Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “time minimization”

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 1,189 records · Page 66
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Current-Voltage Analysis Tool for Solar Fuel Production (CATS) v0.1

The program is expected to be a useful tool during operation of a range of solar-driven electrochemical devices, such as PV-electrolyzers and photoelectrochemical (PEC) devices. It makes use of current-voltage data collected during operation, operation parameters that are easily accessible for many devices of interest. The program captures the time-dependence of loss mechanisms at play during PEC device operation and opens the door for real-time optimizations of operational parameters like the feed humidity to minimize performance losses. Currently, the program is useful for applications where the current-voltage polarization response of the photoabsorber and electrolyzer are pre-recorded, and changes over time can be estimated based on the pre-recorded current-voltage scans. More complicated scenarios that involve permanent degradation of the PV component or complex calculations of the electrolyzer current-voltage characteristics may be included in future versions of this software. Aside from the possibility of deconvoluting loss mechanisms, this software can also reveal possible performance benefits by convective PV cooling when the photoabsorber is integrated into the electrolysis cell. The latter can highlight why certain device architectures may be beneficial over others. No similar technologies are known to the developer.

Kistler, Tobias↗
NASA NTRS2021

Adaptive Aerostructures for Revolutionary Civil Supersonic Transportation

To enable commercially viable civil supersonic transport (SST) aircraft, innovative solutions must be developed to meet noise and efficiency requirements for overland flight. This research effort consists of a multidisciplinary team of academic and industrial experts exploring for the first time the potential of small real-time geometric outer mold line (OML) reconfigurations to minimize sonic boom signatures and aircraft drag in response to changing ambient conditions, thereby enabling noise-compliant overland supersonic flight. The team utilizes recent advances in supersonic computational fluid dynamic (CFD) methods, new noise prediction tools, and new design approaches to consider embedded highly energy-dense shape memory alloy (SMA) actuators for local shape modifications to an SST aircraft leading to optimal low boom signature and low drag in different environments. This university-led program will provide strategic leadership toward technology convergence that advances NASA's Aerospace Research Mission Directorate's (ARMD) research objectives with regard to Thrust 2: “Innovation in Commercial Supersonic Aircraft” by exploring for the first time enabling low-boom operation across a range of flight conditions via structural adaptivity, and will promote education of the next generation of engineers. The overall research strategy is to pursue three critical areas: the design of configurations for reducing boom, SMA material development and modeling, and technology feasibility demonstration in a relevant environment. Initially, the team will identify potential applications where structure or geometry adaptivity provides a benefit in noise or drag across the entire flight envelope. For selected applications/structural locations, required OML geometry changes will be determined based on analysis of sonic boom ground signature and drag reduction using new design tools, trade studies, and atmospheric sensing techniques. Designs will be developed and evaluated against requirements on loading, stroke length, and operational temperature. New alloy formulations will be developed tailored for both autonomous and controlled actuation modes. As the SMA material development matures, integrated system-level factors will be investigated. Optimized designs for small-scale distributed adaptivity applications of maximum benefit will then be matured and tested, moving toward demonstration of the innovative technology approaches at a TRL 4-5 and showing that sonic booms can be reduced by reconfiguration on demand.

Koushik Datta↗
DOE OSTI2025

Transformers and Long Short-Term Memory Transfer Learning for GenIV Reactor Temperature Time Series Forecasting

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors.

LSTM↗
NASA NTRS2008

Pointing Stability Performance of the Cassini Spacecraft

Twelve scientific instruments onboard the Cassini spacecraft depend on the accurate pointing capabilities of the spacecraft to return data critical to the success of the mission and to improving our understanding of Saturn. Throughout the seven year interplanetary cruise to Saturn and the four year prime mission, the control of the Cassini spacecraft is achieved by employing either the Reaction Control System (RCS) composed of a set of eight thrusters or the Reaction Wheel Assembly (RWA) made up of four reaction wheels, only three of which are active at a given time. The operations of Cassini imaging instruments (such as the Narrow Angle Camera) require a high level of spacecraft pointing stability in order to minimize the distortion and smearing of the image during the exposure time. In designing the Cassini attitude control system, a pointing stability performance metric that considered the frequency contents of the disturbance sources was employed. The flight performance of the Cassini pointing stability, achieved with a set of three reaction wheels or RCS thrusters, is summarized in this paper.

