Search NASA⌕ Search

SEARCH · Search NASA

Results for “prediction algorithms”

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 991 records · Page 55

Optimal Voltage Control in Low-Observable Unbalanced Distribution Systems

The increased integration of distributed energy resources (DERs) in distribution systems brings both advantages and technical challenges. High levels of DERs can often cause over/under voltage problems. Classical voltage control algorithms are based on full knowledge of voltage states across all nodes in the system. However, this may not be a practical assumption since many locations in distribution systems are unobservable. Therefore, this paper proposes a new model predictive control (MPC) based control algorithm that accounts for system unobservability to efficiently eliminate voltage violations with as low as 50% fraction of observable nodes. Additionally, an analytical voltage sensitivity framework is employed to quickly determine the change in voltage states due to PV injections. The effectiveness of the proposed method is validated via simulations on the unbalanced IEEE 37 node test system.

Abujubbeh, Mohammad↗

Application of Sequential Design of Experiments (SDoE) to Large Pilot-Scale Solvent-Based CO2 Capture Process at Technology Centre Mongstad (TCM)

The United States Department of Energy’s Carbon Capture Simulation for Industry Impact (CCSI2) program has developed a framework for sequential design of experiments (SDoE) that aims to maximize knowledge gained from budget- and schedule-limited pilot scale testing. SDoE was applied to the planning and execution of campaigns for testing CO2 capture systems at pilot-scale in order to optimally allocate resources available for the testing. In this methodology, a stochastic process model is developed by quantifying the parametric uncertainty in submodels of interest; for a solvent-based CO2 capture system, these may include physical properties and equipment performance submodels (e.g., mass transfer, interfacial area). This uncertainty is propagated through the full process model, over variable operating conditions, for estimating the resulting uncertainty in key model outputs (e.g., percentage of CO2 capture, solvent regeneration energy requirement). In developing a data collection plan, the predicted output uncertainty is incorporated into an algorithm that seeks simultaneously to select process operating conditions for which the predicted uncertainty is relatively high and to ensure that the entire space of operation is well represented. This test plan is then used to guide operation of the pilot plant at varying steady-state conditions, with resulting process data incorporated into the existing model using Bayesian inference to refine parameter distributions. The updated stochastic model, with reduced parametric uncertainty from data collected, is then used to guide additional data collection, thus the sequential nature of the experimental design. The SDoE process was implemented at the pilot test unit (12 MWe in scale) at Norway’s Technology Centre Mongstad (TCM) in a summer 2018 test campaign with aqueous monoethanolamine (MEA). During the test campaign, the varied operating conditions included the flowrates of circulated solvent, flue gas, and reboiler steam and the CO2 concentration in the flue gas. The process data were used to update probability distributions of mass transfer and interfacial area parameters of a stochastic process model developed by the CCSI2 team. Two iterations of the SDoE process were executed, resulting in the uncertainty in model predicted CO2 capture percentage decreasing by an average of 58.0 ± 4.7% over the full input space of interest. This work demonstrates the potential of the SDoE process for model refinement through reduction in process model parametric uncertainty, and ultimately risk in scale-up, in CO2 capture technology performance.

carbon capture↗

Resource Selection Using Execution and Queue Wait Time Predictions

Computational grids provide users with many possible places to execute their applications. We wish to help users select where to run their applications by providing predictions of the execution times of applications on space shared parallel computers and predictions of when scheduling systems for such parallel computers will start applications. Our predictions are based on instance based learning techniques and simulations of scheduling algorithms. We find that our execution time prediction techniques have an average error of 37 percent of the execution times for trace data recorded from SGI Origins at NASA Ames Research Center and that this error is 67 percent lower than the error of user estimates. We also find that the error when predicting how long applications will wait in scheduling queues is 95 percent of mean queue wait times when using our execution time predictions and this is 57 percent lower than if we use user execution time estimates.

Warren, Smith↗

Resource Selection Using Execution and Queue Wait Time Predictions

Computational grids provide users with many possible places to execute their applications. We wish to help users select where to run their applications by providing predictions of the execution times of applications on space shared parallel computers and predictions of when scheduling systems for such parallel computers will start applications. Our predictions are based on instance based learning techniques and simulations of scheduling algorithms. We find that our execution time prediction techniques have an average error of 37 percent of the execution times for trace data recorded from SGI Origins at NASA Ames Research Center and that this error is 67 percent lower than the error of user estimates. We also find that the error when predicting how long applications will wait in scheduling queues is 95 percent of mean queue wait times when using our execution time predictions and this is 57 percent lower than if we use user execution time estimates.

