Search NASA⌕ Search

SEARCH · Search NASA

Results for “Regularization”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Creep ductility limiting mechanisms in an additively manufactured Al-Ce-Ni-Mn-Zr alloy

Tensile creep response and cavitation damage evolution in an additively manufactured Al-7.5Ce-4.5Ni-0.4Mn-0.7Zr (wt%) alloy with peak-aging and overaging treatments were investigated in the 300–400 ºC range. Microstructural heterogeneity and its response to heat treatment and subsequent creep deformation were studied to understand the interplay between cavity formation, creep lifetime and ductility. Increasing the applied stress activated the nucleation of more cavities, an experimental observation that is well described using the vacancy accumulation model. Cavities nucleated prematurely due to localized plasticity in the denuded zones that formed at/near melt-pool or grain boundaries. Microstructure/deformation heterogeneity with consequent evolution of stress triaxiality, especially at lower stresses, causes accelerated cavitation, thus producing low creep ductility (∼ 0.2–2.4 %), compared to (∼12–21 %) ductility of the alloy measured by regular tensile tests at equivalent temperatures. A constrained diffusional cavity growth mechanism with continuous cavity nucleation during creep is established as the dominant mechanism, implying that cavitation involves vacancy diffusion, yet its growth rate is dictated by the minimum creep rate. In conclusion, the ductility-limiting creep and cavitation mechanisms discussed here provide new insight into the creep behavior of 3D-printed metallic alloys.

Additive manufacturing↗
DOE OSTI2026

Hollow-structured Ni-N-C catalysts for highly selective CO 2 electroreduction

Atomically dispersed single-atom catalysts have emerged as promising non-precious catalyst alternatives to expensive Ag and Au catalysts for electrochemical CO 2 reduction reaction (CO 2 RR). In particular, nickel-nitrogen-carbon (Ni-N-C) catalysts have demonstrated a high faradaic efficiency (FE) toward CO formation at low overpotentials. Nonetheless, the exact nature of Ni active sites under CO 2 RR remains elusive and conventional Ni-N-C catalysts are limited by microporosity and low density of Ni single atoms, hindering performance in CO 2 electrolyzers. Here, we report the synthesis of hollow-structured Ni-N-C ( hs -Ni-N-C) catalysts via a post-synthesis modification (PSM) strategy using partial ligand exchange of 2-methylimidazole with 3-amino-1,2,4-triazole. This approach enables the formation of a hollow structure, resulting in more than a twofold increase in Ni atom density compared to regular Ni-N-C (r-Ni-N-C). In a zero-gap CO 2 electrolyzer, the optimized hs -Ni-N-C allows for achieving an FE CO of 97% at a current density of > 100 mA cm⁻ 2 , while maintaining high CO selectivity with stable performance over 100 h at 2.5 V. hs-Ni-N-C shows a more than sevenfold increase in the CO partial current density relative to r-Ni-N-C resulting from the combined effects of a higher density of Ni single-atom sites, improved kinetics, and lower transport resistance under the operating conditions, as indicated by electrochemical impedance spectra and distribution of relaxation times analysis. Operando high energy-resolution X-ray absorption spectroscopy (XAS) reveals that atop-bonded CO on Ni single sites induces dynamic transformations of the Ni–N coordination environment, leading to a symmetric coordination structure of hs -Ni-N-C. Under CO 2 RR, the catalysts undergo a more pronounced structural change and form a minor fraction of Ni nanoparticles. Density functional theory calculations are consistent with the XAS results and provide molecular insights showing that the interplay between protonation and CO adsorption leads to adsorbate-induced restructuring of the Ni single atom. This work demonstrates the synergistic role of hollow structure and high-density Ni atoms in governing CO 2 RR selectivity and provides mechanistic insights into the structural dynamics of single-atom catalysts under operating conditions.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Rapid DNA unwinding accelerates genome editing by engineered CRISPR-Cas9