Lee, Allan Y.↗
DOE OSTI2023

Reinforcement-Learning-Based Smart Water Heater Control: An Actual Deployment

Utilizing smart control algorithms for electric water heaters (EWHs) is essential for fully harnessing the demand response (DR) potential of EWHs. For this reason, the use of reinforcement learning (RL) algorithms for EWHs has received increasing attention in recent years. However, existing RL approaches are either simulation-based or use pretrained RL agents. To this end, this paper presents the real-world deployment of a set of model-free RL approaches that aim to minimize the electricity cost of a EWH under a time-of-use electricity pricing policy using standard DR commands (e.g., shed, load up). The experiment results showed that the RL agents can help save electricity cost in the range of 11% to 14% compared to the baseline operation. This study demonstrated that RL-based EWH controllers can be deployed in real world without any prior training and can still save electricity cost.

deep learning↗
NASA NTRS2010

Evaluation of Enhanced High Resolution MODIS/AMSR-E SSTs and the Impact on Regional Weather Forecast

Over the last few years, the NASA Short-term Prediction Research and Transition (SPoRT) Center has been generating a 1-km sea surface temperature (SST) composite derived from retrievals of the Moderate Resolution Imaging Spectroradiometer (MODIS) for use in operational diagnostics and regional model initialization. With the assumption that the day-to-day variation in the SST is nominal, individual MODIS passes aboard the Earth Observing System (EOS) Aqua and Terra satellites are used to create and update four composite SST products each day at 0400, 0700, 1600, and 1900 UTC, valid over the western Atlantic and Caribbean waters. A six month study from February to August 2007 over the marine areas surrounding southern Florida was conducted to compare the use of the MODIS SST composite versus the Real-Time Global SST analysis to initialize the Weather Research and Forecasting (WRF) model. Substantial changes in the forecast heat fluxes were seen at times in the marine boundary layer, but relatively little overall improvement was measured in the sensible weather elements. The limited improvement in the WRF model forecasts could be attributed to the diurnal changes in SST seen in the MODIS SST composites but not accounted for by the model. Furthermore, cloud contamination caused extended periods when individual passes of MODIS were unable to update the SSTs, leading to substantial SST latency and a cool bias during the early summer months. In order to alleviate the latency problems, the SPoRT Center recently enhanced its MODIS SST composite by incorporating information from the Advanced Microwave Scanning Radiometer-EOS (AMSR-E) instruments as well as the Operational Sea Surface Temperature and Sea Ice Analysis. These enhancements substantially decreased the latency due to cloud cover and improved the bias and correlation of the composites at available marine point observations. While these enhancements improved upon the modeled cold bias using the original MODIS SSTs, the discernable impacts on the WRF model were still somewhat limited. This paper explores several factors that may have contributed to this result. First, the original methodology to initialize the model used the most recent SST composite available in a hypothetical real ]time configuration, often matching the forecast initial time with an SST field that was 5-8 hours offset. To minimize the differences that result from the diurnal variations in SST, the previous day fs SST composite is incorporated at a time closest to the model initialization hour (e.g. 1600 UTC composite at 1500 UTC model initialization). Second, the diurnal change seen in the MODIS SST composites was not represented by the WRF model in previous simulations, since the SSTs were held constant throughout the model integration. To address this issue, we explore the use of a water skin-temperature diurnal cycle prediction capability within v3.1 of the WRF model to better represent fluctuations in marine surface forcing. Finally, the verification of the WRF model is limited to very few over-water sites, many of which are located near the coastlines. In order to measure the open ocean improvements from the AMSR-E, we could use an independent 2-dimensional, satellite-derived data set to validate the forecast model by applying an object-based verification method. Such a validation technique could aid in better understanding the benefits of the mesoscale SST spatial structure to regional models applications.

