Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 1,495 records · Page 83
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Different Features of Cloud Macrophysical Changes Observed by MODIS, CALIPSO, and CloudSat for the 11-Year Period

From the A-train satellite mission, more than 11 years of Cloud–Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO), and CloudSat satellite measurements are available from 2007 to 2017. In this study, we examine cloud macrophysical changes from a passive sensor, Moderate Resolution Imaging Spectroradiometer (MODIS), and two active sensors, CALIPSO and CloudSat (CALCS). MODIS and CALCS capture common features of the cloud changes related to El Niño–Southern Oscillation (ENSO) events, i.e., increase of low clouds during La Niña and increase of mid and high clouds during El Niño over the eastern Pacific. However, optically thin cirrus clouds are well detected by CALCS while these are often missed by MODIS. As a result, MODIS shows much flatter distributions of cloud top heights. In addition, compared to MODIS, CALCS cloud volume anomalies are better correlated with relative humidity anomalies. The differences between MODIS and CALCS appear in low cloud variations. Particularly, fluctuations in MODIS low cloud anomalies are larger than CALCS, and MODIS low cloud anomalies are anticorrelated with mid/high cloud anomalies. This is because of the limitation in detecting underlying clouds by MODIS passive sensor. Also, the layer thickness of MODIS mid/high clouds is thinner than that from CALCS, less affecting cloud amounts at 0-3 km altitude.

Cloud↗
DOE OSTI2023

Application of unsupervised deep learning to image segmentation and in-situ contact angle measurements in a CO 2 -water-rock system

Rock surface wettability is a critical property that regulates multiphase flows in porous media, which can be quantified using the surface contact angle (CA). X-ray micro-computed tomography (μCT) provides an effective approach to in-situ measurements of surface CAs. However, the CA measurement accuracy depends significantly on the quality of CT image segmentation, which is the clustering of CT pixels into separate phases. Inspired by this, we developed a deep learning (DL)-based CA measurement workflow. Motivated by the recent tremendous progress in unsupervised learning techniques and aiming to avoid expensive manual data annotations, an unsupervised DL pipeline for CT image segmentation was proposed and implemented, which includes unsupervised model training and post-processing. The unsupervised model training was driven by a novel loss function constrained with feature similarity and spatial continuity and implemented by iterative forward and backward paths; the former clustered the pixel-wise feature vectors extracted by convolution neural networks, whereas the latter updated the parameters using gradient descent. An over-segmentation strategy was adopted for model training. The post-processing steps based on agglomerative hierarchical clustering (AHC) were implemented to further merge the over-segmented model output to the desired cluster number, which is intended to improve the efficiency of image segmentation. The developed unsupervised DL pipeline was compared with other commonly-used image segmentation methods using pixel-wise and physics-based evaluation metrics on a synthetic raw-image dataset, which had a known ground truth. The unsupervised DL pipeline showed the best performance. Next, the segmented images were input to an automatic CA measurement tool, and the results were validated by comparisons with manual measurements. The CA values from the manual and automatic measurements showed similar distributions and statistical properties. The automatic measurement demonstrated a wider spectrum because of the much larger number of measurement data points. The primary novelty of the unsupervised DL pipeline developed in this study lies in the novel loss function and the over-segmentation strategy associated with AHC post-processing. Finally, the workflow has been proven an efficient tool for pore-scale wettability characterization, which has a wide range of applications in fundamental studies of multiphase flows in natural porous media, which have critical implications to geological carbon sequestration, hydrocarbon energy recovery, and contaminant transport in groundwater.

42 ENGINEERING↗
DOE OSTI2025

Novel Approach to PV Inverter Modeling and Simulation Leveraging Experiments, Learning Based Modeling and Co-Simulation

Photovoltaic (PV) inverter manufacturers use custom, proprietary control approaches and topologies in their inverter design. The proprietary nature of these approaches makes it challenging to share electromagnetic transients (EMT) domain models for system studies. This research work presents an approach to develop EMT models from experimental data. We use novel approach in experimental design, high fidelity data collection, use of learning-based modeling, and co-simulation to reduce the time taken to develop an EMT model for an inverter under test (IUT). We used a 20 kW off-the-shelf grid following PV inverter and subjected the inverter to controlled tests. The tests include voltage and frequency step changes, as well as solar irradiance variations. The recorded high frequency data were used to train a neural network model representing the dynamic behavior of the IUT. The model was subsequently imported into an EMT tool using co-simulation techniques, and thus completing the modeling effort.

