Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory effect”

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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Intrinsic property of defective β-Ga 2 O 3 to self-heal under ionizing irradiation

Damage evolution and phase stability in defective β-Ga 2 O 3 and an irradiation-converted γ-Ga 2 O 3 layer have been studied under ionizing irradiation at 300 K. By exploring athermal nonequilibrium processes in β-Ga 2 O 3 , we succeed in identifying a self-healing mechanism that enables recovery pre-existing damage, characterized by a recovery cross-section of ~0.17 nm 2 . Remarkably, this study further demonstrates that the crystallinity of the irradiation-converted γ-Ga 2 O 3 layer improves under ionizing irradiation. More importantly, X-ray diffraction analysis reveals that the highly-strained 𝛾 -phase transforms into a highly-crystalline structure without film disintegration, contrasting to that reported for isochronal annealing at 1000 K. The inelastic thermal spike calculations provide insights into the important effects of energy transfer to electrons in reordering the local atomic arrangement of both defective β- Ga 2 O 3 and 𝛾-Ga 2 O 3 . This behavior suggests a pathway for low-temperature crystallization, offering a promising strategy for fabricating ultrahigh-speed non-volatile memory devices.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Recent advancements in chiral spintronics: from molecular-level insights to device applications. A prospect based on the interplay between physical and chemical properties of chiral systems

This review discusses recent advancements in chiral-based spin-electronic devices achieved using suitable combinations of organic, inorganic and hybrid materials. The focus is on how chirality can be effectively used to control spin in practical applications, particularly in spintronic sensors and consumer devices. Interestingly, the underlying mechanism for this control is the chiral-induced spin selectivity (CISS) effect, which links the structural chirality of a material to its spin-selective electronic transport properties. The CISS effect arises from the observation that charge transmission in chiral systems is spin selective. Experimental evidence suggests a relationship between electron spin and the structural handedness of the material. In conclusion, this unique structure-transport relationship can be exploited to design a wide range of spintronics devices, including memory, transistors, logic gates and molecular q-bits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Time scales for nonlinear processes in preheating after multifield inflation with nonminimal couplings

We have conducted extensive lattice simulations to study the postinflation dynamics of multifield models involving nonminimal couplings. In this work, we explore the parameter dependence of preheating in these models and describe the various time scales that control such nonlinear processes as energy transfer, rescattering, and the approach to radiation domination and thermalization. In the limit of large nonminimal couplings ($ξ_I$ ~ 100), we find that efficient transfer of energy from the inflaton condensate to radiative degrees of freedom, emergence of a radiation-dominated equation of state, and the onset of thermalization each consistently occur within $N_{\text{reh}} ≲ 3 e$-folds after the end of inflation, largely independent of the values of the other couplings in the models. The exception is the case of negative ellipticity, in which there is a misalignment between the dominant direction in field space along which the system evolves and the larger of the nonminimal couplings $ξ_I$. In those cases, the field-space-driven parametric resonance is effectively shut off. More generally, the competition between the scalar fields’ potential and the field-space manifold structure can yield interesting phenomena such as two-stage resonances. Across many regions of parameter space, we find efficient re-scattering between the distinct fields, leading to a partial memory loss of the shape of the initial fluctuation spectrum. Despite the explosive particle production, which can lead to a quick depletion of the background energy density, the nonlinear processes do not induce any superhorizon correlations after the end of inflation in these models, which keeps predictions for cosmic microwave background observables unaffected by the late-time amplification of isocurvature fluctuations. Hence the excellent agreement between primordial observables and recent observations is preserved for this class of models, even when we consider postinflation dynamics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

DDStore: Distributed Data Store for Scalable Training of Graph Neural Networks on Large Atomistic Modeling Datasets

Graph neural networks (GNNs) are a class of Deep Learning models used in designing atomistic materials for effective screening of large chemical spaces. To ensure robust prediction, GNN models must be trained on large volumes of atomistic data on leadership class supercomputers. Even with the advent of modern architectures that consist of multiple storage layers that include node-local NVMe devices in addition to device memory for caching large datasets, extreme-scale model training faces I/O challenges at scale.We present DDStore, an in-memory distributed data store designed for GNN training on large-scale graph data. DDStore provides a hierarchical, distributed, data caching technique that combines data chunking, replication, low-latency random access, and high throughput communication. DDStore achieves near-linear scaling for training a GNN model using up to 1000 GPUs on the Summit and Perlmutter supercomputers, and reaches up to a 6.15x reduction in GNN training time compared to state-of-the-art methodologies.