Schiferl, Luke D.↗
NASA NTRS2007

Flight Qualified Micro Sun Sensor

A prototype small, lightweight micro Sun sensor (MSS) has been flight qualified as part of the attitude-determination system of a spacecraft or for Mars surface operations. The MSS has previously been reported at a very early stage of development in NASA Tech Briefs, Vol. 28, No. 1 (January 2004). An MSS is essentially a miniature multiple-pinhole electronic camera combined with digital processing electronics that functions analogously to a sundial. A micromachined mask containing a number of microscopic pinholes is mounted in front of an active-pixel sensor (APS). Electronic circuits for controlling the operation of the APS, readout from the pixel photodetectors, and analog-to-digital conversion are all integrated onto the same chip along with the APS. The digital processing includes computation of the centroids of the pinhole Sun images on the APS. The spacecraft computer has the task of converting the Sun centroids into Sun angles utilizing a calibration polynomial. The micromachined mask comprises a 500-micron-thick silicon wafer, onto which is deposited a 57-nm-thick chromium adhesion- promotion layer followed by a 200-nm-thick gold light-absorption layer. The pinholes, 50 microns in diameter, are formed in the gold layer by photolithography. The chromium layer is thin enough to be penetrable by an amount of Sunlight adequate to form measurable pinhole images. A spacer frame between the mask and the APS maintains a gap of .1 mm between the pinhole plane and the photodetector plane of the APS. To minimize data volume, mass, and power consumption, the digital processing of the APS readouts takes place in a single field-programmable gate array (FPGA). The particular FPGA is a radiation- tolerant unit that contains .32,000 gates. No external memory is used so the FPGA calculates the centroids in real time as pixels are read off the APS with minimal internal memory. To enable the MSS to fit into a small package, the APS, the FPGA, and other components are mounted on a single two-sided board following chip-on-board design practices

Liebe, Carl Christian↗
DOE OSTI2025

Bridging the gap: Deploying AI-based Models in Real-Time Fusion Plasma Control Systems

Achieving reliable real-time control in fusion plasma experiments requires strict timing guarantees across entire control algorithms. In earlier work by Abbate et al. (2023), we demonstrated the feasibility of neural-network-based control algorithms on the DIII-D tokamak using the internally developed open-source Keras2C library for model conversion into C (Conlin et al. (2021)). However, the initial implementations relied on data buffering and branching logic outside the neural network code, causing variability in execution times. Subsequent deployments on DIII-D and KSTAR—including the RTCAKENN algorithm for kinetic profile reconstruction—proved that minimizing branching and buffering throughout the pipeline yields consistent millisecond-level cycle times under real experimental conditions (Shousha et al. (2023)). However, keeping pace with rapidly evolving AI frameworks (e.g. PyTorch) is challenging. Finally, we, therefore, propose a community-driven open-source effort to expand the tool, enabling real-time deployment across diverse systems that require strictly bounded execution times.

AI-based models↗
DOE OSTI2020

Remediation of Temporary Storage Sites in Support of the Port Hope Area Initiative - 20295