Thermostable clustered regularly interspaced short palindromic repeats (CRISPR) and CRISPR-associated (Cas9) enzymes could improve genome-editing efficiency and delivery due to extended protein lifetimes. However, initial experimentation demonstrated Geobacillus stearothermophilus Cas9 (GeoCas9) to be virtually inactive when used in cultured human cells. Laboratory-evolved variants of GeoCas9 overcome this natural limitation by acquiring mutations in the wedge (WED) domain that produce >100-fold-higher genome-editing levels. Cryoelectron microscopy (cryo-EM) structures of the wild-type and improved GeoCas9 (iGeoCas9) enzymes reveal extended contacts between the WED domain of iGeoCas9 and DNA substrates. Biochemical analysis shows that iGeoCas9 accelerates DNA unwinding to capture substrates under the magnesium-restricted conditions typical of mammalian but not bacterial cells. These findings enabled rational engineering of other Cas9 orthologs to enhance genome-editing levels, pointing to a general strategy for editing enzyme improvement. Together, these results uncover a new role for the Cas9 WED domain in DNA unwinding and demonstrate how accelerated target unwinding dramatically improves Cas9-induced genome-editing activity.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Isochronous and period-doubling diagrams for symplectic maps of the plane

Symplectic mappings of the plane serve as key models for exploring the fundamental nature of complex behavior in nonlinear systems. Central to this exploration is the effective visualization of stability regimes, which enables the interpretation of how systems evolve under varying conditions. While the area-preserving quadratic Hénon map has received significant theoretical attention, a comprehensive description of its mixed parameter-space dynamics remain lacking. This limitation arises from early attempts to reduce the full two-dimensional phase space to a one-dimensional projection, a simplification that resulted in the loss of important dynamical features. Consequently, there is a clear need for a more thorough understanding of the underlying qualitative aspects. This paper aims to address this gap by revisiting the foundational concepts of reversibility and associated symmetries, first explored in the early works of G.D. Birkhoff. We extend the original framework proposed by Hénon by adding a period-doubling diagram to his isochronous diagram, which allows to represents the system’s bifurcations and the groups of symmetric periodic orbits that emerge in typical bifurcations of the fixed point. A qualitative and quantitative explanation of the main features of the region of parameters with bounded motion is provided, along with the application of this technique to other symplectic mappings, including cases of multiple reversibility. Modern chaos indicators, such as the Reversibility Error Method (REM) and the Generalized Alignment Index (GALI), are employed to distinguish between various dynamical regimes in the mixed space of variables and parameters. These tools prove effective in differentiating regular and chaotic dynamics, as well as in identifying twistless orbits and their associated bifurcations. Additionally, we discuss the application of these methods to real-world problems, such as visualizing dynamic aperture in accelerator physics, where our findings have direct relevance.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Development of a SnO 2 -based 44 Ti/ 44 Sc generator for medical applications

Towards application of 44 Sc for diagnostic nuclear medicine, a 44 Ti/ 44 Sc generator based on an inorganic resin has been evaluated. Unlike other radionuclide generators used for medical applications, the long-term retention of the parent 44 Ti is vital due to its long half life. In this work, tin dioxide (SnO 2 ), a robust inorganic-based resin, has been synthesized and used as the stationary phase for a 44 Ti/ 44 Sc generator. The sorption behavior of 44 Ti/ 44 Sc was tested on SnO 2 with varying acids, concentrations, and times. Preliminary batch study results showed >88 % 44 Ti retention to the resin at lower acid concentrations (0.05 M HNO 3 and 0.05 M HCl). A pilot generator was evaluated for a year, demonstrating 85.3 ± 2.8 % 44 Sc elution yields and 0.71 ± 0.14 % 44 Ti breakthrough in 5 M HNO 3 . Based on capacity studies, a 7.4 MBq (200 µCi) upscaled generator system was constructed for further evaluation of the SnO 2 resin stability and the efficacy of the eluted 44 Sc for radiolabeling. 44 Sc could be regularly eluted from this generator in 5 M HNO 3 with an overall average radiochemical yield 84.7 ± 9.5 %. Post-elution processing of the 44 Sc with DGA-normal resin removed all 44 Ti present and allowed for high 44 Sc-DOTA labeling yields of 94.2 ± 0.5 %. Overall, SnO 2 has been shown to be a viable material for a 44 Ti/ 44 Sc generator.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2024