black box inverter modeling↗
DOE OSTI2022

Deep Learning Based Frequency Stability Assessment in Power Grid with High Renewables

Frequency stability assessment is one critical aspect of power system security assessment. Traditional N-1 screening method is based on the simulations of a few typical daily and seasonal operation scenarios. However, the increasing integration of inverter-based renewables and the retirement of conventional synchronous generators result in decreasing system inertia and growing complexity of system operating conditions. Selecting a few typical operation scenarios cannot cover all operating conditions, and the time-domain simulation of all operation conditions requires tremendous time. This paper proposes a more efficient frequency stability assessment method based on deep learning. The affinity propagation clustering algorithm is used to divide the dataset into different clusters, so the selected dataset for training can cover the diversified operating conditions as much as possible. Also, feature normalization is applied to both the training dataset and testing dataset in order to remove any unnecessary bias. Especially, trained model based on full dataset normalization has bounded error in the prediction. The case study on the reduced 240-bus WECC system demonstrates that the proposed method can predict accurate frequency nadir with limited training dataset. The deep learning model using the revised feature normalization can predict more accurate frequency nadir than that using the traditional feature normalization and has very small maximum prediction error.

affinity propagation↗
NASA NTRS2009

Comparison of Image Restoration Methods for Lunar Epithermal Neutron Emission Mapping

Orbital measurements of neutrons by the Lunar Exploring Neutron Detector (LEND) onboard the Lunar Reconnaissance Orbiter are being used to quantify the spatial distribution of near surface hydrogen (H). Inferred H concentration maps have low signal-to-noise (SN) and image restoration (IR) techniques are being studied to enhance results. A single-blind. two-phase study is described in which four teams of researchers independently developed image restoration techniques optimized for LEND data. Synthetic lunar epithermal neutron emission maps were derived from LEND simulations. These data were used as ground truth to determine the relative quantitative performance of the IR methods vs. a default denoising (smoothing) technique. We review and used factors influencing orbital remote sensing of neutrons emitted from the lunar surface to develop a database of synthetic "true" maps for performance evaluation. A prior independent training phase was implemented for each technique to assure methods were optimized before the blind trial. Method performance was determined using several regional root-mean-square error metrics specific to epithermal signals of interest. Results indicate unbiased IR methods realize only small signal gains in most of the tested metrics. This suggests other physically based modeling assumptions are required to produce appreciable signal gains in similar low SN IR applications.

McClanahan, T. P.↗
DOE OSTI2025

Deployment and validation of predictive 6-dimensional beam diagnostics through generative reconstruction with standard accelerator elements

Understanding the 6-dimensional phase space distribution of particle beams is essential for optimizing accelerator performance. Conventional diagnostics such as use of transverse deflecting cavities offer detailed characterization but require dedicated hardware and space. Generative phase space reconstruction (GPSR) methods have shown promise in beam diagnostics, yet prior implementations still rely on such components. Here we present the first experimental implementation and validation of the GPSR methodology, realized by the use of standard accelerator elements including accelerating cavities and dipole magnets, to achieve complete 6-dimensional phase space reconstruction. Through simulations and experiments at the Pohang Accelerator Laboratory X-ray Free Electron Laser facility, we successfully reconstruct complex, nonlinear beam structures. Furthermore, we validate the methodology by predicting independent downstream measurements excluded from training, revealing the reconstruction closely resembling ground truth. This advancement establishes a pathway for predictive diagnostics across beamline segments while reducing hardware requirements and expanding applicability to various accelerator facilities.

Kim, Seongyeol [Pohang Univ. of Science and Techno↗
DOE OSTI2024

Scaling Ensembles of Data-Intensive Quantum Chemical Calculations for Millions of Molecules

Deep learning models are efficient computational tools that can accelerate the inverse design of molecules with desired functional properties by generating predictions at a fraction of the time required by traditional quantum chemical approaches. To ensure that a model maintains accuracy and transferability across broad regions of the chemical space explored during the inverse design, it must be trained on massively large volumes of simulation data. This requires running large-scale ensemble quantum chemical calculations on high-performance computing (HPC) systems for data collection. However, the efficient execution of such large ensemble calculations and the management of large volumes of output data require tools that can judiciously utilize computational resources and manage metadata overhead on the file system. Therefore, we present a high-performance, scalable, ensemble management framework for performing data-intensive quantum chemical electronic structure calculations for organic molecules. This framework provides abstractions to plug different ab initio, first principles, and first principles-based semi-empirical methods and executes them efficiently at large scale on HPC systems. It dynamically distributes tasks to resources and uses tiered storage for managing large collections of files. We employed this framework to process over ten million organic molecules and generate open-source datasets that provide UV-vis absorption spectra by running time-dependent density-functional tight-binding calculations. It is the largest database containing molecular optical spectra that were simulated with quantum chemical methods in a consistent manner.