The Port Hope Area Initiative is a community-based solution for the long-term management of historic low level radioactive waste (LLRW) resulting from 60 years of uranium and radium processing operations in the Town of Port Hope which is located in Ontario, Canada. The Eldorado refinery, on the north shore of Lake Ontario, began refining radium-226 from pitchblende ore, later transitioning to the refining of uranium. Through the history of the operation, LLRW was deposited throughout the town of Port Hope as a result of fugitive emissions from the plant and/or through the re-use of process residues as building material and backfill. Historical clean-up activities conducted in the late 1970's involved the remediation of approximately 400 properties and the relocation of 100,000 cubic metres of contaminated soil to a disposal facility in Chalk River operated by Atomic Energy of Canada Limited (AECL). Owing to space limitations at that disposal facility, any LLRW identified through construction monitoring since that time has been stored in the community at three temporary storage sites located throughout the town. These include: the Centre Pier mound that contained approximately of 19,800 m{sup 3} of LLRW-impacted soil that originated from the construction of a new water treatment plant; two mounds located at a licensed storage facility containing LLRW obtained from residential clean-up activities (11,000 m{sup 3}); and a small pad adjacent to the municipal sewage treatment plant containing 2200 m{sup 3} of LLRW-containing sludge. With the construction of a new long-term waste management facility (LTWMF) that has been designed to house all of the LLRW identified within Port Hope, the three sites were early candidates for remediation. The clean-up of the three temporary storage sites was a significant milestone for the Port Hope Area Initiative. After a decade of planning and consultation, this work represents the first sites in the municipality to be remediated with the waste being safety removed and transferred to the newly constructed LTWMF. This paper discusses the challenges associated with the clean-up activities for these three sites and the strategies employed to address those challenges. These included weather-related challenges, owing to the seasons over which the work was conducted as well as those associated with working within a closely-knit community. Canadian Nuclear Laboratories (CNL), working on behalf of the federal government, has worked diligently to develop a positive and trusting relationship with the community. Consequently, the successful execution of this project needed to be sensitive to, and respectful of the needs of the community. In addition to the usual Health, Safety and Environment training, project staff received community awareness training that spoke to the history of this community-based initiative and the expected behavior when working within the community. Transportation routes were defined based on safety and the need to minimize disruption to local traffic while haul-times where scheduled around school bus hours to enhance public safety. The successful completion of this first of many remediation projects to be completed under the Port Hope Area Initiative reflected years of careful planning. Nevertheless, there were a number of 'lessons learned' that have been applied on other ongoing projects be completed under the Port Hope Area Initiative. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Optimal Traffic Signal Control Using Priority Metric Based on Real-Time Measured Traffic Information

Optimizing traffic control systems at traffic intersections can reduce network-wide fuel consumption as well as improve traffic flow. While traffic signals have conventionally been controlled based on predetermined schedules, various adaptive control systems have been developed recently using advanced sensors such as cameras, radars, and LiDARs. By utilizing rich traffic information enabled by the advanced sensors, more efficient or optimal traffic signal control is possible in response to varying traffic conditions. This paper proposes an optimal traffic signal control method to minimize network-wide fuel consumption utilizing real-time traffic information provided by advanced sensors. This new method employs a priority metric calculated by a weighted sum of various factors, including the total number of vehicles, total vehicle speed, vehicle waiting time, and road preference. Genetic Algorithm (GA) is used as a global optimization method to determine the optimal weights in the priority metric. In order to evaluate the effectiveness of the proposed method, a traffic simulation model is developed in a high-fidelity traffic simulation environment called SUMO, based on a real-world traffic network. The traffic flow within this model is simulated using actual measured traffic data from the traffic network, enabling a comprehensive assessment of the novel optimal traffic signal control method in realistic conditions. The simulation results show that the proposed priority metric-based real-time traffic signal control algorithm can significantly reduce network-wide fuel consumption compared to the conventional fixed-time control and coordinated actuated control methods that are currently used in the modeled network. Additionally, incorporating truck priority in the priority metric leads to further improvements in fuel consumption reduction.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Simulation of 24,000 Electron Dynamics: Real-Time Time-Dependent Density Functional Theory (TDDFT) with the Real-Space Multigrids (RMG)

Here, we present the theory, implementation, and benchmarking of a real-time time-dependent density functional theory (RT-TDDFT) module within the RMG code, designed to simulate the electronic response of molecular systems to external perturbations. Our method offers insights into nonequilibrium dynamics and excited states across a diverse range of systems, from small organic molecules to large metallic nanoparticles. Benchmarking results demonstrate excellent agreement with established TDDFT implementations and showcase the superior stability of our time integration algorithm, enabling long-term simulations with minimal energy drift. The scalability and efficiency of RMG on massively parallel architectures allow for simulations of complex systems, such as plasmonic nanoparticles with thousands of atoms. Future extensions, including nuclear and spin dynamics, will broaden the applicability of this RT-TDDFT implementation, providing a powerful toolset for studies of photoactive materials, nanoscale devices, and other systems where real-time electronic dynamics is essential.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1990

