Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model uncertainty”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Reactor antineutrino flux and anomaly

Reactor antineutrinos have played a significant role in establishing the standard model of particle physics and the theory of neutrino oscillations. In this article, we review the reactor antineutrino flux and in particular the reactor antineutrino anomaly (RAA) coined over a decade ago. RAA refers to a deficit of the measured antineutrino inverse beta decay rates at very short-baseline reactor experiments compared to the theoretically improved predictions (i.e. the Huber–Mueller model). Since the resolution of several previous experimental anomalies have led to the discovery of non-zero neutrino mass and mixing, many efforts have been invested to study the origin of RAA both experimentally and theoretically. The progress includes the observation of discrepancies in antineutrino energy spectrum between data and the Huber–Mueller model, the re-evaluation of the Huber–Mueller model uncertainties, the potential isotope-dependent rate deficits, and the better agreement between data and new model predictions using the improved summation method. Importantly, these developments disfavor the hypothesis of a light sterile neutrino as the explanation of RAA and supports the deficiencies of Huber–Mueller model as the origin. Looking forward, more effort from both the theoretical and experimental sides is needed to fully understand the root of RAA and to make accurate predictions of reactor antineutrino flux and energy spectrum for future discoveries.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Planck 2018 results. V. CMB power spectra and likelihoods

We describe the legacy Planck cosmic microwave background (CMB) likelihoods derived from the 2018 data release. The overall approach is similar in spirit to the one retained for the 2013 and 2015 data release, with a hybrid method using different approximations at low ( ℓ < 30) and high ( ℓ ≥ 30) multipoles, implementing several methodological and data-analysis refinements compared to previous releases. With more realistic simulations, and better correction and modelling of systematic effects, we can now make full use of the CMB polarization observed in the High Frequency Instrument (HFI) channels. The low-multipole EE cross-spectra from the 100 GHz and 143 GHz data give a constraint on the ΛCDM reionization optical-depth parameter τ to better than 15% (in combination with the TT low- ℓ data and the high- ℓ temperature and polarization data), tightening constraints on all parameters with posterior distributions correlated with τ . We also update the weaker constraint on τ from the joint TEB likelihood using the Low Frequency Instrument (LFI) channels, which was used in 2015 as part of our baseline analysis. At higher multipoles, the CMB temperature spectrum and likelihood are very similar to previous releases. A better model of the temperature-to-polarization leakage and corrections for the effective calibrations of the polarization channels (i.e., the polarization efficiencies) allow us to make full use of polarization spectra, improving the ΛCDM constraints on the parameters θ MC , ω c , ω b , and H 0 by more than 30%, and n s by more than 20% compared to TT-only constraints. Extensive tests on the robustness of the modelling of the polarization data demonstrate good consistency, with some residual modelling uncertainties. At high multipoles, we are now limited mainly by the accuracy of the polarization efficiency modelling. Using our various tests, simulations, and comparison between different high-multipole likelihood implementations, we estimate the consistency of the results to be better than the 0.5 σ level on the ΛCDM parameters, as well as classical single-parameter extensions for the joint likelihood (to be compared to the 0.3 σ levels we achieved in 2015 for the temperature data alone on ΛCDM only). Minor curiosities already present in the previous releases remain, such as the differences between the best-fit ΛCDM parameters for the ℓ < 800 and ℓ > 800 ranges of the power spectrum, or the preference for more smoothing of the power-spectrum peaks than predicted in ΛCDM fits. These are shown to be driven by the temperature power spectrum and are not significantly modified by the inclusion of the polarization data. Overall, the legacy Planck CMB likelihoods provide a robust tool for constraining the cosmological model and represent a reference for future CMB observations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

DEPRECATED AI-Batt-OS (Autonomous Identification of Battery Life Models - Open Source) [SWR 21-17]

