Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 415 records · Page 23

Beyond Fine Tuning: Adding capacity to leverage few labels

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural networks or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning. Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.

data science↗

Working With Your Utility Series: Interconnection Basics

This training provided information on interconnection basics for federal agencies developing distributed energy projects. Considerations covered included: Understanding interconnection processes and timelines, interconnection siting considerations, technology-specific interconnection issues, and interconnect agreements. This webinar is the first in a multi-part series on working with electric utilities to develop distributed energy projects on federal sites.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Multi-Kernel Adaptive Support Vector Machine for Scalable Predictive Maintenance

Application of data-driven solutions across an industry is challenging, since the data are often stored locally, and increasing privacy and security concerns restrict access to the data. In addition, it is highly unlikely that all potential data patterns are captured in a single data source. Because it is highly unlikely that all potential data patterns are captured in a single data source, machine learning (ML) models developed from a single source cannot be robust enough. An alternative is to train the ML model at each source and develop a distributed knowledge discovery and aggregation approach to build global knowledge. In this paper, we develop and demonstrate a distributed ML model, federated transfer learning (FTL), using a multi-kernel-based adaptive support vector machine (MK-A-SVM). For federated learning (FL), the multi-kernel (MK) approach enables feature-specific model aggregation under data heterogeneity; whereas for transfer learning (TL) the adaptive model enables utilization of an aggregated model from a different task. The proposed approach is validated using nuclear power plant (NPP) vertical motor-driven pump data to predict the health condition of vertical motor-driven pumps as an anomaly detection. The efficiency of the proposed approach is also quantified and compared with neural network.

42 ENGINEERING↗

Normalizing flows for likelihood-free inference with fusion simulations

Fluid-based scrape-off layer transport codes, such as UEDGE, are heavily utilized in tokamak analysis and design, but typically require user-specified anomalous transport coefficients to match experiments. Determining the uniqueness of these parameters and the uncertainties in them to match experiments can provide valuable insights to fusion scientists. Here, we leverage recent work in the area of likelihood-free inference (‘simulation-based inference’) to train a neural network, which enables accurate statistical inference of the anomalous transport coefficients given experimental plasma profile input. UEDGE is treated as a black-box simulator and runs multiple times with anomalous transport coefficients sampled from priors, and the neural network is trained on these simulations to emulate the posterior. The neural network is trained as a normalizing flow model for density estimation, allowing it to accurately represent complicated, high-dimensional distribution functions. With a fixed simulation budget, we compare a single-round procedure to a multi-round approach that guides the training simulations toward a specific target observation. Finally, we discuss the future possibilities for use of amortized models, which train on a wide range of simulations and enable fast statistical inference for results during experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Estimating Watershed Subsurface Permeability From Stream Discharge Data Using Deep Neural Networks

Subsurface permeability is a key parameter in watershed models that controls the contribution from the subsurface flow to stream flows. Since the permeability is difficult and expensive to measure directly at the spatial extent and resolution required by fully distributed watershed models, estimation through inverse modeling has had a long history in subsurface hydrology. The wide availability of stream surface flow data, compared to groundwater monitoring data, provides a new data source to infer soil and geologic properties using integrated surface and subsurface hydrologic models. As most of the existing methods have shown difficulty in dealing with highly nonlinear inverse problems, we explore the use of deep neural networks for inversion owing to their successes in mapping complex, highly nonlinear relationships. We train various deep neural network (DNN) models with different architectures to predict subsurface permeability from stream discharge hydrograph at the watershed outlet. The training data are obtained from ensemble simulations of hydrographs corresponding to an permeability ensemble using a fully-distributed, integrated surface-subsurface hydrologic model. The trained model is then applied to estimate the permeability of the real watershed using its observed hydrograph at the outlet. Our study demonstrates that the permeabilities of the soil and geologic facies that make significant contributions to the outlet discharge can be more accurately estimated from the discharge data. Their estimations are also more robust with observation errors. Compared to the traditional ensemble smoother method, DNNs show stronger performance in capturing the nonlinear relationship between permeability and stream hydrograph to accurately estimate permeability. Our study sheds new light on the value of the emerging deep learning methods in assisting integrated watershed modeling by improving parameter estimation, which will eventually reduce the uncertainty in predictive watershed models.