The whole earth telescope - A new astronomical instrument

A new multimirror ground-based telescope for time-series photometry of rapid variable stars, designed to minimize or eliminate gaps in the brightness record caused by the rotation of the earth, is described. A sequence of existing telescopes distributed in longitude, coordinated from a single control center, is used to measure designated target stars so long as they are in darkness. Data are returned by electronic mail to the control center, where they are analyzed in real time. This instrument is the first to provide data of continuity and quality that permit true high-resolution power spectroscopy of pulsating white dwarf stars.

Nather, R. E.↗
NASA NTRS2003

Star Identification Using a Triplet Algorithm

The stars observed by onboard star trackers must be identified in order for the star tracker information to be used for attitude determination. Star identification associates the observed stars in the body frame with catalog stars, the positions of which in an inertial frame are well known. If the attitude is approximately known (from less accurate sensors) identification is relatively simple, but if there is no prior attitude knowledge (the Lost in Space problem) star identification is quite difficult. A new, reliable, and accurate star identification algorithm has been developed for use in a batch, ground-based attitude determination system. The identification algorithm uses input from one or more star trackers, each of which can observe three or more stars simultaneously. If observations are available at different times, rate data is used to relate them. The algorithm includes the following steps that are automatically performed: 1) Observations are examined to determine the optimal set of simultaneous star observations in a single tracker. 2) The selected optimal observations are identified using a triplet match. 3) The identified stars in the selected tracker at the selected time are used to compute an attitude at that time. 4) The rate data is refined by determination of biases that minimize the dispersion of repeated observations of the same stars. 5) The refined rate data is used to propagate the attitude to the times of each star observation. 6) The attitude at each time is used to associate all stars observed at that time, in each tracker, with catalog stars. The overall algorithm is very dependable at producing accurate star identification with no initial attitude input.

Hashmall, Joseph A.↗
NASA NTRS2005

Human Factors Assessment of Respiratory Support Pack (RSP) Cue Card

The Respiratory Support Pack (RSP) is a medical pack onboard the International Space Station (ISS) that contains much of the necessary equipment for providing aid to a conscious or unconscious crewmember in respiratory distress. Inside the RSP lid pocket is a 5.5 by 11 inch paper cue card, which is used by a Crew Medical Officer as the procedure to set up the equipment and deliver oxygen to a crewmember. In training, crewmembers expressed concerns about the readability and usability of the cue card; consequently, updating the cue card was prioritized as an activity to be completed prior to Space Shuttle return-to-flight. The Usability Testing and Analysis Facility at the Johnson Space Center evaluated the current layout of the cue card, and proposed several new cue card designs based on human factors principals. A series of three studies were performed in order to experimentally compare performance with each of the cue card designs. Nonmedically trained personnel used either a redesigned RSP cue card, or the original card to simulate resuscitation (using a mannequin along with the hardware). Time to completion, errors and subjective ratings were recorded. The addition of pictures, colors, borders, and simplification of the flow of information (making minimal changes to the actual procedure content) elicited great benefits during testing. Time to complete RSP procedures was reduced by as much as three minutes with the final cue card design. Detailed results from these studies, as well as general guidelines for cue card design will be discussed.

Whitmore, Mihriban↗
NASA NTRS1992

Improvement of observer/Kalman filter identification (OKID) by residual whitening

This paper presents a time-domain method to identify a state space model of a linear system and its corresponding observer/Kalman filter from a given set of general input-output data. The identified filter has the properties that its residual is minimized in the least squares sense, orthogonal to the time-shifted versions of itself, and to the given input-output data sequence. The connection between the state space model and a particular auto-regressive moving average description of a linear system is made in terms of the Kalman filter and a deadbeat gain matrix. The procedure first identifies the Markov parameters of an observer system, from which a state space model of the system and the filter gain are computed. The developed procedure is shown to improve results obtained by an existing observer/Kalman filter identification method, which is based on an auto-regressive model without the moving average terms. Numerical and experimental results are presented to illustrate the proposed method.