Smith, Warren↗

Neural Generalized Predictive Control: A Newton-Raphson Implementation

An efficient implementation of Generalized Predictive Control using a multi-layer feedforward neural network as the plant's nonlinear model is presented. In using Newton-Raphson as the optimization algorithm, the number of iterations needed for convergence is significantly reduced from other techniques. The main cost of the Newton-Raphson algorithm is in the calculation of the Hessian, but even with this overhead the low iteration numbers make Newton-Raphson faster than other techniques and a viable algorithm for real-time control. This paper presents a detailed derivation of the Neural Generalized Predictive Control algorithm with Newton-Raphson as the minimization algorithm. Simulation results show convergence to a good solution within two iterations and timing data show that real-time control is possible. Comments about the algorithm's implementation are also included.

Soloway, Donald↗

3D printed cellular solid outperforms traditional stochastic foam in long-term mechanical response

3D printing of polymeric foams by direct-ink-write is a recent technological breakthrough that enables the creation of versatile compressible solids with programmable microstructure, customizable shapes, and tunable mechanical response including negative elastic modulus. However, in many applications the success of these 3D printed materials as a viable replacement for traditional stochastic foams critically depends on their mechanical performance and micro-architectural stability while deployed under long-term mechanical strain. To predict the long-term performance of the two types of foams we employed multi-year-long accelerated aging studies under compressive strain followed by a time-temperature-superposition analysis using a minimum-arc-length-based algorithm. The resulting master curves predict superior long-term performance of the 3D printed foam in terms of two different metrics, i.e., compression set and load retention. To gain deeper understanding, we imaged the microstructure of both foams using X-ray computed tomography, and performed finite-element analysis of the mechanical response within these microstructures. As a result, this indicates a wider stress variation in the stochastic foam with points of more extreme local stress as compared to the 3D printed material, which might explain the latter’s improved long-term stability and mechanical performance.

36 MATERIALS SCIENCE↗

A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

Ground-level ozone is a pollutant that is harmful to urban populations, particularly in developing countries where it is present in significant quantities. It greatly increases the risk of heart and lung diseases and harms agricultural crops. This study hypothesized that, as a secondary pollutant, ground-level ozone is amenable to 24 h forecasting based on measurements of weather conditions and primary pollutants such as nitrogen oxides and volatile organic compounds. We developed software to analyze hourly records of 12 air pollutants and 5 weather variables over the course of one year in Delhi, India. To determine the best predictive model, eight machine learning algorithms were tuned, trained, tested, and compared using cross-validation with hourly data for a full year. The algorithms, ranked by R2 values, were XGBoost (0.61), Random Forest (0.61), K-Nearest Neighbor Regression (0.55), Support Vector Regression (0.48), Decision Trees (0.43), AdaBoost (0.39), and linear regression (0.39). When trained by separate seasons across five years, the predictive capabilities of all models increased, with a maximum R 2 of 0.75 during winter. Bidirectional Long Short-Term Memory was the least accurate model for annual training, but had some of the best predictions for seasonal training. Out of five air quality index categories, the XGBoost model was able to predict the correct category 24 h in advance 90% of the time when trained with full-year data. Separated by season, winter is considerably more predictable (97.3%), followed by post-monsoon (92.8%), monsoon (90.3%), and summer (88.9%). These results show the importance of training machine learning methods with season-specific data sets and comparing a large number of methods for specific applications.