Mehta, Kshitij↗
DOE OSTI2024

Probabilistic projections of the Amery Ice Shelf catchment, Antarctica, under conditions of high ice-shelf basal melt

Abstract. Antarctica's Lambert Glacier drains about one-sixth of the ice from the East Antarctic Ice Sheet and is considered stable due to the strong buttressing provided by the Amery Ice Shelf. While previous projections of the sea-level contribution from this sector of the ice sheet have predicted significant mass loss only with near-complete removal of the ice shelf, the ocean warming necessary for this was deemed unlikely. Recent climate projections through 2300 indicate that sufficient ocean warming is a distinct possibility after 2100. This work explores the impact of parametric uncertainty on projections of the response of the Lambert–Amery system (hereafter “the Amery sector”) to abrupt ocean warming through Bayesian calibration of a perturbed-parameter ice-sheet model ensemble. We address the computational cost of uncertainty quantification for ice-sheet model projections via statistical emulation, which employs surrogate models for fast and inexpensive parameter space exploration while retaining critical features of the high-fidelity simulations. To this end, we build Gaussian process (GP) emulators from simulations of the Amery sector at a medium resolution (4–20 km mesh) using the Model for Prediction Across Scales (MPAS)-Albany Land Ice (MALI) model. We consider six input parameters that control basal friction, ice stiffness, calving, and ice-shelf basal melting. From these, we generate 200 perturbed input parameter initializations using space filling Sobol sampling. For our end-to-end probabilistic modeling workflow, we first train emulators on the simulation ensemble and then calibrate the input parameters using observations of the mass balance, grounding line movement, and calving front movement with priors assigned via expert knowledge. Next, we use MALI to project a subset of simulations to 2300 using ocean and atmosphere forcings from a climate model for both low- and high-greenhouse-gas-emission scenarios. From these simulation outputs, we build multivariate emulators by combining GP regression with principal component dimension reduction to emulate multivariate sea-level contribution time series data from the MALI simulations. We then use these emulators to propagate uncertainty from model input parameters to predictions of glacier mass loss through 2300, demonstrating that the calibrated posterior distributions have both greater mass loss and reduced variance compared to the uncalibrated prior distributions. Parametric uncertainty is large enough through about 2130 that the two projections under different emission scenarios are indistinguishable from one another. However, after rapid ocean warming in the first half of the 22nd century, the projections become statistically distinct within decades. Overall, this study demonstrates an efficient Bayesian calibration and uncertainty propagation workflow for ice-sheet model projections and identifies the potential for large sea-level rise contributions from the Amery sector of the Antarctic Ice Sheet after 2100 under high-greenhouse-gas-emission scenarios.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2005

Simulating a Direction-Finder Search for an ELT

A computer program simulates the operation of direction-finding equipment engaged in a search for an emergency locator transmitter (ELT) aboard an aircraft that has crashed. The simulated equipment is patterned after the equipment used by the Civil Air Patrol to search for missing aircraft. The program is designed to be used for training in radio direction-finding and/or searching for missing aircraft without incurring the expense and risk of using real aircraft and ground search resources. The program places a hidden ELT on a map and enables the user to search for the location of the ELT by moving a 14 NASA Tech Briefs, March 2005 small aircraft image around the map while observing signal-strength and direction readings on a simulated direction- finding locator instrument. As the simulated aircraft is turned and moved on the map, the program updates the readings on the direction-finding instrument to reflect the current position and heading of the aircraft relative to the location of the ELT. The software is distributed in a zip file that contains an installation program. The software runs on the Microsoft Windows 9x, NT, and XP operating systems.