Choi, Jong Youl↗
DOE OSTI2022

Unconventional short-range structural fluctuations in cuprate superconductors

Abstract The interplay between structural and electronic degrees of freedom in complex materials is the subject of extensive debate in physics and materials science. Particularly interesting questions pertain to the nature and extent of pre-transitional short-range order in diverse systems ranging from shape-memory alloys to unconventional superconductors, and how this microstructure affects macroscopic properties. Here we use neutron and X-ray diffuse scattering to uncover universal structural fluctuations in La 2-x Sr x CuO 4 and Tl 2 Ba 2 CuO 6+δ , two cuprate superconductors with distinct point disorder effects and with optimal superconducting transition temperatures that differ by more than a factor of two. The fluctuations are present in wide doping and temperature ranges, including compositions that maintain high average structural symmetry, and they exhibit unusual, yet simple scaling behaviour. The scaling regime is robust and universal, similar to the well-known critical fluctuations close to second-order phase transitions, but with a distinctly different physical origin. We relate this behaviour to pre-transitional phenomena in a broad class of systems with structural and magnetic transitions, and propose an explanation based on rare structural fluctuations caused by intrinsic nanoscale inhomogeneity. We also uncover parallels with superconducting fluctuations, which indicates that the underlying inhomogeneity plays an important role in cuprate physics.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

GronOR: Massively Parallel and GPU-Accelerated Non-Orthogonal Configuration Interaction for Large Molecular Systems

GronOR is a program package for non-orthogonal configuration interaction calculations for an electronic wave function built in terms of anti-symmetrized products of multi-configuration molecular fragment wave functions. The two-electron integrals that have to be processed may be expressed in terms of atomic orbitals or in terms of an orbital basis determined from the molecular orbitals of the fragments. The code has been specifically designed for execution on distributed memory massively parallel and Graphics Processing Unit (GPU)-accelerated computer architectures, using an MPI+OpenACC/OpenMP programming approach. The task-based execution model used in the implementation allows for linear scaling with the number of nodes on the largest pre-exascale architectures available, provides hardware fault resiliency, and enables effective execution on systems with distinct central processing unit-only and GPU-accelerated partitions. The code interfaces with existing multi-configuration electronic structure codes that provide optimized molecular fragment orbitals, configuration interaction coefficients, and the required integrals. Algorithm and implementation details, parallel and accelerated performance benchmarks, and an analysis of the sensitivity of the accuracy of results and computational performance to thresholds used in the calculations are presented.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Quantum Networks for Resilient Power Grids: Theory and Simulated Evaluation

Quantum networks are considered the future of secure communication in the coming quantum era. Yet there lack significant efforts on developing practical quantum networks for power grids. Here, in this paper, we establish a quantum network-based power grid (QNetGrid) framework and develops a real-time, reliable, flexible, programmable, and cost-effective QNetGrid software testbed containing repeater-based quantum communication, quantum routing, real software-defined networking (SDN) switches, and real-time networked microgrids (NMs) operations. It makes the following contributions: 1) a repeater and routing based quantum network simulator (QNSim) is developed, 2) repeaters with and without quantum memories are respectively simulated in QNSim, 3) different routing scenarios in QNetGrid are investigated, 4) a real-time QNetGrid software testbed is built in RTDS incorporating QNSim and real SDN switches, and 5) various test cases are designed, and experimental results produced with the QNetGrid testbed provide valuable insights for building quantum networks in power grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Investigation of spin and magnetism in two dimensional materials with atomic-scale spatial resolution (Final Technical Report)

