Search NASA⌕ Search

SEARCH · Search NASA

Results for “timing error evaluation”

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 199 records · Page 11

Exploring the feasibility of lossy compression for PDE simulations

Checkpoint restart plays an important role in high-performance computing (HPC) applications, allowing simulation runtime to extend beyond a single job allocation and facilitating recovery from hardware failure. Yet, as machines grow in size and in complexity, traditional approaches to checkpoint restart are becoming prohibitive. Current methods store a subset of the application’s state and exploit the memory hierarchy in the machine. However, as the energy cost of data movement continues to dominate, further reductions in checkpoint size are needed. Lossy compression, which can significantly reduce checkpoint sizes, offers a potential to reduce computational cost in checkpoint restart. This article investigates the use of numerical properties of partial differential equation (PDE) simulations, such as bounds on the truncation error, to evaluate the feasibility of using lossy compression in checkpointing PDE simulations. Restart from a checkpoint with lossy compression is considered for a fail-stop error in two time-dependent HPC application codes: PlasComCM and Nek5000. Results show that error in application variables due to a restart from a lossy compressed checkpoint can be masked by the numerical error in the discretization, leading to increased efficiency in checkpoint restart without influencing overall accuracy in the simulation.

97 MATHEMATICS AND COMPUTING↗

Informative Path Planning for Mapping Radiation

This project involves making measurements of contaminated areas using portable radiation detectors and small robots. Tasks involve operating detectors and small robots, combining data acquisition for the two systems, and automating the systems. The end result is a radiation map of contamination areas. Localization of radioactive sources and mapping of contamination distribution is essential when responding to emergencies, or when dealing with cleanup efforts. Radiation maps are used for situational awareness and for establishing a safe perimeter. However, it may be hazardous or impossible for humans to safely enter the site and survey the area. Informative Path Planning (IPP) is used to design a path for a robotic sensor platform to gather the most information about the radiation distribution while operating under the set of constraints given by the dynamics of the robot and other requirements such as minimizing the overall mission time. The key challenge for IPP is the tight coupling in multiple layers of decisions: Selection of locations to visit; Allocation of sensors to those locations; Processing of information gathered. Given a robot equipped with a basic gamma detector and Lidar sensor, how can we efficiently explore an unknown environment in such a way that we can satisfy the robot's constraints while simultaneously maximizing the accuracy of the map and minimizing the total runtime? This work presents a systematic procedure for IPP and environmental mapping that: Selects the best locations at which to sample; Finds the best path for robots; Estimates the measurement value at unknown locations using a Gaussian Process regression framework. Given a set of points where radiation measurements were taken, we are utilizing a Gaussian Process Regression with a Matern kernel to reconstruct the shape of the underlying ground truth. Mapping is done via the Robot Operating System's OpenSlam Gmapping package, which creates a 2D occupancy grid map. Simulated trials were run with a radiation source placed at random locations, and allowing the robot to select and move towards 20 samples at separate locations, as well as sampling along the path while moving. The simulated sensor model assumed an efficiency of 0.3, collection time of 1 second. Various weighting schemes were tested and compared. Quantitative evaluations often favored exploitation-heavy weighting schemes where μ was emphasized, with the Root Mean Squared Error (RMSE) quickly tending towards 2, whereas qualitative comparisons would favor exploration-biased schemes with greater weight on σ. The difference comes from operators often favoring knowing the general location of a source, rather than the exact properties of a source. Weighting of the path-length π often reduced the quality of the regression as less exploration occurred, however this may be deemed a worthwhile trade-off under certain circumstances, such as with sensitive robots. Successfully developed a methodology for informative path-planning for a robot to efficiently gather information and create a map of radiation. In the future, we would like to focus on: Hardware trials with integration of the robot platform and the IPP software; More refined sensor and environmental modeling; Multiple robot platforms.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Time delay analysis of the lensed quasar SDSS J1001+5027