D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems. However, challenges arise when dealing with input functions that exhibit heterogeneous properties, requiring multiple sensors to handle functions with minimal regularity. To address this issue, discretization-invariant neural operators have been used, allowing the sampling of diverse input functions with different sensor locations. However, existing frameworks still require an equal number of sensors for all functions. We propose a novel distributed approach to further relax the discretization requirements and solve the heterogeneous dataset challenges. Our method involves partitioning the input function space and processing individual input functions using independent and separate neural networks. A centralized neural network is used to handle shared information across all output functions. This distributed methodology reduces the number of gradient descent back-propagation steps, improving efficiency while maintaining accuracy. Here, we demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators and present three numerical examples to validate its performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A variational phase-field framework for thermal softening and dynamic ductile fracture

A variational phase field model for dynamic ductile fracture is presented. Here, the model is designed for elasto-viscoplastic materials subjected to rapid deformations in which the effects of heat generation and material softening are dominant. The variational framework allows for the consistent inclusion of plastic dissipation in the heat equation as well as thermal softening. It employs a coalescence function to degrade fracture energy during regimes of high plastic flow. A variationally consistent form of the Johnson–Cook model is developed for use with the framework. Results from various benchmark problems in dynamic ductile fracture are presented to demonstrate capabilities. In particular, the ability of the model to regularize shear band formation and subsequent damage evolution in two- and three-dimensional problems is demonstrated. Importantly, these phenomena are naturally captured through the underlying physics without the need for phenomenological criteria such as stability thresholds for the onset of shear band formation.

42 ENGINEERING↗
DOE OSTI2025

An end-to-end deep learning method for solving nonlocal Allen–Cahn and Cahn–Hilliard phase-field models

Here, we propose an efficient end-to-end deep learning method for solving nonlocal Allen–Cahn (AC) and Cahn–Hilliard (CH) phase-field models. One motivation for this effort emanates from the fact that discretized partial differential equation-based AC or CH phase-field models result in diffuse interfaces between phases, with the only recourse for remediation is to severely refine the spatial grids in the vicinity of the true moving sharp interface whose width is determined by a grid-independent parameter that is substantially larger than the local grid size. In this work, we introduce non-mass conserving nonlocal AC or CH phase-field models with regular, logarithmic, or obstacle double-well potentials. Because of non-locality, some of these models feature totally sharp interfaces separating phases. The discretization of such models can lead to a transition between phases whose width is only a single grid cell wide. Another motivation is to use deep learning approaches to ameliorate the otherwise high cost of solving discretized nonlocal phase-field models. To this end, loss functions of the customized neural networks are defined using the residual of the fully discrete approximations of the AC or CH models, which results from applying a Fourier collocation method and a temporal semi-implicit approximation. To address the long-range interactions in the models, we tailor the architecture of the neural network by incorporating a nonlocal kernel as an input channel to the neural network model. We then provide the results of extensive computational experiments to illustrate the accuracy, predictive capabilities, and cost reductions of the proposed method.