54 ENVIRONMENTAL SCIENCES↗

Explorer-II: Wireless Self-Powered Visual and NDE Robotic Inspection System for Live Gas Distribution Mains

Carnegie Mellon University (CMU) under contract from Department of Energy/National Energy Technology Laboratory (DoE/NETL) and co-funding from the Northeast Gas Association (NGA), has completed the overall system design, field-trial and Magnetic Flux Leakage (MFL) sensor evaluation program for the next-generation Explorer-II (X-II) live gas main Non-destructive Evaluation (NDE) and visual inspection robot platform. The design is based on the Explorer-I prototype which was built and field-tested under a prior (also DoE- and NGA co-funded) program, and served as the validation that self-powered robots under wireless control could access and navigate live natural gas distribution mains. The X-II system design ({approx}8 ft. and 66 lbs.) was heavily based on the X-I design, yet was substantially expanded to allow the addition of NDE sensor systems (while retaining its visual inspection capability), making it a modular system, and expanding its ability to operate at pressures up to 750 psig (high-pressure and unpiggable steel-pipe distribution mains). A new electronics architecture and on-board software kernel were added to again improve system performance. A locating sonde system was integrated to allow for absolute position-referencing during inspection (coupled with external differential GPS) and emergency-locating. The power system was upgraded to utilize lithium-based battery-cells for an increase in mission-time. The resulting robot-train system with CAD renderings of the individual modules. The system architecture now relies on a dual set of end camera-modules to house the 32-bit processors (Single-Board Computer or SBC) as well as the imaging and wireless (off-board) and CAN-based (on-board) communication hardware and software systems (as well as the sonde-coil and -electronics). The drive-module (2 ea.) are still responsible for bracing (and centering) to drive in push/pull fashion the robot train into and through the pipes and obstacles. The steering modules and their arrangement, still allow the robot to configure itself to perform any-angle (up to 90 deg) turns in any orientation (incl. vertical), and enable the live launching and recovery of the system using custom fittings and a (to be developed) launch-chamber/-tube. The battery modules are used to power the system, by providing power to the robot's bus. The support modules perform the functions of centration for the rest of the train as well as odometry pickups using incremental encoding schemes. The electronics architecture is based on a distributed (8-bit) microprocessor architecture (at least 1 in ea. module) communicating to a (one of two) 32-bit SBC, which manages all video-processing, posture and motion control as well as CAN and wireless communications. The operator controls the entire system from an off-board (laptop) controller, which is in constant wireless communication with the robot train in the pipe. The sensor modules collect data and forward it to the robot operator computer (via the CAN-wireless communications chain), who then transfers it to a dedicated NDE data-storage and post-processing computer for further (real-time or off-line) analysis. The prototype robot system was built and tested indoors and outdoors, outfitted with a Remote-Field Eddy Current (RFEC) sensor integrated as its main NDE sensor modality. An angled launcher, allowing for live launching and retrieval, was also built to suit custom angled launch-fittings from TDW. The prototype vehicle and launcher systems are shown. The complete system, including the in-pipe robot train, launcher, integrated NDE-sensor and real-time video and control console and NDE-data collection and -processing and real-time display, were demonstrated to all sponsors prior to proceeding into final field-trials--the individual components and setting for said acceptance demonstration are shown. The launcher-tube was also used to verify that the vehicle system is capable of operating in high-pressure environments, and is safely deployable using proper evacuating/purging techniques for operation in the potentially explosive natural gas environment. The test-setting and environment for safety-certification of the X-II robot platform and the launch and recovery procedures, is shown. Field-trials were successfully carried out in a live steel pipeline in Northwestern Pennsylvania. The robot was launched and recovered multiple times, travelling thousands of feet and communicating in real time with video and command-and-control (C&C) data under remote operator control from a laptop, with NDE sensor-data streaming to a second computer for storage, display and post-processing. Representative images of the activities and systems used in the week-long field-trial are shown. CMU also evaluated the ability of the X-II design to be able to integrate an MFL sensor, by adding additional drive-/battery-/steering- and support-modules to extend the X-II train.