We modify the algorithm we proposed in Aghamousa and Shafieloo for the time delay estimation of strongly lensed systems incorporating the weighted cross-correlation and weighted summation of correlation coefficients. We show the high performance of this algorithm by applying it to Time Delay Challenge (TDC1) simulated data. We apply then our proposed method to the light curves of the lensed quasar SDSS J1001+5027 since this system has been well studied by other groups, to compare our results with their findings. In this work we propose a new estimator, the “mirror” estimator, along with a list of criteria for reliability testing of the estimation. Our mirror estimator results are −117.1{sub −3.7}{sup +7.1} and −117.1{sub −8.8}{sup +7.2} using simple Monte Carlo simulations and simulated light curves provided by Rathna Kumar et al., respectively. Although the TDC1 simulations do not reflect the properties of the SDSS J1001+5027 light curves, using these simulations results in a smaller uncertainty, which shows that the higher quality observations can lead to a substantially more precise time delay estimation. Our time delay estimation is in agreement with the findings of the other groups for this strongly lensed system, and the difference in the size of the error bars reflects the importance of appropriate light curve simulations.

79 ASTRONOMY AND ASTROPHYSICS↗

Wind Energy Management System EMS Integration Project: Incorporating Wind Generation and Load Forecast Uncertainties into Power Grid Operations

The power system balancing process, which includes the scheduling, real time dispatch (load following) and regulation processes, is traditionally based on deterministic models. Since the conventional generation needs time to be committed and dispatched to a desired megawatt level, the scheduling and load following processes use load and wind and solar power production forecasts to achieve future balance between the conventional generation and energy storage on the one side, and system load, intermittent resources (such as wind and solar generation), and scheduled interchange on the other side. Although in real life the forecasting procedures imply some uncertainty around the load and wind/solar forecasts (caused by forecast errors), only their mean values are actually used in the generation dispatch and commitment procedures. Since the actual load and intermittent generation can deviate from their forecasts, it becomes increasingly unclear (especially, with the increasing penetration of renewable resources) whether the system would be actually able to meet the conventional generation requirements within the look-ahead horizon, what the additional balancing efforts would be needed as we get closer to the real time, and what additional costs would be incurred by those needs. To improve the system control performance characteristics, maintain system reliability, and minimize expenses related to the system balancing functions, it becomes necessary to incorporate the predicted uncertainty ranges into the scheduling, load following, and, in some extent, into the regulation processes. It is also important to address the uncertainty problem comprehensively by including all sources of uncertainty (load, intermittent generation, generators’ forced outages, etc.) into consideration. All aspects of uncertainty such as the imbalance size (which is the same as capacity needed to mitigate the imbalance) and generation ramping requirement must be taken into account. The latter unique features make this work a significant step forward toward the objective of incorporating of wind, solar, load, and other uncertainties into power system operations. Currently, uncertainties associated with wind and load forecasts, as well as uncertainties associated with random generator outages and unexpected disconnection of supply lines, are not taken into account in power grid operation. Thus, operators have little means to weigh the likelihood and magnitude of upcoming events of power imbalance. In this project, funded by the U.S. Department of Energy (DOE), a framework has been developed for incorporating uncertainties associated with wind and load forecast errors, unpredicted ramps, and forced generation disconnections into the energy management system (EMS) as well as generation dispatch and commitment applications. A new approach to evaluate the uncertainty ranges for the required generation performance envelope including balancing capacity, ramping capability, and ramp duration has been proposed. The approach includes three stages: forecast and actual data acquisition, statistical analysis of retrospective information, and prediction of future grid balancing requirements for specified time horizons and confidence levels. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on a histogram analysis, incorporating all sources of uncertainties of both continuous (wind and load forecast errors) and discrete (forced generator outages and start-up failures) nature. A new method called the “flying brick” technique has been developed to evaluate the look-ahead required generation performance envelope for the worst case scenario within a user-specified confidence level. A self-validation algorithm has been developed to validate the accuracy of the confidence intervals.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Dose–volume histogram evaluation scheme for beam orientations in intensity-modulated radiation therapy