DEPRECATED. This repository was archived by the owner on Jun 30, 2026. It is now read-only. Open source implementation of some of the methods utilized by AI-Batt, a battery lifetime modeling and analysis toolkit provided by the National Laboratory of the Rockies (NLR). This software demonstrates the use of bi-level optimization and symbolic regression techniques to semi-autonomously identify algebraic models predicting the capacity fade of lithium-ion batteries during calendar aging. Modeling the degradation of batteries is a complex task, due to the difficulty in separating the time-dependent and time-independent factors impacting cell level degradation, across multiple data series with different numbers of measurements and/or data quality. Bi-level optimization enables model parameters to be optimized to either the entire data set or to individual data series, allowing statistical disambiguation of global behaviors (data series independent) and local behaviors (data series dependent). Symbolic regression is used to automatically search for optimal low-dimesional models predicting the variation of locally optimized parameters versus time-independent experimental variables from millions of possible models, resulting in a more accurate and repeatable model identification process than is possible by a manual search. The provided tools also implement cross-validation and bootstrap resampling schemes, empowering statistical model comparison/selection and quantification of model uncertainties. An example script replicates the results from the manuscript "Challenging Practices of Algebraic Battery Life Models through Statistical Validation and Model Identification via Machine-Learning", submitted to ECS. All code is written in MATLAB. Requires the Statistics and Machine Learning Toolbox. Contact Dr. Paul Gasper at Paul.Gasper@nlr.gov for any questions.

Gasper, Paul↗
DOE OSTI2024

Boundary-Aware Adversarial Learning Domain Adaption and Active Learning for Cross-Sensor Building Extraction

The use of convolutional neural networks (CNNs) for building extraction from remote sensing images has been widely studied and many public datasets have been made available for accelerating development of these CNN models. Yet adapting pretrained models at scale in real-world scenarios remains a challenging task. The main barrier is that certain new labels are still needed to compensate for domain shifting between the labeled data and new images that potentially cover new geographic locations or that are from a different sensor. In this article, we propose to add informatively labeled samples from a new image pool under the paradigm of active learning. To select the most useful samples based on model uncertainty, we first tackle the problem of uncalibrated uncertainty estimation due to distribution shifting by adapting feature extractors with boundary-based adversarial learning. Calibrated uncertainty is used as the query criterion in the active learning process, where the most uncertain samples are selected for annotation and included for model retraining. The proposed workflow was tested with three data pairs in which each workflow represents a scenario often encountered in real-world applications, including adapting pretrained models to new images collected with different sensors or to new geographic areas where appearances and types of buildings are very different. Compared to several baselines, including random sampling, temperature scaling (a well-known uncertainty calibration technique), different query strategies, and active domain adaptation methods, the proposed workflow shows that strategically querying a smaller set of samples for labeling achieves comparable or better building extraction performance. The proposed method reduces the number of labeled samples required to achieve sufficient model accuracy, thus significantly reducing hundreds of person-hours for labeled data creation. In addition, we include a few considerations when deploying this workflow in a GPU cluster that can be easily adapted to achieve operational building extraction model retraining.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Model averaging approaches to data subset selection

Model averaging is a useful and robust method for dealing with model uncertainty in statistical analysis. Often, it is useful to consider data subset selection at the same time, in which model selection criteria are used to compare models across different subsets of the data. Two different criteria have been proposed in the literature for how the data subsets should be weighted. We compare the two criteria closely in a unified treatment based on the Kullback-Leibler divergence and conclude that one of them is subtly flawed and will tend to yield larger uncertainties due to loss of information. Here, analytical and numerical examples are provided.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Projective Integral Updates for High-Dimensional Variational Inference

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

Gaussian mean-field↗
DOE OSTI2023

Machine Learning for Daily Forecasts of Arctic Sea Ice Motion: An Attribution Assessment of Model Predictive Skill

Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Total Measurement Uncertainty in Neutron Coincidence Multiplicity Analysis