Spintronics is an approach to energy-efficient electronics beyond silicon CMOS that utilizes the electron’s spin degree of freedom for memory and logic. The record spin diffusion length in graphene has generated considerable interest in two dimensional (2D) materials (i.e. graphene and beyond) as a platform for spintronics. Magnetism in 2D van der Waals materials may offer additional opportunities for tunability via strain, external fields, and layer-dependent quantum effects. The inherently atomic-scale nature of exchange interactions and the inherently all-surface nature of 2D sheets motivate an integrated approach combining atomic-scale magnetic characterization, epitaxial growth, and nanodevice fabrication. The mission of the research is to develop and utilize atomic-scale imaging of spin and magnetism via spin-polarized scanning tunneling microscopy (STM) in conjunction with atom-by-atom materials growth via molecular beam epitaxy (MBE) and nanoscale device fabrication to explore new frontiers of spintronics and quantum science in 2D materials. The PIs are particularly motivated by understanding how the magnetic and spin-dependent properties at the atomic scale lead to interesting and potentially useful phenomena in spintronic devices at the macroscopic scale.

36 MATERIALS SCIENCE↗
DOE OSTI2020

CRADA Final Report: Open Microgrid Platform

Current microgrid control technology is mostly proprietary, expensive, and inflexible. An open-source, vendor-neutral, publish-subscribe controller will significantly lower the barrier to entry for new technologies and market entrants: inverter, battery, and load control manufacturers; cloud and services providers; and energy aggregators. An OpenFMB controller can significantly reduce the acquisition, integration, and ongoing operating and maintenance costs and increase revenue opportunities for energy producers and consumers. It allows distributed energy resource (DER) owners to replace individual DER components as richer-function, lower-cost devices become available or to incorporate new forecast and optimization algorithms as they are developed. A standard, secure, full-function DER field controller will also provide a low-cost means for grid operators to effectively manage the variability and uncertainty of solar photovoltaics (PV). Under the terms of this CRADA, ORNL has worked with Open Energy Solutions (OES) to advance the transition of ORNL’s existing open-source microgrid controller into a platform geared toward mainstream implementation. Using a more prevalent and memory-safe programming language, Rust, OES has converted ORNL’s current generation on-grid optimization into an application more suitable for industry use. The results of the ported optimization were analyzed by inputting the same arguments in both the current-generation and next-generation optimizers and verifying that the results were equivalent.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Néel domain walls with bistable chirality in a perpendicularly magnetized ferrimagnetic insulator

Field-free spin-orbit torque-driven domain wall motion in magnetic thin films with perpendicular magnetic anisotropy (PMA) requires the domain walls to have Néel character. Conventionally, Néel domain walls are stabilized by the Dzyaloshinskii-Moriya interaction (DMI) in ultrathin films. Here, in a europium iron garnet thin film with PMA and an additional uniaxial in-plane anisotropy, we demonstrate two bistable Néel domain wall states in the absence of DMI, and the capability to toggle the wall states with an in-plane field pulse and consequently their directions of motion under a current pulse. We present a phase diagram for the bistable Néel domain wall states as a function of in-plane field pulse width and amplitude. By fitting the experimental data to an analytical model of Néel wall reversal through the nucleation and propagation of Bloch lines, we extract the length of the initial reversed domain wall segment and Bloch line nucleation energy barrier. Current-driven motion of in-plane anisotropy stabilized Néel walls is qualitatively different from that of DMI-stabilized ones owing to the different symmetry of the effective fields that stabilize the Néel configuration. Furthermore, we present a proof of principle demonstration for 2-bit random number generation based on the stochastic reversal of domain wall chirality. These results provide critical insight into the topological energy barrier of Bloch lines and identify paths towards domain wall-based memory and computing devices.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Short- vs . long-range elastic distortion: structural dynamics of a [2 × 2] tetrairon( II ) spin crossover grid complex observed by time-resolved X-Ray crystallography