Beam orientations in intensity-modulated radiation therapy (IMRT) is an important, but difficult NP-hard optimization problem. A considerable part of this difficulty is due to the essential prerequisite of defining, appropriately, counter-intuitive criteria for a mathematical plan evaluation that coincides with the clinical judgment of the considered plan. Moreover, the quality of beam directions depends heavily on their intensities. Usually a stochastic selector is utilized for optimizing beam orientations, and the intensities are thus calculated many thousands of times, each time for a different selection of beam directions, resulting in excessive time complexity. Therefore, selecting an appropriate set of beam directions in IMRT is still a time-consuming manual trial-and-error search procedure that depends on intuition and empirical knowledge. To overcome these difficulties, this work utilizes the concept of dose–volume histogram (DVH), which is one of the main recognized quantitative measurement tools used for plan judgment, and presents a DVH evaluation scheme that parallelizes plan evaluation with clinical plan judgment. This scheme is then utilized to optimize the intensities of each individual beam, enabling it to be represented by its DVHs, produced for the different irradiated volumes. Finally, an evolutionary algorithm is employed to search for the best combination of those DVHs reflecting the clinical optimal. The presented methods have been applied to three real clinical examples. In comparison to the standard equally spaced beam plans, improvements were reported in all three cases. In comparison with the greedy algorithm, improvements were reported in those examples requiring more than five beam directions.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Lab-Scale Cable-Driven Parallel Robot Prototype for Automated Prefabricated Component Manipulation

This paper presents the design and evaluation of a lab-scale cable-driven parallel robot (CDPR) developed as a flexible platform for automated installation of prefabricated components onto exterior building envelopes. Traditional manual installation methods for prefabricated components, which depend on scaffolding, cranes, cherry pickers, and verbal coordination, are not only labor-intensive and error-prone but also face significant limitations in dense urban environments due to site access constraints. To address these challenges, we developed a lab-scale CDPR platform capable of autonomously transporting building envelope components from a designated pickup zone to their target installation location, minimizing the need for human intervention. This study describes the system’s mechanical design, actuation architecture, real-time feedback system, and control strategy of the CDPR, and evaluates its performance in a laboratory environment. The robot’s actuation system uses torque control for end-effector manipulation. The robot’s real-time pose feedback comes from a construction-grade total station and a wireless inertial measurement unit (IMU), which together support precise end-effector control. Experimental results demonstrate the successful integration of the hardware, sensing, state estimation, and control subsystems. Preliminary tests showed that our lab-scale prototype can position the end effector with an error of less than 3 mm, which is a level of precision not previously achieved by existing CDPRs in construction applications. The key findings are twofold: (1) torque-only control is necessary but not sufficient for minimizing final pose error, and (2) incorporating real-time pose feedback can achieve the desired placement accuracy.

Liu, Yifang [Oak Ridge National Laboratory (ORNL),↗

High‐Frequency Intermittency in Observed and Model‐Simulated Precipitation

Abstract A newly reprocessed, bias‐corrected version of hourly satellite observations that provides global coverage of precipitation at high space‐time resolution is evaluated and compared with climate model simulations. Irregular subdaily fluctuations are the dominant component around the world, greater than variance of daily mean precipitation, and much greater than variance associated with the mean diurnal cycle of precipitation. Irregular subdaily fluctuations of precipitation are severely underestimated by models, even after taking into account the observational “error bars” implied by different space‐time resolutions. Variance of daily mean precipitation is less severely underestimated. Although mean diurnal cycle amplitudes vary among the models, this component is but a small part of total precipitation variance. Therefore, the total precipitation variance is significantly underestimated by models in general. Further exploration of model‐data discrepancies in precipitation at high‐time frequency may lead to new and useful climate model diagnostics.

54 ENVIRONMENTAL SCIENCES↗

Assessing the Effects of Data Compression in Simulations Using Physically Motivated Metrics

This paper examines whether lossy compression can be used effectively in physics simulations as a possible strategy to combat the expected data-movement bottleneck in future high performance computing architectures. We show that, for the codes and simulations we tested, compression levels of 3–5X can be applied without causing significant changes to important physical quantities. Rather than applying signal processing error metrics, we utilize physics-based metrics appropriate for each code to assess the impact of compression. We evaluate three different simulation codes: a Lagrangian shock-hydrodynamics code, an Eulerian higher-order hydrodynamics turbulence modeling code, and an Eulerian coupled laser-plasma interaction code. We compress relevant quantities after each time-step to approximate the effects of tightly coupled compression and study the compression rates to estimate memory and disk-bandwidth reduction. We find that the error characteristics of compression algorithms must be carefully considered in the context of the underlying physics being modeled.