Bream, Bruce↗
DOE OSTI2024

Constraining Galaxy-Halo connection using machine learning

We investigate the potential of machine learning (ML) methods to model small-scale galaxy clustering for constraining Halo Occupation Distribution (HOD) parameters. Our analysis reveals that while many ML algorithms report good statistical fits, they often yield likelihood contours that are significantly biased in both mean values and variances relative to the true model parameters. This highlights the importance of careful data processing and algorithm selection in ML applications for galaxy clustering, as even seemingly robust methods can lead to biased results if not applied correctly. ML tools offer a promising approach to exploring the HOD parameter space with significantly reduced computational costs compared to traditional brute-force methods if their robustness is established. Using our ANN-based pipeline, we successfully recreate some standard results from recent literature. Properly restricting the HOD parameter space, transforming the training data, and carefully selecting ML algorithms are essential for achieving unbiased and robust predictions. Among the methods tested, artificial neural networks (ANNs) outperform random forests (RF) and ridge regression in predicting clustering statistics, when the HOD prior space is appropriately restricted. We demonstrate these findings using the projected two-point correlation function (w p (r p )), angular multipoles of the correlation function (ξ ℓ (r)), and the void probability function (VPF) of Luminous Red Galaxies from Dark Energy Spectroscopic Instrument mocks. Our results show that while combining w p (r p ) and VPF improves parameter constraints, adding the multipoles ξ 0 , ξ 2 , and ξ 4 to w p (r p ) does not significantly improve the constraints.

cosmology↗
DOE OSTI2026

Inverse Mapping of the Collision Kernel and Wall Flux Scaling in a Tall Convection‐Cloud Chamber Using Local Sensors and Knowledge‐Informed Deep Learning

Droplet collision–coalescence is a crucial process in cloud physics, but accurately representing this process under different dynamical conditions remains challenging. A proposed future convective‐cloud chamber aims to investigate this key process, but the method for observing it remains unclear, even though it is theoretically established that collision‐coalescence will occur. This study serves as a proof‐of‐concept demonstration of how knowledge‐informed deep learning, combined with measurement data from local sensors in the chamber, can be used to estimate the collision kernels, which determine how the droplet size distribution evolves during collision‐coalescence. In addition to estimating the collision kernel, we also address wall fluxes, another uncertain but important process that acts as a source of heat and moisture in the chamber. Ensemble runs of large‐eddy simulations are conducted by scaling the wall fluxes and the collision kernel, while the measured flow and cloud properties are used as inputs for a neural network. Results indicate that this approach successfully maps the scaling of wall fluxes and the collision kernel with biases of approximately 1% or less relative to the range of the target data. This proof‐of‐concept lays the groundwork for future applications; when the real measurements are available, real sensor data combined with the trained model presented in this work will enable estimation of the actual wall fluxes and collision kernel.

cloud chamber↗
DOE OSTI2023

Neural networks for parameter estimation in intractable models

The goal is to use deep learning models to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible. For instance, inference for max-stable processes is exceptionally challenging even with small datasets, but simulation is straightforward. Data from model simulations are used to train deep neural networks and learn statistical parameters from max-stable models. The proposed neural network-based method provides a competitive alternative to current approaches, as demonstrated by considerable accuracy and computational time improvements. Finally, it serves as a proof of concept for deep learning in statistical parameter estimation and can be extended to other estimation problems.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1977

Supersonic separated turbulent boundary - layer over a wavy wall

A prediction method is developed for calculating distributions of surface heating rates, pressure and skin friction over a wavy wall in a two-dimensional supersonic flow. Of particular interest is the flow of thick turbulent boundary layers. The surface geometry and the flow conditions considered are such that there exists a strong interaction between the viscous and inviscid flow. First, using the interacting turbulent boundary layer equations, the problem is formulated in physical coordinates and then a reformulation of the governing equations in terms of Levy-Lees variables is given. Next, a numerical scheme for solving interacting boundary layer equations is adapted. A number of modifications which led to the improvement of the numerical algorithm are discussed. Finally, results are presented for flow over a train of up to six waves at various flow conditions.