Spin crossover complexes (SCO) are among the most studied molecular switches due to their potential use in displays, sensors, actuators and memory components. A prerequisite to using these materials is the understanding of the structural changes following the spin transition at out-of-equilibrium conditions. So far, out-of-equilibrium studies in SCO solids have been focused on mononuclear complexes, though a growing number of oligonuclear SCO complexes showing cooperative effects are being reported. Here, we use time-resolved pink Laue crystallography to study the out-of-equilibrium dynamics of a [2 × 2] tetranuclear metallogrid of the form [Fe II 4 L Me 4 ](BF 4 ) 4 ·2MeCN ([L Me ] - = 4-methyl-3,5-bis{6-(2,2'-bipyridyl)}pyrazolate). The out-of-equilibrium spin state switching induced by a ps laser pulse demonstrates that the metallogrid exhibits a multi-step response similar to that reported for mononuclear complexes. Contrary to the mononuclear complexes, the metallogrid shows two types of elastic distortions at different time scales. The first is a short-range distortion that propagates over the entire Fe 4 grid complex during the ps time scale, and it is caused by the rearrangement of the coordination sphere of the photo-switching ion and the constant feedback between strongly linked metal ions. The second is a long-range distortion caused by the anisotropic expansion of the lattice during the ns time scale, observed in mononuclear materials. The structural analysis demonstrates that the long-range prevails over the short-range distortion, inducing the largest deformation of both the entire grid and the coordination sphere of each metal ion. The present study sheds light on the out-of -equilibrium dynamics of a non-cooperative oligonuclear complex.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Pushing the limits of NAND technology scaling with ferroelectrics

Artificial intelligence (AI) continues to drive transformative advancements across various industries. The data-intensive nature of AI training (and inferencing) has resulted in the generation of unprecedented volumes of data with machine-generated content surpassing human-generated data by more than 100-fold in 2025. Efficiently managing this data influx necessitates advanced digital storage technologies. However, traditional NAND flash memory, which is critical for supporting data flows in AI systems—alongside high-bandwidth memory, for AI training—faces fundamental scaling limitations as it approaches the 1000-layer milestone, encompassing more than 40 trillion transistors. This article delves into the potential of hafnia-based ferroelectric materials as a breakthrough solution to these challenges. Recent advancements indicate that the intrinsic limitations of ferroelectric field-effect transistors (FEFETs) can be mitigated through material and device-level engineering. These advancements enable FEFETs to meet the stringent density, reliability, and scalability requirements of future three-dimensional NAND technology. The role of ferroelectrics in addressing NAND scaling challenges and expanding storage capabilities presents a promising avenue for meeting the storage demands of the AI-driven era.

3D NAND↗
DOE OSTI2024

Developing And Scaling an OpenFOAM Model to Study Turbulent Flow in a HFIR Coolant Channel