Laney, Daniel↗

Influence of sun zenith angle on canopy clumping and the resulting impacts on photosynthesis

Addressing the impact of vegetation architecture on shortwave radiation transfer in land surface models is important for accurate weather forecasting, carbon budget estimates, and climate predictions. This paper investigates to what extent it is possible to retrieve structural parameters of two different parameterization schemes from direct transmittance derived from digital hemispherical photography and 3D radiative transfer modeling for two study sites with different vegetation canopy architectures. Neglecting the representation of 3D canopy structure in radiative transfer schemes leads to significant errors in shortwave radiation partitioning (up to 3.5 times more direct transmittance in the 3D model). Structural parameters, referred to as whole canopy ‘clumping indices’, were obtained in order to evaluate the impact of angular variation in clumping on shortwave radiation transfer. Impacts on photosynthesis were evaluated at site level with the UKESM land surface model, JULES. A comparison between flux tower derived and modeled photosynthesis indicates that considering zenith angular variations of structural parameters in the radiative transfer scheme of the UKESM land surface model significantly improves photosynthesis prediction in light limited ecosystems (from RMSE = 2.91 μmol CO 2 .m -2 .s -1 to RMSE = 1.51 μmol CO 2 .m -2 .s -1 , 48% smaller), typically with enhanced photosynthesis from bottom layers.

54 ENVIRONMENTAL SCIENCES↗

Performance Evaluation of an Offshore Wave Measurement Buoy in Monochromatic Waves

The accurate measurement of waves underpins marine energy resource characterization, device design, and project development. Datawell wave buoys are widely deployed and have long served as a trusted standard for wave measurements. We quantify the measurement performance, including wave elevation and energy flux estimation, of a Datawell DWR-MkIII buoy using prescribed monochromatic heave motions on a large-amplitude six-degree-of-freedom motion platform at the National Laboratory of the Rockies, assuming the buoy behaves as an ideal wave follower. Commanded motions were validated with an optical motion tracking system while buoy elevation and raw acceleration were recorded. Wave elevations were propagated to wave energy flux estimation using four methods, including one frequency-domain method and three time-domain methods. The Bayesian optimization was applied for design of experiments, and records from three test sites were also applied and evaluated in the present study. Results show two error regions within the nominal period range of 1.6 s to 30 s. For wave periods between 5 s and 25 s, the buoy provides accurate wave height measurements. For short periods less than 5 s, the 1.28 Hz sampling frequency induces sub-Nyquist artifacts that bias elevation and can drive maximum energy flux estimation errors above 100%. For long periods exceeding 25 s, the buoy reported elevation is underpredicted with error depending on period but relatively independent of wave height, with maximum wave height and wave energy flux errors reaching 64% and 87%, respectively. Furthermore, analysis of three field-derived cases shows that frequency-domain estimates at 1.28 Hz agree within 2% of the corresponding 100 Hz estimates, while larger method-dependent differences are observed for the Hilbert method.

16 TIDAL AND WAVE POWER↗

Monte Carlo MP2-F12 for Noncovalent Interactions: The C 60 Dimer

A scalable stochastic algorithm is presented that can evaluate explicitly correlated (F12) second-order many-body perturbation (MP2) energies of weak, noncovalent, intermolecular interactions. It first transforms the formulas of the MP2 and F12 energy differences into a short sum of high-dimensional integrals of Green’s functions in real space and imaginary time. Furthermore, these integrals are then evaluated by the Monte Carlo method augmented by parallel execution, redundant-walker convergence acceleration, direct-sampling autocorrelation elimination, and control-variate error reduction. By sharing electron-pair walkers across the supermolecule and its subsystems spanned by the joint basis set, the statistical uncertainty is reduced by one to 2 orders of magnitude in the MP2 binding energy corrected for the basis-set incompleteness and superposition errors. The method predicts the MP2-F12/aug-cc-pVDZ binding energy of 19.1 ± 4.0 kcal mol –1 for the C 60 dimer at the center distance of 9.748 Å.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Beam-Based Diagnostics of Electric Guide Fields and Lattice Parameters for Run-1 of the Muon g-2 Storage Ring at Fermilab

A portion of the Muon g-2 Storage Ring electric system, which provides vertical beam focusing, exhibited an unexpected time dependence that produced a characteristic evolution of the stored beam during Run-1 of the Muon g-2 Experiment at Fermilab (E989). A method to reconstruct the Run-1 electric guide fields has been developed, which is based on a numerical model of the muon storage ring and optimization algorithms supported by COSY INFINITY. This method takes beam profile measurements from the Muon g-2 straw tracking detectors as input, and it produces a full reconstruction of the time-dependent fields. The fields can then be used for the reproduction of detailed beam tracking simulations and the calculation of ring lattice parameters for acceptance studies and systematic error evaluations.