42 ENGINEERING↗
DOE OSTI2025

Non-intrusive reduced-order modeling for dynamical systems with spatially localized features

This work presents a non-intrusive reduced-order modeling framework for dynamical systems with spatially localized features characterized by slow singular value decay. The proposed approach builds upon two existing methodologies for reduced and full-order non-intrusive modeling, namely Operator Inference (OpInf) and sparse Full-Order Model (sFOM) inference. We decompose the domain into two complementary subdomains that exhibit fast and slow singular value decay. The dynamics of the subdomain exhibiting slow singular value decay are learned with sFOM while the dynamics with intrinsically low dimensionality on the complementary subdomain are learned with OpInf. The resulting, coupled OpInf-sFOM formulation leverages the computational efficiency of OpInf and the high resolution of sFOM, and thus enables fast non-intrusive predictions for conditions beyond those sampled in the training data set. A novel regularization technique with a closed-form solution based on the Gershgorin disk theorem is introduced to promote stable sFOM and OpInf models. We also provide a data-driven indicator for subdomain selection and ensure solution smoothness over the interface via a post-processing interpolation step. We evaluate the efficiency of the approach in terms of offline and online speedup through a quantitative, parametric computational cost analysis. We demonstrate the coupled OpInf-sFOM formulation for two test cases: a one-dimensional Burgers’ model for which accurate predictions beyond the span of the training snapshots are presented, and a two-dimensional parametric model for the Pine Island Glacier ice thickness dynamics, for which the OpInf-sFOM model achieves an average prediction error on the order of 1% with an online speedup factor of approximately 8$\times$ compared to the numerical simulation.

42 ENGINEERING↗
DOE OSTI2025

An adaptive, data-driven multiscale approach for dense granular flows

The accuracy of coarse-grained continuum models of dense granular flows is limited by the lack of high-fidelity closure models for granular rheology. One approach to addressing this issue, referred to as the hierarchical multiscale method, is to use a high-fidelity fine-grained model to compute the closure terms needed by the coarse-grained model. The difficulty with this approach is that the overall model can become computationally intractable due to the high computational cost of the high-fidelity model. In this work, we describe a multiscale modeling approach for dense granular flows that utilizes neural networks trained using high-fidelity discrete element method (DEM) simulations to approximate the constitutive granular rheology for a continuum incompressible flow model. Our approach leverages an ensemble of neural networks to estimate predictive uncertainty that allows us to determine whether the rheology at a given point is accurately represented by the neural network model. Additional DEM simulations are only performed when needed, minimizing the number of additional DEM simulations required when updating the rheology. This adaptive coupling significantly reduces the overall computational cost of the approach while controlling the error. In addition, the neural networks are customized to learn regularized rheological behavior to ensure well-posedness of the continuum solution. We first validate the approach using two-dimensional steady-state and decelerating inclined flows. We then demonstrate the efficiency of our approach by modeling three-dimensional sub-aerial granular column collapse for varying initial column aspect ratios, where our multiscale method compares well with the computationally expensive computational fluid dynamics (CFD)-DEM simulation.

Dense granular flows↗
DOE OSTI2025

A Green’s function fast multipole method for computation of micromechanical fields in heterogeneous materials

Computation of micromechanical fields in heterogeneous materials is usually performed using either the finite element method or the Green’s function method based on FFTs. The finite element method allows for accurate discretization and for non-periodic boundary conditions but is computationally expensive. On the other hand, the FFT-based method is computationally efficient but requires discretization on a regular grid of hexahedral voxels. In this paper, a Green’s function method allowing for accurate discretization using tetrahedral elements and for non-periodic boundary conditions is proposed. The convolution is computed using the fast multipole method, which provides good accuracy even for low-order expansion due to the fast decay of interactions between elements. The proposed Green’s function fast multipole method is verified by comparison with analytical and FFT-based solutions. Furthermore, the computational time is analyzed and compared to the FFT-based method for non-periodic convolution. Finally, effective properties of an elastic polycrystalline microstructure containing thin intergranular cracks are computed and analyzed.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Differentiable lagrangian shock hydrodynamics with application to stable shock acceleration of density interfaces