Neutron multiplicity counting is the most commonly used nondestructive assay technique for determining the plutonium mass within containers of scrap PuO 2 or mixed oxide (MOX). In multiplicity analysis, the 240 Pu eff mass, leakage multiplication, and alpha ratio (the ratio of [α, n]-to-spontaneous fission neutron production) are the three primary unknown sample properties. They must be determined simultaneously. To solve for these three unknowns in a multiplicity assay, three measured values are needed: the singles, doubles, and triples neutron count rates. While the analysis is limited to solving for three unknowns, there are many additional factors that impact the observed count rates and contribute to the measurement uncertainty. In this study we investigate the various uncertainty contributors for the multiplicity analysis through a combination of traditional uncertainty propagation techniques supplemented by Monte Carlo simulations to address the dependences not explicitly expressed by the point source model. Uncertainties arising from counting statistics, calibration parameters, calibration method, nuclear data, and various material characteristics (isotopic abundances, chemical form, density, and impurities) are considered. A Total Measurement Uncertainty (TMU) estimate is then developed from these uncertainty contributors. This study is confined to multiplicity analysis of items commonly encountered in international safeguards applications. That is, the study focused on Pu oxides and MOX materials for the masses ranging up to 4000 grams total Pu. Multiplicity measurements were simulated using MCNP V6 based on the Plutonium Scrap Multiplicity Counter (PSMC), Epithermal Multiplicity Counter (ENMC), Pyrochemical Multiplicity Counter, and Large Epithermal Multiplicity Counter (LEMC) for this study; however, this report focuses on the parameterization of the uncertainties for the PSMC. The performance differences between the PSMC and the other multiplicity counting systems are relatively small, primarily manifesting in the impact on measurement precision so that the evaluation developed for the PSMC can be applied to the other multiplicity counting systems. Finally an analysis tool, the Multiplicity TMU Estimator, was developed from this study to serve as an aid for evaluation of the total measurement uncertainty of multiplicity assay results obtained from the commonly used INCC acquisition and analysis software.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Robust constrained tension control for high-precision roll-to-roll processes

Tension control is critical for maintaining good product quality in most roll-to-roll (R2R) production systems. Previous work has primarily focused on improving the disturbance rejection performance of tension controllers. Here, a robust linear parameter-varying model predictive control (LPV-MPC) scheme is designed to enhance the tension tracking performance of a pilot R2R system for deposition of materials used in flexible thin film applications. The performance of a tension controller may degrade due to disturbances associated with model uncertainties and the slowly-changing dynamics in R2R systems. We introduce a method that separately treats these two sources of disturbance. The controller utilizes an incremental model to eliminate the errors caused by the mismatch between the nominal model and the actual system. A tube-based MPC formulation combined with scheduled parameters adequately updates models and corrects for the time-varying dynamics. Constraints on the rated motor torque are incorporated in the MPC to maintain the controller reliability and avoid machine failures. We illustrate the operation of our control algorithm through simulation of an actual R2R system. The controller outperforms the benchmarks in terms of fast transient response and offset-free tension tracking. Furthermore, it also demonstrates immunity from variations due to parametric uncertainties.

42 ENGINEERING↗
DOE OSTI2023

Knowledge-Informed Uncertainty-Aware Machine Learning for Time Series Forecasting of Dynamical Engineered Systems

The high complexity and multiscale nature of many engineered systems—such as those in nuclear power plants—make representing and forecasting their dynamic behavior challenging. Physics-based models can be overly complex and computationally intractable, whereas machine learning (ML) tools are often data-hungry and prone to unphysical solutions. This study proposes a knowledge-informed ML-aided hybrid residual modeling approach that offers accurate and efficient time series forecasting for the operation of dynamical engineered systems. Hybrid residual modeling entails a baseline solution from domain knowledge and known physics expressions about the system dynamics integrated with an ML model to capture undiscovered information from the mismatch (i.e., residuals) between true states from measurements and baseline-predicted outputs. This study further quantifies the ML model uncertainty to provide trustworthy solutions. Real-time operational data from thermal-hydraulic flow loops of the cryogenic moderator system in Oak Ridge National Laboratory’s Spallation Neutron Source facility were used to demonstrate the potential of knowledge-informed uncertainty-aware ML in real-world applications. The state variables of the cryogenic helium loop were modeled with (1) first principles–based system identification (sysID), (2) long short-term memory (LSTM) neural network, and (3) hybrid sysID (baseline) + LSTM (residual). The superior predictive capability of the sysID+LSTM model versus stand-alone sysID and LSTM is confirmed by average performance metrics and individual data points across different prediction horizons. By creating a robust representation of the underlying physical system, the widely applicable hybrid residual modeling approach will enable the future development of digital twins for performance prediction, prognostics, and operation control.