43 PARTICLE ACCELERATORS↗

Highly Accurate Method for Real-Time Active Power Reserve Estimation for Utility-Scale Photovoltaic Power Plants

This paper applies a robust technique for determining the available power from a curtailed utility-scale photovoltaic (PV) power plant. The proposed technique does not require deploying any additional equipment or sensors and is based only on the addition of new control logic to the existing power plant controller. Also, the proposed method is universally applicable to PV plants with any type of smart inverters and PV modules. Accurate determination of available power is important for using curtailed PV generation as a resource for various types of active power controls, such as spinning reserves and primary and secondary frequency control. For PV plants to be able to maintain the desired regulation range, the plant controller must be able to estimate the available aggregate peak power that all the plant's inverters can produce at any point in time and ensure that the control error stays within the tolerance band at all times. In this paper, we explore a highly accurate control method that uses dedicated inverters within the plant as reference units and evaluates the available aggregate peak power for the whole plant under different cloud variability conditions.

14 SOLAR ENERGY↗

High-Resolution Regional Wave Hindcast for Hawaii

This report summarizes modeling efforts for hindcasting of wave climate within the exclusive economic zone (EEZ) around the state of Hawaii. Specifically, the report provides detailed description of model mesh development, sensitivity analysis of the configuration of model parameters, data used for model forcing and validation, model skill assessment, and model outputs for resource characterization. The unstructured, nested-grid modeling approach incorporates a regional high-resolution SWAN (Simulating WAves Nearshore) model within the global-regional WAVEWATCH III® (WW3) wave model. The models were configured to comply with the International Electrotechnical Commission (IEC) Technical Standards for wave energy resource characterization. The SWAN model domain covers the entire EEZ with a spatial resolution of approximately 300 m in the nearshore region. Two levels of WW3 nested grids, from 0.5 arc-degree at global to 7.5 arc-minute at regional scale, were used to provide boundary conditions that drive the high-resolution nearshore SWAN model. The WW3 and SWAN models were forced by 0.5 arc-degree Climate Forecast System Reanalysis wind and 5 km regional Weather Research and Forecasting wind, respectively. Wave resource and bulk wave parameters were simulated for a 32-year period from 1979 to 2010, and were subsequently validated using wave buoy data within the model domain. Model performance was evaluated using a set of error statistics. Overall, the model shows good skills in reproducing the wave climate in the Hawaii EEZ in both spatial and temporal domains. Comparisons of time series and scatter plots for the six IEC resource parameters and the associated error statistics tables, and horizontal two-dimensional plots of annually averaged and monthly averaged IEC parameters are provided.

16 TIDAL AND WAVE POWER↗

Evaluating pulse-shaping capabilities of next-generation pulsed power architectures

This project evaluated the pulse shaping capabilities of next-generation pulsed power (NGPP) architectures. NGPP architectures share several common attributes including multiple independent pulse-generation lines, a radial water-insulated impedance transformer, and a central vacuum insulated load region. A multi-module circuit model was developed, incorporating independent pulse-generation lines and a 2-D transmission line mesh of the radial impedance transformer to assess the effects of azimuthal asymmetry in pulse-shaped experiments. Circuit model simulations demonstrated that NGPP architectures are able to produce the the desired current pulse shapes for exemplar NGPP experiments. Additionally, the project explored automated methods for experiment design, including derivative -ree optimization and machine learning. Pulse-shaped experiments require designers to determine machine parameters that reliably produce the desired current pulse at the load, a process that typically relies on expert knowledge and iterative adjustments using the Z circuit model. Given the increased complexity of NGPP systems, this manual approach may be impractical. While the evaluated methods do not eliminate the need for manual iteration, they can reduce the time required for experiment design. Derivative-free optimization automates much of the trial-and-error process, providing a close starting point for manual adjustments or making small modifications to near-final designs. Meanwhile, deep neural network methods can generate a good qualitative match to the desired current pulse in under one second without requiring circuit model simulations.