We develop a gradient based optimization approach for the equations of compressible, Lagrangian hydrodynamics and demonstrate how it can be employed to automatically uncover strategies to control hydrodynamic instabilities arising from shock acceleration of density interfaces. Strategies for controlling the Richtmyer-Meshkov instability (RMI) are of great benefit for inertial confinement fusion (ICF) where shock interactions with many small imperfections in the density interface lead to instabilities which rapidly grow over time. These instabilities lead to mixing which, in the case of laser driven ICF, quenches the runaway fusion process ruining the potential for positive energy return. Here, we demonstrate that control of these instabilities can be achieved by optimization of initial conditions with ( > 100) parameters. Optimizing over a large parameter space like this is not possible with gradient-free optimization strategies. This requires computation of the gradient of the outputs of a numerical solution to the equations of Lagrangian hydrodynamics with respect to the inputs. We show that the efficient computation of these gradients is made possible via a judicious application of (i) adjoint methods, the exact formal representation of sensitivities involving partial differential equations, and (ii) automatic differentiation (AD), the algorithmic calculation of derivatives of functions. Careful regularization of multiple operators including artificial viscosity and timestep control is required. We perform design optimization of > 100 parameter energy field driving the Richtmyer Meshkov instability showing significant suppression while simultaneously enhancing the acceleration of the interface relative to a nominal baseline case.

Hydrophysics↗
DOE OSTI2026

Accelerating multigrid with streaming chiral SVD for Wilson fermions in lattice QCD

A modification to the setup algorithm for the multigrid preconditioner of Wilson fermions in lattice QCD is presented. A larger basis of test vectors than that used in regular multigrid is calculated by the smoother and truncated by singular value decomposition on the chiral components of the test vectors. The truncated basis is used to form the prolongation and restriction matrices of the multigrid hierarchy. This modification of the setup method is demonstrated to increase the convergence of linear solvers on an anisotropic lattice with m π ≈ 239 MeV from the Hadron Spectrum Collaboration and an isotropic lattice with m π ≈ 220 MeV from the MILC Collaboration. The lattice volume dependence of the method is also examined. Increasing the number of test vectors improves speedup up to a point, but storing these vectors becomes impossible in limited memory resources such as GPUs. To address storage cost, we implement a streaming singular value decomposition of the basis of test vectors on the chiral components and demonstrate a decrease in the number of fine level iterations by a factor of 1.7 for m q ≈ m crit

Iterative methods↗
DOE OSTI2026

Fast solvers for tokamak fluid models with PETSc

Multigrid (MG) is widely recognized as a highly effective solver for the model problem, the Laplacian, but textbook MG fails on most problems of interest. MG methods have been applied to complex, real-world applications with careful consideration of the physical model and discretization. In this work we develop the first step in applying MG methods to science and engineering relevant magnetohydrodynamics (MHD) tokamak models in the M3D-C1 (https://m3dc1.pppl.gov) fusion energy science code. The semi-implicit time integrator in M3D-C1 is composed of many linear solves. The implicit advance of the momentum equation is the most challenging and is the focus of this work. The current production solver in M3D-C1 is a block Jacobi (BJ) preconditioner within a Krylov solver, where blocks group degrees of freedom on planes of constant toroidal coordinate. BJ convergence degrades as the number of planes increases due to the spectral properties of the matrix preconditioned with BJ. The partially magnetic field-aligned, regular toroidal grid structure in M3D-C1 is amenable to semi-coarsening geometric MG in the toroidal direction. This paper develops such a solver and demonstrates competitive performance on a runaway electron model of a SPARC (https://cfs.energy/technology/sparc) disruption, and superior robustness on a stellarator model on which the BJ solver fails to converge.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
DOE OSTI2025

Ice storage model-predictive control in an office building with PV: scenario, error and sensitivity analysis