Polak, A.↗
NASA NTRS2000

Crew Factors in Flight Operations: A Survey of Fatigue Factors in Corporate/Executive A Viation Operations - 8

Corporate flight crews face unique challenges including unscheduled flights, quickly changing schedules, extended duty days, long waits, time zone changes, and peripheral tasks. Most corporate operations are regulated by Part 91 FARs which set no flight or duty time limits. The objective of this study was to identify operationally significant factors that may influence fatigue, alertness, and performance in corporate operations. In collaboration with the National Business Aircraft Association and the Flight Safety Foundation, NASA developed and distributed a retrospective survey comprising 107 questions addressing demographics, home sleep habits, flight experience, duty schedules, fatigue during operations, and work environment. Corporate crewmembers returned 1,488 surveys. Respondents averaged 45.2 years of age, had 14.9 years of corporate flying experience, and 9,750 total flight hours. The majority (89%) rated themselves as 'good' or 'very good' sleepers at home. Most (82%) indicated they are subject to call for duty and described an average duty day of 9.9 h. About two-thirds reported having a daily duty time limit and over half (57%) reported a daily flight time limit. Nearly three-quarters (71%) acknowledged having 'nodded off' during a flight. Only 21% reported that their flight departments offer training on fatigue issues. Almost three-quarters (74%) described fatigue as a 'moderate' or 'serious' concern, and a majority (61%) characterized it as a common occurrence. Most (85%) identified fatigue as a 'moderate' or 'serious' safety issue.

Rosekind, Mark R.↗
NASA NTRS2002

Enhancing Science Teacher Training Using Water Resources and GLOBE

Heritage College, located on the Yakama Indian Reservation in south central Washington state, serves a multicultural, underserved, rural population and trains teachers to staff the disadvantaged school districts on and surrounding the reservation. In-service teachers and pre-service teachers in the area show strength in biology but have weak backgrounds in chemistry and mathematics. We are addressing this problem by providing a 2-year core of courses for 3 groups of 25 students (15 pre-service and 10 in-service teachers) using GLOBE to teach integrated physical science and mathematics. At the conclusion of the program, the students will qualify for science certification by Washington State. Water resources are the focal point of the curriculum because it is central to life in our desert area. The lack or excess of water, its uses, quality and distribution is being studied by using GIS, remote sensing and historical records. Students are learning the methodology to incorporate scientific protocols and data into all aspects of their future teaching curriculum. In addition, in each of the three years of the project, pre-service teachers attended a seminar series during the fall semester with presentations by collaborators from industry, agriculture, education and government agencies. Students used NASA educational materials in the presentations that they gave at the conclusion of the seminar series. All pre- and in-service teachers continue to have support via a local web site for Heritage College GLOBE participants.

Falco, James W.↗
NASA NTRS2019

Application of High-Dimensional Fuzzy K-Means Cluster Analysis to CALIOP/CALIPSO Version 4.1 Cloud-Aerosol Discrimination

This study applies fuzzy k-means (FKM) cluster analyses to a subset of the parameters reported in the CALIPSO lidar level 2 data products in order to classify the layers detected as either clouds or aerosols. The results obtained are used to assess the reliability of the cloud–aerosol discrimination (CAD) scores reported in the version 4.1 release of the CALIPSO data products. FKM is an unsupervised learning algorithm, whereas the CALIPSO operational CAD algorithm (COCA) takes a highly supervised approach. Despite these substantial computational and architectural differences, our statistical analyses show that the FKM classifications agree with the COCA classifications for more than 94 % of the cases in the troposphere. This high degree of similarity is achieved because the lidar-measured signatures of the majority of the clouds and the aerosols are naturally distinct, and hence objective methods can independently and effectively separate the two classes in most cases. Classification differences most often occur in complex scenes (e.g., evaporating water cloud filaments embedded in dense aerosol) or when observing diffuse features that occur only intermittently (e.g., volcanic ash in the tropical tropopause layer). The two methods examined in this study establish overall classification correctness boundaries due to their differing algorithm uncertainties. In addition to comparing the outputs from the two algorithms, analysis of sampling, data training, performance measurements, fuzzy linear discriminants, defuzzification, error propagation, and key parameters in feature type discrimination with the FKM method are further discussed in order to better understand the utility and limits of the application of clustering algorithms to space lidar measurements. In general, we find that both FKM and COCA classification uncertainties are only minimally affected by noise in the CALIPSO measurements, though both algorithms can be challenged by especially complex scenes containing mixtures of discrete layer types. Our analysis results show that attenuated backscatter and color ratio are the driving factors that separate water clouds from aerosols; backscatter intensity, depolarization, and mid-layer altitude are most useful in discriminating between aerosols and ice clouds; and the joint distribution of backscatter intensity and depolarization ratio is critically important for distinguishing ice clouds from water clouds.