Phan, Minh↗
DOE OSTI2022

Molybdenum Carbide Electrocatalyst In Situ Embedded in Porous Nitrogen–Rich Carbon Nanotubes Promotes Rapid Kinetics in Sodium–Metal–Sulfur Batteries

This work is the first report of a molybdenum carbide-based electrocatalyst for sulfur-based sodium metal batteries (SMBs/NMBs). MoC/Mo 2 C is in-situ grown on nitrogen-doped carbon nanotubes in parallel with formation of extensive nanoporosity. Sulfur impregnation (50 wt% S) results in unique triphasic architecture termed MoC/Mo 2 C@PCNT-S. Quasi-solid-state phase transformation to Na 2 S is promoted in carbonate electrolyte, with in-situ time-resolved Raman, XPS and optical analysis demonstrating minimal soluble polysulfides. MoC/Mo 2 C@PCNT-S cathodes delivered among the most promising rate performance characteristics in literature, achieving 987 mAh g -1 at 1 Ag -1 , 818 mAh g -1 at 3 A g -1 , and 621 mAh g -1 at 5 A g -1 . The cells deliver superior cycling stability, retaining 650 mAh g -1 after 1000 cycles at 1.5 Ag -1 , corresponding to 0.028% capacity decay per cycle. High mass loading cathodes (64 wt% S, 12.7 mg cm -2 ) also show cycling stability, with anode degradation due to deep plating/stripping driving capacity decay. Density functional theory (DFT) demonstrates that formation energy of Na 2 S x (1 ≤ x ≤ 4) on surface of MoC/Mo 2 C is significantly lowered compared to analogous redox in liquid. Strong binding of Na 2 S x (1 ≤ x ≤ 4) on MoC/Mo 2 C surfaces results from charge transfer between the sulfur and Mo sites on carbides' surface.

25 ENERGY STORAGE↗
DOE OSTI2023

Precision cosmological constraints on atomic dark matter

Abstract Atomic dark matter is a simple but highly theoretically motivated possibility for an interacting dark sector that could constitute some or all of dark matter. We perform a comprehensive study of precision cosmological observables on minimal atomic dark matter, exploring for the first time the full parameter space of dark QED coupling and dark electron and proton masses (α D ,$$ {m}_{e_D} $$ m e D ,$$ {m}_{p_D} $$ m p D ) as well as the two cosmological parameters of aDM mass fractionf D and temperature ratioξat time of SM recombination. We also show how aDM can accommodate the (H 0 , S 8 ) tension from late-time measurements, leading to a better fit than ΛCDM or ΛCDM + dark radiation. Furthermore, including late-time measurements leads to closed contours of preferredξand dark hydrogen binding energy. The dark proton mass is seemingly unconstrained. Our results serve as an important new jumping-off point for future precision studies of atomic dark matter at non-linear and smaller scales.

Physics↗
DOE OSTI2021

A learning-augmented approach for AC optimal power flow

Because of the high nonlinearity of AC optimal power flow (OPF), numerous efforts have been made in recent decades to find efficient methods. Machine learning (ML) has proven to significantly reduce the computational costs in many real-world problems. Thus, this paper develops a learning-augmented method for solving AC OPF, which integrates both power network equations and ML to yield near-optimal solutions. More specifically, ML models are developed to first predict bus voltage magnitudes and angles. Then, physics-based network equations are employed to calculate the power injection at different buses. Three ML algorithms, i.e., random forest, multi-target decision tree, and extreme learning machine, are explored and compared. To evaluate the efficiency of the proposed learning-augmented AC OPF solver, the MATPOWER Interior Point Solver is adopted as a baseline. Case studies on both 500-bus and 4918-bus test networks show that the proposed learning-augmented method has reduced the computational time by 15–100 times depending on the network size with a minimal loss in optimality.

42 ENGINEERING↗