03 NATURAL GAS↗

Physics-Informed Machine Learning Model for Ceramic Matrix Composite Creep

A physics-informed recurrent neural network (RNN) based surrogate model is developed to emulate the nonlinear, time-dependent constitutive behavior of ceramic matrix composites (CMCs) driven by matrix damage and constituent creep at the microscale. Physics-informed constraints are introduced into the surrogate model through regularization to ground the prediction in physics and improve its predictive capabilities. Training data is generated using the high-fidelity generalized method of cells (HFGMC) approach which calls appropriate creep and damage models for each of the constituents. This coupling permits simulating the nonlinear behavior of CMCs based on constituent response at the microscale along with microstructural features such as fiber and porosity volume fraction and fiber radius. The microscale repeating unit cell is loaded under creep fatigue conditions to replicate the material loading experienced in a turbine engine. Therefore, the RNN-based surrogate model is tasked with predicting, as a function of variable input stress sequence, temperature, and microstructural features, the resulting strain history response while satisfying physical constraints related to creep rate, isochoric inelastic deformation, and strain energy density. The trained surrogate model is shown to effectively match the strain history over quantified distributions of microstructural features and relevant loading regimes and temperatures. Neural network based surrogate models can offer efficient alternatives to running computationally intensive multiscale material models to simulate the nonlinear response of large structural models. Therefore, the presented work provides evidence towards the feasibility of developing, training, and running such models for CMCs with complex microstructures, nonlinear time-dependent material response, and under non-monotonic loading conditions.

ceramic matrix composites↗

Adaptive hyperparameter updating for training restricted Boltzmann machines on quantum annealers

Restricted Boltzmann Machines (RBMs) have been proposed for developing neural networks for a variety of unsupervised machine learning applications such as image recognition, drug discovery, and materials design. The Boltzmann probability distribution is used as a model to identify network parameters by optimizing the likelihood of predicting an output given hidden states trained on available data. Training such networks often requires sampling over a large probability space that must be approximated during gradient based optimization. Quantum annealing has been proposed as a means to search this space more efficiently which has been experimentally investigated on D-Wave hardware. D-Wave implementation requires selection of an effective inverse temperature or hyperparameter (β) within the Boltzmann distribution which can strongly influence optimization. Here, we show how this parameter can be estimated as a hyperparameter applied to D-Wave hardware during neural network training by maximizing the likelihood or minimizing the Shannon entropy. We find both methods improve training RBMs based upon D-Wave hardware experimental validation on an image recognition problem. Neural network image reconstruction errors are evaluated using Bayesian uncertainty analysis which illustrate more than an order magnitude lower image reconstruction error using the maximum likelihood over manually optimizing the hyperparameter. The maximum likelihood method is also shown to out-perform minimizing the Shannon entropy for image reconstruction.

97 MATHEMATICS AND COMPUTING↗

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗

Soil response model verification: A multi-year study of foot traffic impact

The purpose of this research is to build upon the baseline study of soil compaction response to trampling previously conducted. Although trampling studies have been conducted in the past, the analysis of military training, in part, provides a different perspective and approach. The baseline data showed bulk densities remained relatively constant for a time and then began to increase at an increasing rate for several hundred passes and finally leveled and remained at or below 1.30 gm/cm{sup 3} through the remainder of the experiment. A mathematical model was created based on empirical data from the trampling experiment using a gamma cumulative distribution function. Subsequent similar experiments were conducted over the following 2 years to verify the baseline model soil response. The follow-on data were modeled using the same gamma distribution function with good results. The model replicated the soil response for the subsequent years well with the exception of the initial threshold which was dramatically reduced for both years. The experiments and the resulting model give quantifiable continuous inference on the effects of trampling, as opposed to the existing qualitative assessments. This model performed well and can be used as a foundation for future studies of land management when trampling occurs.

54 ENVIRONMENTAL SCIENCES↗

Large-Eddy Simulation of Flow Over Boeing Gaussian Bump Using Multiagent Reinforcement Learning Wall Model: Preprint

We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning. The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall at various computational grid points. It utilizes a wall eddy-viscosity formulation as the boundary condition to apply the modeled wall shear stress. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow. To further assess the robustness of the developed wall model, simulations of flow over the Boeing Gaussian bump are conducted at a Reynolds number of 2 x 10^6, based on the free-stream velocity and the bump width. The results of mean skin friction and pressure on the bump surface, as well as the velocity statistics of the flow field, are compared to those obtained from equilibrium wall model (EQWM) simulations and published experimental data sets. The developed wall model is found to successfully capture the acceleration and deceleration of the turbulent boundary layer on the bump surface, providing better predictions of skin friction near the bump peak and exhibiting comparable performance to the EQWM with respect to the wall pressure and velocity field. We also conclude that the subgrid-scale model is crucial to the accurate prediction of the flow field, in particular the prediction of separation.

boundary layer↗

Regularization via f -Divergence: An Application to Multi-Oxide Spectroscopic Analysis