Thermal energy storage (TES) can enable more building-sited renewable electricity generation and lower utility bill costs for buildings owners and occupants, especially when there are high demand and variable time-of-use (TOU) charges. A model predictive control (MPC) strategy can offer additional savings over a schedule-based control with added complexity and reliance on forecasts. Here, this study examines savings for medium office buildings with chiller plants in three locations with building-installed solar photovoltaics (PV) to understand the impact of MPC. Control setpoints are fixed by a schedule-based control or optimized by nonlinear MPC. These control setpoints are actuated within EnergyPlus building models to simulate the utility cost of the chiller plant. NLP solutions can be unstable or unrealistic, but our results show that by regularizing the NLP, the solutions can be reasonably followed by the building model. MPC models make simplifications that lead to errors once the controller is participating in and changing the operation of the building. These errors average 9 % across the cases, showing that the most important parts of the system are represented. The no-thermal load costs are computed to show that the optimization can in some cases achieve both the minimum TOU and minimum monthly demand costs by demand management while reducing TOU energy costs by energy arbitrage. The MPC saves 35–66 % in the annual chiller plant operating costs, which is an additional savings above the schedule by 1–33 %. PV and TES are complementary and mostly independent, but a load with PV often results in better performance for the schedule. Our case study and sensitivity analysis show the importance of modeling and optimization for complex rates, but also the circumstances wherein a simpler strategy achieves the same performance with less potential for error.

14 SOLAR ENERGY↗
DOE OSTI2026

Surrogate model evaluation and building energy benchmarking for commercial buildings

Building energy consumption benchmarking involves challenges associated with various energy patterns for different building types; heating, ventilating, and air-conditioning (HVAC) system types; and climates. Given significant variation in energy use patterns, accurate prediction of long-term energy use using surrogate models remains challenging. Multiple linear regression (MLR) is commonly used for building energy benchmarking because of its simple structure; however, it lacks accuracy compared to other black-box models. Although many studies have compared surrogate models and offer guidance on model selection based on metrics, they do not provide detailed analysis on improving the surrogate model accuracy. In this paper, we implement a surrogate model using polynomial ridge regression (i.e., MLR with interaction terms combined with ridge regularization) for small office and retail strip mall buildings across six HVAC system types and all climate zones, for electricity and natural gas in baseline and proposed scenarios. A simulation workflow is developed using OpenStudio TM /EnergyPlus TM to generate simulation data using measures over a wide range of efficiency inputs. Enhancements based on statistical insights are used for improving the model accuracy using filters, input transformations, and change points. Surrogate models achieved average coefficient of variation of the root mean squared error (CVRMSE) values of 2.17, 1.06, 2.05, and 3.26 for proposed electricity, proposed natural gas, baseline electricity, and baseline natural gas, respectively, with enhancements reducing CVRMSE by an average of 14.9% across all combinations. We provide model interpretation via Shapley additive explanations to determine which input variables most influence energy consumption and provide supportive arguments for enhancements.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

A Decomposition-Based Learn-To-Optimize Approach with Feasibility Layer Assistance for Sub-Hourly Unit Commitment

Sub-hourly unit commitment (UC) with 15-min intervals is gaining significant attention as a way to respond rapidly to the fluctuations in electricity supply and demand introduced by renewable resources. However, the increased temporal resolution and complex inter-temporal dependencies pose substantial computational challenges for traditional optimization methods. To this end, this paper explores a decomposition-based learn-to-optimize approach. Building on recent advances in machine learning, our method revisits the long- overlooked Lagrangian relaxation framework, which is a classical decomposition technique that enables tractable subproblem solving. These smaller subproblems are inherently well-suited for machine learning, as their reduced dimensionality and structural regularity allow predictive models to efficiently learn and generalize solution patterns. We thus propose a generic predictive model, which embeds Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure, and integrate a rule-based feasibility layer to capture temporal dependencies, reduce training effort, and improve feasibility w.r.t. unit-level constraints. Our method has been validated on the IEEE 118-bus system, demonstrating promising performance in solving sub-hourly UC problems efficiently and feasibly.

97 MATHEMATICS AND COMPUTING↗