Zeng, Shan↗
DOE OSTI2026

Innovating Distributed Embedded Energy Prize (InDEEP): A Lessons Learned Report

The U.S. Department of Energy's Water Power Technologies Office (WPTO) launched the Innovating Distributed Embedded Energy Prize (InDEEP) in March 2023 to accelerate innovation in Distributed Embedded Energy Conversion Technologies (DEEC-Tec) for ocean wave energy. Administered by the National Laboratory of the Rockies (NLR) with technical support from Sandia National Laboratories (SNL), InDEEP focused on the development of small, distributed, and embeddable energy converters (DEECs) and their integration into scalable DEEC-Tec metamaterials for marine renewable energy applications. Spanning three phases over two years, InDEEP awarded approximately $2.3 million to teams from academia, industry, and startups. Phase I emphasized conceptual design. Phase II moved into the prototyping of individual DEECs. Phase III required integration into functional DEEC-Tec metamaterial prototypes. Across 60 submissions, teams explored a wide range of energy conversion mechanisms - including piezoelectric, variable-capacitance, ionic, and inductive methods. Note, the prize did not include the design nor demonstration of ocean wave energy conversion systems. Rather, the prize only required participants to design and demonstrate individual DEECs and corresponding DEEC-Tec metamaterials. This prize utilized a mix of novel and proven techniques to attract participants from outside marine energy, including an engagement leaderboard, robust recruitment, technical expert mentorship, and a suite of technical trainings. Key insights from the competition emphasized that DEEC-Tec metamaterials must be intentionally designed to produce beneficial emergent behaviors - advantages that go beyond simply combining multiple DEEC units. Top-performing teams showed that thoughtful design of system architecture, coordinated deformation, and systems adaptabilities could unlock meaningful performance gains both at the DEEC system level and DEEC-Tec metamaterial system level. A critical realization was that many DEEC-Tec metamaterials could benefit from being designed to accept lower-frequency energy inputs and shift those into higher-frequencies per each DEEC making up the respective DEEC-Tec metamaterial. Other important takeaways included the need for rigorous and quantitative performance testing, effective integration of power conditioning electronics, and the pivotal role of material science in enabling innovative, adaptive DEEC-Tec-based energy conversion designs. InDEEP also helped establish a growing DEEC-Tec community of practitioners, attracting participants from beyond traditional marine energy sectors. Through a strong support infrastructure, InDEEP fostered early-stage innovation and laid a foundation for future DEEC-Tec-based ocean wave energy conversion solutions - positioning DEEC-Tec as a promising pathway toward scalable, resilient ocean wave energy conversion. Through focused R&D of individual DEECs and their integration into DEEC-Tec metamaterials, alongside a growing, multidisciplinary community catalyzed by InDEEP, there is a strong opportunity to drive a disruptive shift in ocean wave energy conversion design and development. This convergence of novel architectures, emergent behaviors, and collaborative innovation positions DEEC-Tec as a transformative approach, moving the field from rigid, centralized energy conversion-based designs to resilient, modular systems highly adaptable for real-world ocean wave energy conversion applications.

16 TIDAL AND WAVE POWER↗
DOE OSTI2023

Reinforcement Learning-based Output Structured Feedback for Distributed Multi-Area Power System Frequency Control

Load frequency control (LFC) is a key factor to maintain the stable frequency in multi-area power systems. As the modern power systems evolve from centralized to decentralized paradigm, LFC needs to consider the decentralized scheme that considers limited information from the information-exchange graph for the generator control of each interconnected area. This paper aims to solve a data-driven constrained LQR problem with mean-variance risk constraints and output structured feedback, and applies this framework to solve the LFC problem in multi-area power systems. By reformulating the constrained optimization problem into a minimax problem, the stochastic gradient descent max-oracle (SGDmax) algorithm with zero-order policy gradient (ZOPG) is adopted to find the optimal feedback gain from the learning, while guaranteeing the convergence. In addition, to improve the adaptation of the proposed learning method to new or varying models, we construct an emulator grid that approximates the dynamics of a physical grid and performs training based on this model. Once the feedback gain is obtained from the emulator grid, it is applied to the physical grid with a robustness test to check whether the controller from the approximated emulator applies to the actual system. Numerical tests show that the obtained feedback controller can successfully control the frequency of each area, while mitigating the uncertainty from the loads, with reliable robustness that ensures the adaptability of the obtained feedback gain to the actual physical grid.

Kwon, Kyung-bin↗