In this paper, we explore the application of convolutional neural networks (CNNs) for predicting the chemical composition of complex geologic samples in a simulated Martian atmospheric environment. Specifically, we aim to characterize oxide weight percentages (wt.%) of rock samples analyzed by remote Laser-Induced Breakdown Spectroscopy (LIBS), framing the problem as a multi-target regression task . Neural networks trained on LIBS spectra are prone to overfitting due to high spectral complexity, limited labeled data, and measurement noise. While regularization is critical for improving generalization, common methods (e.g., ℓ 2 regularization) impose constraints not directly tied to data distribution properties. We propose a novel regularization method based on a specific ƒ-divergence induced by a graph-based estimator, designed to constrain the distributional discrepancy between predictions and targets. This regularizer serves a dual purpose: (a) mitigating overfitting by enforcing a constraint on the distributional difference between predictions and noisy targets, and (b) acting as an auxiliary loss that penalizes large divergences. To enable backpropagation, we develop a differentiable approximation of this particular ƒ-divergence, making the method feasible for neural networks. Experiments on ChemCam and SuperCam LIBS calibration spectra show that mathematical equation-divergence regularization outperforms or matches standard regularization methods (ℓ 1 , ℓ 2 , dropout) and the classical baseline, partial least squares (PLS). Combining ƒ-divergence regularization with standard regularization yields further performance gains, indicating that distributional regularization is useful in this context giving a promising direction for robust model training in planetary science applications. Source code is publicly available at Klein and Li (2025), https://doi.org/10.11578/dc.20250530.7.

58 GEOSCIENCES↗

Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO

Abstract Streambed grain sizes control river hydro‐biogeochemical (HBGC) processes and functions. However, measuring their quantities, distributions, and uncertainties is challenging due to the diversity and heterogeneity of natural streams. This work presents a photo‐driven, artificial intelligence (AI)‐enabled, and theory‐based workflow for extracting the quantities, distributions, and uncertainties of streambed grain sizes from photos. Specifically, we first trained You Only Look Once, an object detection AI, using 11,977 grain labels from 36 photos collected from nine different stream environments. We demonstrated its accuracy with a coefficient of determination of 0.98, a Nash–Sutcliffe efficiency of 0.98, and a mean absolute relative error of 6.65% in predicting the median grain size of 20 ground‐truth photos representing nine typical stream environments. The AI is then used to extract the grain size distributions and determine their characteristic grain sizes, including the 10th, 50th, 60th, and 84th percentiles, for 1,999 photos taken at 66 sites within a watershed in the Northwest US. The results indicate that the 10th, median, 60th, and 84th percentiles of the grain sizes follow log‐normal distributions, with most likely values of 2.49, 6.62, 7.68, and 10.78 cm, respectively. The average uncertainties associated with these values are 9.70%, 7.33%, 9.27%, and 11.11%, respectively. These data allow for the computation of the quantities, distributions, and uncertainties of streambed HBGC parameters, including Manning's coefficient, Darcy‐Weisbach friction factor, top layer interstitial velocity magnitude, and nitrate uptake velocity. Additionally, major sources of uncertainty in grain sizes and their impact on HBGC parameters are examined.

58 GEOSCIENCES↗

Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy

Purpose: To demonstrate knowledge-based 3D dose prediction for external beam radiotherapy. Methods: Using previously treated plans as training data, an artificial neural network (ANN) was trained to predict a dose matrix based on patient-specific geometric and planning parameters, such as the closest distance (r) to planning target volume (PTV) and organ-at-risks (OARs). Twenty-three prostate and 43 stereotactic radiosurgery/radiotherapy (SRS/SRT) cases with at least one nearby OAR were studied. All were planned with volumetric-modulated arc therapy to prescription doses of 81 Gy for prostate and 12–30 Gy for SRS. Using these clinically approved plans, ANNs were trained to predict dose matrix and the predictive accuracy was evaluated using the dose difference between the clinical plan and prediction, δD = D{sub clin} − D{sub pred}. The mean (〈δD{sub r}〉), standard deviation (σ{sub δD{sub r}}), and their interquartile range (IQR) for the training plans were evaluated at a 2–3 mm interval from the PTV boundary (r{sub PTV}) to assess prediction bias and precision. Initially, unfiltered models which were trained using all plans in the cohorts were created for each treatment site. The models predict approximately the average quality of OAR sparing. Emphasizing a subset of plans that exhibited superior to the average OAR sparing during training, refined models were created to predict high-quality rectum sparing for prostate and brainstem sparing for SRS. Using the refined model, potentially suboptimal plans were identified where the model predicted further sparing of the OARs was achievable. Replans were performed to test if the OAR sparing could be improved as predicted by the model. Results: The refined models demonstrated highly accurate dose distribution prediction. For prostate cases, the average prediction bias for all voxels irrespective of organ delineation ranged from −1% to 0% with maximum IQR of 3% over r{sub PTV} ∈ [ − 6, 30] mm. The average prediction error was less than 10% for the same r{sub PTV} range. For SRS cases, the average prediction bias ranged from −0.7% to 1.5% with maximum IQR of 5% over r{sub PTV} ∈ [ − 4, 32] mm. The average prediction error was less than 8%. Four potentially suboptimal plans were identified for each site and subsequent replanning demonstrated improved sparing of rectum and brainstem. Conclusions: The study demonstrates highly accurate knowledge-based 3D dose predictions for radiotherapy plans.