Improving the understanding of how computational fluid dynamics (CFD) direct numerical simulations (DNS) of flows in the High Flux Isotope Reactor (HFIR) perform when run in parallel using the high performance computing (HPC) platform Summit at the Oak Ridge Leadership Computing Facility (OLCF) is of particular importance to boost the computational tools used to support HFIR conversion to low enriched fuel (LEU). Evaluation of scaling performance was driven by the increasing importance of graphics processing unit (GPU) usage in HPC, which is becoming the standard for modern supercomputers such as Summit. The desired results are to obtain a strong positive correlation between the computational resources dedicated to a problem and the relative speed-up of the simulation in comparison to a benchmark. This capability will allow substantially improvement in HFIR flow analytical capabilities, specifically when predicting turbulence properties at high Reynolds numbers. The study leverages previous simulation results performed with code PHASTA (finite element) on HPC platforms Cori (NERSC) and Theta (ALCF) [1] with computing options provided in the computing platform OpenFOAM (finite volume) at OLCF. Transitioning from PHASTA to OpenFOAM will (1) eliminate dependence on third-party software for mesh generation and manipulation, (2) reduce resource needs by employing modern architectures, and (3) build expertise for future modeling of HFIR-specific problems like heat transfer in involute geometry, entrance effects, flow structure in channel corners, and so on—all important issues when defining the available thermal margins in the transition to LEU. CPUs and GPUs differ significantly in their architecture and utilization, as discussed in the literature [2]. The most important differences are in the approach to computations and their memory. A single GPU contains a large quantity of cores, enabling it to perform with a much higher throughput than a CPU, but execution requires a different approach. GPU codes execute instructions using the Single-Instruction Multiple-Thread (SIMT) approach in which a single instruction is used for groups of threads called warps. A warp typically consists of 32 threads which must execute the same set of instructions, although on separate threads. Alternately, a CPU has far fewer cores that are much more flexible in their operation, excelling at quickly performing more complex serial computations. This is why GPUs have greater throughput when properly utilized. The second important difference is seen when comparing their memory spaces. Limited memory allocations and CPU–GPU communications cause a significant bottleneck in GPU-accelerated programs. Further study was required to properly take advantage of GPU resources. A comprehensive analysis of code performance and the model-specific features of turbulence constitutes the core of this work. In this study, a DNS simulation of HFIR channel turbulence was performed with the finite volume CFD code OpenFOAM v2112 and CUDA v11.0 on Red Hat Enterprise Linux v8.2. The OpenFOAM installation had AMGx integrated to enable GPU acceleration and utilizes the PETSc4FOAM library. The computational resources and the problem size were scaled on CPU and CPU + GPU architectures to gain a better understanding of the performance of a DNS problem on modern computing hardware. The study aimed to analyze the scaling of the code exclusively on CPUs and then to examine the scaling of the codes with GPU acceleration enabled. Scaling studies included CPU and GPU acceleration on a mesh of varying resolution to analyze the impact of problem size relative to computational resources. In the course of preparing the GPU configuration on Summit, mainly using the AMGX solvers, difficulties were encountered stemming from constant changes resulting from extensive ongoing development activities and the changing environment. This resulted in the inability to complete the GPU portion of the work. The code was compiled and tested, but production runs to assess acceleration were not performed because the used discretional compute time allocation expired as year-end approached. The Summit HPC platform is scheduled for decommissioning in 2024, making it unattractive for future use with Nvidia-based GPUs. Therefore, the work will be moved onto NERSC machines in FY24. An application was prepared and submitted, and sufficient node-hours were awarded to continue the research in the next calendar year. This report summarizes work performed thus far, which mostly focused on CPU OpenFOAM computing.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2024

Additively Manufacturing Nitinol Shape Memory Alloys for Advanced Actuator Designs

The objective of this research was to understand the role of feedstock production in the phase transformation behavior of additively manufactured Ni-Ti alloys for advanced actuator design. Industrial adoption of additively manufactured Ni-Ti alloys depends on the ability to produce repeatable phase transformation behavior, quantified here by the austenite to martensite transformation on heating. Small variations in the alloy composition may have a significant effect on the temperature at which this transformation occurs. This project showed that the powder characteristics play an important role in determining this behavior. Increases in the surface area per unit volume of the powder, either as a function of size distribution or morphology, have the effect of reducing the Ti content in the alloy through the formation of Ti-rich oxides on the powder surface, which has the effect of depressing the transformation temperature. Preferential Ni vaporization during additive manufacturing can partially offset this effect. To achieve repeatable results, it is important to understand the effect of powder oxidation, and to control the powder characteristics.

36 MATERIALS SCIENCE↗
DOE OSTI2021

iSPECTRON: a simulation interface for linear and nonlinear spectra with ab-initio quantum chemistry software

We introduce iSPECTRON, an open source (under the Educational Community License version 2.0) program that parses data from common quantum chemistry software (NWChem, OpenMolcas, Gaussian, Cobramm, etc.), produces the input files for the simulation of linear and nonlinear spectroscopy of molecules with the Spectron code, and analyzes the spectra with a broad range of tools. Vibronic spectra are expressed in term of the electronic eigenstates, obtained through quantum chemistry computations, and vibrational/bath effects are incorporated in the framework of the displaced harmonic oscillator model, where all required quantities are computed at the Franck-Condon point. The code capabilities are illustrated by simulating linear absorption, transient absorption and two dimensional electronic spectra of the pyrene molecule. Two levels of electronic structure theory, TDDFT (with NWChem) and RASSCF/RASPT2 (with OpenMolcas), are compared where possible. Acknowledgements: F.S., A.N., D.R.N., N.G., S.M, M.G. acknowledge support from the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Chemical Sciences, Geosciences, and Biosciences Division under Award Nos. DE-SC0019484, KC-030103172684. The Spectron code was developed with support from the National Science Foundation (Grant CHE- 1953045). This research benefited from computational resources provided by EMSL, a DOE Office of Science User Facility sponsored by the Office of Biological and Environmental Research and located at PNNL. PNNL is operated by Battelle Memorial Institute for the United States Department of Energy under DOE Contract No. DE-AC05-76RL1830.