Zhao, Xingang↗
DOE OSTI2022

Diffuse Radiation Forcing Constraints on Gross Primary Productivity and Global Terrestrial Evapotranspiration

Abstract The diffuse radiation fertilization effect—the increase in plant productivity in the presence of higher diffuse radiation ( K ↓,d )—is an important yet understudied aspect of atmosphere‐biosphere interactions and can modify the terrestrial carbon, energy, and water budgets. The K ↓,d fertilization effect links the carbon cycle with clouds and aerosols, all of which are large sources of uncertainties for our current understanding of the Earth system and for future climate projections. Here we establish to what extent observational and modeling uncertainty in sunlight's diffuse fraction ( k d ) affects simulated gross primary productivity (GPP) and terrestrial evapotranspiration ( λE ). We find only 48 eddy covariance sites with simultaneous sufficient measurements of K ↓,d with none in the tropical climate zone, making it difficult to constrain this mechanism globally using observations. Using a land modeling framework based on the latest version of the Community Land Model, we find that global GPP ranges from 114 Pg C year −1 when using k d forcing from the Modern‐Era Retrospective analysis for Research and Applications, version 2 reanalysis to a ∼7% higher value of 122 Pg C year −1 when using the Clouds and the Earth's Radiant Energy System satellite product, with especially strong differences apparent over the tropical region (mean increase ∼9%). The differences in λE , although smaller (−0.4%) due to competing changes in shaded and sunlit leaf transpiration, can be greater than regional impacts of individual forcing agents like aerosols. Our results demonstrate the importance of comprehensively and systematically validating the simulated k d by atmosphere modules as well as the response to differences in k d within land modules across Earth System Models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Hyper‐Local Temperature Prediction Using Detailed Urban Climate Informatics

The accurate modeling of urban microclimate is a challenging task given the high surface heterogeneity of urban land cover and the vertical structure of street morphology. Recent years have witnessed significant efforts in numerical modeling and data collection of the urban environment. Nonetheless, it is difficult for the physical‐based models to fully utilize the high‐resolution data under the constraints of computing resources. The advancement in machine learning (ML) techniques offers the computational strength to handle the massive volume of data. In this study, we proposed a modeling framework that uses ML approach to estimate point‐scale street‐level air temperature from the urban‐resolving meso‐scale climate model and a suite of hyper‐resolution urban geospatial data sets, including three‐dimensional urban morphology, parcel‐level land use inventory, and weather observations from a sensor network. We implemented this approach in the City of Chicago as a case study to demonstrate the capability of the framework. The proposed approach vastly improves the resolution of temperature predictions in cities, which will help the city with walkability, drivability, and heat‐related behavioral studies. Moreover, we tested the model's reliability on out‐of‐sample locations to investigate the modeling uncertainties and the application potentials to the other areas. This study aims to gain insights into next‐gen urban climate modeling and guide the observation efforts in cities to build the strength for the holistic understanding of urban microclimate dynamics.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Impacts of irrigation expansion on moist-heat stress based on IRRMIP results

Irrigation rapidly expanded during the 20 th century, affecting climate via water, energy, and biogeochemical changes. Previous assessments of these effects predominantly relied on a single Earth System Model, and therefore suffered from structural model uncertainties. Here we quantify the impacts of historical irrigation expansion on climate by analysing simulation results from six Earth system models participating in the Irrigation Model Intercomparison Project (IRRMIP). Results show that irrigation expansion causes a rapid increase in irrigation water withdrawal, which leads to less frequent 2-meter air temperature heat extremes across heavily irrigated areas (≥4 times less likely). However, due to the irrigation-induced increase in air humidity, the cooling effect of irrigation expansion on moist-heat stress is less pronounced or even reversed, depending on the heat stress metric. In summary, this study indicates that irrigation deployment is not an efficient adaptation measure to escalating human heat stress under climate change, calling for carefully dealing with the increased exposure of local people to moist-heat stress.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Quantifying Uncertainty in All-to-All Estimates of Space Object Conjunction Probabilities using U-Statistics

Predicting space object conjunctions is inherently probabilistic due to initial state and orbit model uncertainty. A commonly considered Monte Carlo estimator of the conjunction probability is the ’all-to-all’ estimator. Given independent random samples of the trajectories of both objects, the estimator is the percentage of all pairs of trajectories that result in a conjunction. Intuitively, the all-to-all estimator is the best possible estimator of the conjunction probability since it considers all pairs of Monte Carlo samples. However, its distribution is not available in closed-form, which limits its use in practice and makes this intuition difficult to make rigorous. In this paper, the all-to-all estimator is identified as a U-statistic, which implies that it has several favorable properties. Specifically, the estimator is the minimum variance unbiased estimator of the conjunction probability and is asymptotically Gaussian distributed. An approximate confidence interval for the conjunction probability is obtained from an estimate of the asymptotic Gaussian distribution. We show how to efficiently compute the confidence interval and demonstrate that the interval has the nominal coverage level. The confidence intervals are also seen to be narrower than those based on the commonly-used each-to-each estimator. Furthermore, the all-to-all estimator is shown to allow different Monte Carlo sample sizes, whereas the each-to-each estimator requires equal sample sizes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Quantifying uncertainty in machine learning for nuclear binding energy

Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory; however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked. Epistemic uncertainties arising from training the same network multiple times for an ensemble of initial weight sets offer a first insight into the confidence of machine learning predictions, but they often come with a high computational cost. Instead, we apply a single-model uncertainty quantification method called Δ-UQ that gives epistemic uncertainties with one-time training. Here, we demonstrate our approach on a two-feature model of nuclear binding energies per nucleon with proton and neutron number pairs as inputs. We show that Δ-UQ can produce reliable and self-consistent epistemic uncertainty estimates and can be used to assess the degree of confidence in predictions made with deep neural networks.

Huang, Mengyao [Lawrence Livermore National Labora↗
DOE OSTI2024

Enhancing Solar Power Forecasting with Regularized Constrained Quantile Regression Averaging and Bootstrapping Techniques

Probabilistic solar power forecasting (SPF) plays an essential role in optimizing power-grid operations by quantifying the forecast uncertainty. To improve the accuracy and robustness of probabilistic SPF, this paper introduces the regularized constrained quantile regression averaging (rCQRA) method to combine outputs from multiple PSPF models. In addition, a bootstrapping method was used to quantify model uncertainty, providing insights into the reliability and significance of each ensemble component. To evaluate its efficacy, the proposed rCQRA method is used to integrate four PSPF methods. The resulting SPF models are trained and validated using a real-world six-year dataset from a rooftop solar plant in the USA. The performance of the proposed rCQRA method is evaluated and compared with two benchmark methods under three categories of weather conditions. It is shown that the rCQRA method has superior performance in its forecast reliability, sharpness, and accuracy.

Ensemble learning, probabilistic solar power forec↗
DOE OSTI2025

Understanding drivers and uncertainty in projected African precipitation

We investigate the drivers of projected summer precipitation changes and their uncertainties across Africa in the second half of the 21st century under the SSP2-4.5 and SSP5-8.5 scenarios using CMIP6 models. Our results reveal distinct regional precipitation changes, particularly under SSP5-8.5, with robust increases of 75%, 24%, and 17% over the Sahara, South Eastern Africa, and South Central Africa, respectively, and a decline of up to 5% over West Southern Africa (WSAF). In most regions, precipitation increases are driven by enhanced vertical thermodynamic processes associated with temperature-induced moisture increases and enhanced moisture convergence. In contrast, the WSAF decrease is associated with vertical dynamic processes driven by a weakening of the Hadley circulation’s ascending branch. Model uncertainty accounts for over 85% of total projection uncertainty across all regions and is largely due to subgrid-scale parameterizations. Overall, this study enhances our understanding of climate change impacts on African precipitation.

Taguela, Thierry N↗
DOE OSTI2021

Deep Reinforcement Scheduling of Energy Storage Systems for Real-time Voltage Regulation in Unbalanced LV Networks with High PV Penetration

The ever-growing higher penetration of distributed energy resources (DERs) in low-voltage (LV) distribution systems brings both opportunities and challenges to voltage support and regulation. This paper proposes a deep reinforcement learning (DRL)-based scheduling scheme of energy storage systems (ESSs) to mitigate system voltage deviations in unbalanced LV distribution networks. The ESS-based voltage regulation problem is formulated as a multi-stage quadratic stochastic program, with the objective of minimizing the expected total daily voltage regulation cost while satisfying operational constraints. While existing voltage regulation methods are mostly focused on onetime- step control, this paper explores a day-horizon systemwide voltage regulation problem. In other words, the size of action and state spaces are extremely high-dimensional and need to be delicately handled. Furthermore, in order to overcome the difficulty of modeling uncertainties and develop a realtime solution, a learn-to-schedule feedback control framework is proposed by adapting the problem to a model-free DRL setting. The proposed algorithm is tested on a customized 6-bus system and a modified IEEE 34-bus system. Simulation results validate the effectiveness and near-optimality of voltage regulation by ESS in comparison with a deterministic quadratic program solution.

Wang, Shengyi↗