61 RADIATION PROTECTION AND DOSIMETRY↗

Scaling Resolution of Gigapixel Whole Slide Images Using Spatial Decomposition on Convolutional Neural Networks

Gigapixel images are prevalent in scientific domains ranging from remote sensing, and satellite imagery to microscopy, etc. However, training a deep learning model at the natural resolution of those images has been a challenge in terms of both, overcoming the resource limit (e.g. HBM memory constraints), as well as scaling up to a large number of GPUs. In this paper, we trained Residual neural Networks (ResNet) on 22,528 x 22,528-pixel size images using a distributed spatial decomposition method on 2,304 GPUs on the Summit Supercomputer. We applied our method on a Whole Slide Imaging (WSI) dataset from The Cancer Genome Atlas (TCGA) database. WSI images can be in the size of 100,000 x 100,000 pixels or even larger, and in this work we studied the effect of image resolution on a classification task, while achieving state-of-the-art AUC scores. Moreover, our approach doesn't need pixel-level labels, since we're avoiding patching from the WSI images completely, while adding the capability of training arbitrary large-size images. This is achieved through a distributed spatial decomposition method, by leveraging the non-block fat-tree interconnect network of the Summit architecture, which enabled GPU-to-GPU direct communication. Finally, detailed performance analysis results are shown, as well as a comparison with a data-parallel approach when possible.

Tsaris, Aristeidis (aris)↗

Synthesizing realistic sand assemblies with denoising diffusion in latent space

Abstract The shapes and morphological features of grains in sand assemblies have far‐reaching implications in many engineering applications, such as geotechnical engineering, computer animations, petroleum engineering, and concentrated solar power. Yet, our understanding of the influence of grain geometries on macroscopic response is often only qualitative, due to the limited availability of high‐quality 3D grain geometry data. In this paper, we introduce a denoising diffusion algorithm that uses a set of point clouds collected from the surface of individual sand grains to generate grains in the latent space. By employing a point cloud autoencoder, the three‐dimensional point cloud structures of sand grains are first encoded into a lower‐dimensional latent space. A generative denoising diffusion probabilistic model is trained to produce synthetic sand that maximizes the log‐likelihood of the generated samples belonging to the original data distribution measured by a Kullback‐Leibler divergence. Numerical experiments suggest that the proposed method is capable of generating realistic grains with morphology, shapes and sizes consistent with the training data inferred from an F50 sand database. We then use a rigid contact dynamic simulator to pour the synthetic sand in a confined volume to form granular assemblies in a static equilibrium state with targeted distribution properties. To ensure third‐party validation, 50,000 synthetic sand grains and the 1542 real synchrotron microcomputed tomography (SMT) scans of the F50 sand, as well as the granular assemblies composed of synthetic sand grains are made available in an open‐source repository.

Vlassis, Nikolaos N.↗

LLM-Based Adaptive Distribution Voltage Regulation Under Frequent Topology Changes: An In-Context MPC Framework

This paper proposes a large language model (LLM) based adaptive inverter control for distribution voltage regulation under frequent topology changes. We leverage the ability of the LLM to perform in-context learning and create a topology-adaptive surrogate model for power flow calculation. The surrogate model is then integrated with a long short-term memory-based load forecaster and a model predictive control (MPC) scheme to achieve the optimal inverter control that adapts to frequent topology changes. Unlike many existing works that assume fixed-topology grids or require the knowledge of all possible topologies when training a model, the proposed in-context MPC method tackles the distribution voltage control problem under various topologies and adapts to unknown topologies with limited data requirement for fine-tuning. The effectiveness of our method is demonstrated on a modified IEEE 123-bus test system.

24 POWER TRANSMISSION AND DISTRIBUTION↗