Segatta, Francesco↗
DOE OSTI2025

Time-tagging data acquisition system for testing superconducting electronics based on an RFSoC and custom analog frontend

Novel electronic devices can often be operated in a plethoraof ways, which makes testing circuits comprised of them difficult.Often, no single tool can simultaneously analyze the operatingmargins, maximum speed, and failure modes of a circuit, particularlywhen the intended behavior of subcomponents of the circuit is notstandardized. This work demonstrates a cost-effective time-domaindata acquisition system for electronic circuits that enables moreintricate verification techniques than are practical withconventional experimental setups. We use high-speeddigital-to-analog converters and real-timemulti-gigasample-per-second waveform processing to push experimentalcircuits beyond their maximum operating speed. Our customtime-tagging data capture firmware reduces memory requirements andcan be used to determine when errors occur. The firmware iscombined with a thermal-noise-limited analog frontend with50 dB of dynamic range. Compared to currentlyavailable commercial test equipment that is seven times moreexpensive, this data acquisition system was able to operate asuperconducting shift register at a nearly three-times-higher clockfrequency (200 MHz vs. 80 MHz).

Foster, Reed A. [MIT] (ORCID:0000000231002127)↗
DOE OSTI2020

Quantum Dynamics at Scale: Ultrafast Control of Emergent Functional Materials

Confluence of extreme-scale quantum dynamics simulations (i.e. quantum@scale) and cutting-edge x-ray free-electron laser experiments are revolutionizing materials science. An archetypal example is the exciting concept of using picosecond light pulses to control emergent material properties on demand in atomically-thin layered materials. This paper describes efforts to scale our quantum molecular dynamics engine toward the United States' first exaflop/s computer, under an Aurora Early Science Program project named "Metascalable layered material genome". Key algorithmic and computing techniques incorporated are: (1) globally-scalable and locally-fast solvers within a linear-scaling divide-conquer-recombine algorithmic framework; (2) algebraic `BLASification' of computational kernels; and (3) data alignment and loop restructuring, along with register and cache blocking, for enhanced vectorization and efficient memory access. The resulting weak-scaling parallel efficiency was 0.93 on 131,072 Intel Xeon Phi cores for a 56.6 million atom (or 169 million valence-electron) system, whereas the various code transformations achieved 5-fold speedup. The optimized simulation engine allowed us for the first time to establish a significant effect of substrate on the dynamics of layered material upon electronic excitation.

Algebraic BLASification↗
DOE OSTI2026

LAF-Net: A Deep Residual and Cross-Attention Framework for Day-Ahead Load Forecasting: Preprint

Accurate day-ahead load forecasting is essential for reliable power system operations and market efficiency. System operators such as the Midcontinent Independent System Operator (MISO) rely on forecasts from multiple vendors, yet combining them effectively remains a persistent challenge due to vendor-specific biases. This paper presents a novel LSTM-Attention Fusion Network with Error Representation (LAF-Net) that enhances day-ahead hourly load forecasting through deep residual learning and multi-modal cross-attention. The proposed model builds a historical error memory from past vendor performance and dynamically queries it with future hour context to generate adaptive, hour-specific trust weights for each vendor. A bounded residual correction further refines forecasts by mitigating systematic and temporally localized errors. Tested on real MISO LBA data with multi-vendor forecasts, LAF-Net consistently outperforms the best vendor baseline across all 38 LBAs, achieving more than a 40% reduction in system-level mean absolute error (MAE) during peak load hours relative to the best vendor baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