42 ENGINEERING↗

Highly Accurate Method for Real-Time Active Power Reserve Estimation for Utility-Scale PV Power Plants: Preprint

This paper applies a robust technique for determining the available power reserve from a curtailed utility-scale photovoltaic (PV) power plant. The proposed technique does not require deploying any additional equipment or sensors and is based only on the addition of new control logic to the existing power plant controller. Also, the proposed method is universally applicable to PV plants with any type of smart inverters and PV modules. Accurate determination of available power is important for using curtailed PV generation as a resource for various types of active power controls, such as spinning reserves and primary and secondary frequency control. For PV plants to be able to maintain the desired regulation range, the plant controller must be able to estimate the available aggregate peak power that all the plant's inverters can produce at any point in time and ensure that the control error stays within the tolerance band at all times. In this paper, we explore a highly accurate control method that uses dedicated inverters within the plant as reference units and evaluates the available aggregate peak power for the whole plant under different cloud variability conditions.

14 SOLAR ENERGY↗

SU-E-J-123: Targeting Accuracy of Image-Guided Radiosurgery for Intracranial Lesions

Purpose: To evaluate the setup accuracies of image-guided intracranial radiosurgery across several different linear accelerator platforms. Methods: A CT scan with a slice thickness of 1.0 mm was acquired of a Rando head phantom (The Phantom Laboratory) in a U-frame mask (BrainLAB AG). The phantom had three embedded BBs, simulating a central, left, and anterior lesion. The phantom was setup with each BB placed at the radiation isocenter under image guidance. Four different setup procedures were investigated: (1) NTX-ExacTrac: 6 degree-of-freedom (6D) correction on a Novalis Tx (BrainLAB AG) with ExacTrac localization (BrainLAB AG); (2) NTX-CBCT: 4D correction on the Novalis Tx with cone-beam computed tomography (CBCT); (3) TrueBeam-CBCT: 4D correction on a TrueBeam (Varian) with CBCT; (4) Edge-CBCT: 6D correction on an Edge (Varian) with CBCT. The experiment was repeated 5 times with different initial setup error at each BB location on each platform, and the mean (μ) and one standard deviation (σ) of the residual error was compared.The congruence between radiation and imaging isocenters on each platform was evaluated by acquiring Winston Lutz (WL) images of a WL jig followed by imaging using ExacTrac or CBCT. The difference in coordinates of the jig relative to radiation and imaging isocenters was then recorded. Results: Averaged over all three BB locations, the residual vector setup errors (μ±σ) of the phantom in mm were 0.6±0.2, 1.0±0.5, 0.2±0.1, and 0.3±0.1 on NTX-ExacTrac, NTX-CBCT, TrueBeam-CBCT, and Edge-CBCT, with their ranges in mm being 0.4∼1.1, 0.4∼1.9, 0.1∼0.5, and 0.2∼0.6, respectively. And imaging isocenter was found stable relative to radiation isocenter, with the congruence to radiation isocenter in mm being 0.6±0.1, 0.7±0.1, 0.3±0.1, 0.2±0.1, respectively, on the four systems in the same order. Conclusion: Millimeter accuracy can be achieved with image-guided radiosurgery for intracranial lesions based on this set of experiments.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Transformer Neural Networks with Spatiotemporal Attention for Predictive Control and Optimization of Industrial Processes

In the context of real-time optimization and model predictive control of industrial systems, machine learning, and neural networks represent cutting-edge tools that hold promise for enhancing dynamic modeling. This work presents a novel transformer neural network architecture for real-time optimization and model predictive control. This network design includes a modified attention mechanism inspired by positional embedding attention from vision transformers and task-specific modifications to the input-output structure of the transformer’s decoder stack. Experiments were conducted using data from a 450 MW coal-fired power plant to evaluate this approach's effectiveness. The transformer neural network was compared with conventional recurrent models, including GRU and LSTM. The transformer exhibited a 6% increase in the R-squared (R2) value of predictions and an 83% reduction in mean squared error (MSE). Computation time was also reduced by 84% compared to conventional recurrent models.

Gallup, Ethan R.↗