estimates. Herein we present a dynamic-amplitude correction to the usual gradient based on the combination of a generalized finite difference stencil and a time-dependent sampling pattern. Intensity is recorded periodically, then used to normalize numerical derivatives against fluctuations. Error expectation is analyzed, and efficacy is demonstrated on classic benchmarks. We provide a proof of concept by laterally aligning optics on a simulated XFEL beamline using data recorded at both synchrotron and XFEL facilities.

97 MATHEMATICS AND COMPUTING↗