54 ENVIRONMENTAL SCIENCES↗

Community Resilience Through Rapid Restoration Leveraging Distributed Energy Resources (DERs) and Low-Cost Sensors

Equitable and automated bottoms-up power restoration following an extreme event will be demonstrated at a site in Puerto Rico. To do so, the team will develop enhanced grid situational awareness techniques integrating behind-the-meter (BTM) distributed energy resources (DER) discovery, impedance sweeping based outage boundary detection, and feasible restoration path identification algorithms. Resilience metric will be developed and incorporated along with situational awareness information in a distributed Model Predictive Control (MPC)-based restoration optimization algorithm to control and mobilize grid assets. These algorithms will be validated through power hardware-in-the-loop experiments and ultimately, a site demonstration to show that outage recovery time and total recovered load could be improved by >20% over the baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗

An Open-Source Tool for Automated Power Grid Stress Level Prediction at Balancing Authorities

The behavior of modern power systems becomes more stochastic and dynamic, due to the increased penetration of variable generation, demand response, new power market structure, extreme weather conditions, contingencies, and unexpected events. It is critically important to predict potential system operational issues so that grid planners and operators can take preventive actions to mitigate the impact, e.g., lack of operational reserves. In this paper, an innovative software tool is presented to assist power grid operators in a balancing authority (BA) to predict the grid stress level over the next operating day. It periodically collects necessary information from public domain such as weather forecasts, electricity demand, and automatically estimates the stress levels on a daily basis. Advanced Neural Network and regression tree algorithms are developed as the prediction engines to achieve this goal. The tool has been tested on a few key balancing authorities that successfully predicates the growing system peak load and increased stress levels under extreme heat waves in the United States of America.

Berscheid, Alan P.↗

Multi-sensor analysis techniques for SSME safety monitoring

Two algorithms were developed which utilized multi-sensor analysis techniques to complement the current Space Shuttle Main Engine (SSME) safety monitoring system. The first algorithm analyzed the accumulative error between actual and predicted values of the engine parameter set, while the second algorithm combined these error terms into a response pattern and correlated each pattern with a standard pattern. These algorithms were applied to twelve SSME anomalous test firings and were found to produce improved failure detection times in eight of those twelve compared to the current engine safety monitoring system. Of the eight detected anomalous test firings, the first algorithm detected all eight, while the second algorithm detected seven of the eight. No false alarms were indicated by either algorithm for twelve nominal test firings. An initial parametric study of these algorithms for optimized parameter selection is presented and algorithm robustness to sensor failure is demonstrated.

Maul, William A., III↗

GOOML: Geothermal Operational Optimization with Machine Learning

Geothermal Operational Optimization with Machine Learning (GOOML) is a project focused on maximizing increased availability and capacity from existing industrial-scale geothermal generation assets. The GOOML project will develop a suite of machine learning-based algorithms that analyze historical production datasets and provide predictive setpoints for geothermal field operations. Historical datasets from New Zealand and the US will provide the input to develop digital geothermal system twins which allow prediction of market conditions, maintenance operations and steamfield optimization. The algorithms will identify key parameters within fields and suggest setpoints for components of the system to maintain optimal generation. Set-points can be instructed to follow mass flow restrictions, generation maximization and optimal field/reservoir balance and give field operators a guide by which generation can be optimized. The datasets that will be used to develop GOOML are sourced from operating geothermal fields in New Zealand and the United States with varying degrees of complexity. This will ensure that most geothermal systems can utilize the GOOML tool to assist in optimizing operations. GOOML aims to achieve a step-change in geothermal operations by developing state-of-the-art machine learning algorithms, comprehensive data analytics, and a first-of-its-kind automated, intelligent geothermal system model.

algorithms↗

RECOVERY ACT: DYNAMIC ENERGY CONSUMPTION MANAGEMENT OF ROUTING TELECOM AND DATA CENTERS THROUGH REAL-TIME OPTIMAL CONTROL (RTOC): Final Scientific/Technical Report

This final scientific report documents the Industrial Technology Program (ITP) Stage 2 Concept Development effort on Data Center Energy Reduction and Management Through Real-Time Optimal Control (RTOC). Society is becoming increasingly dependent on information technology systems, driving exponential growth in demand for data center processing and an insatiable appetite for energy. David Raths noted, 'A 50,000-square-foot data center uses approximately 4 megawatts of power, or the equivalent of 57 barrels of oil a day1.' The problem has become so severe that in some cases, users are giving up raw performance for a better balance between performance and energy efficiency. Historically, power systems for data centers were crudely sized to meet maximum demand. Since many servers operate at 60%-90% of maximum power while only utilizing an average of 5% to 15% of their capability, there are huge inefficiencies in the consumption and delivery of power in these data centers. The goal of the 'Recovery Act: Decreasing Data Center Energy Use through Network and Infrastructure Control' is to develop a state of the art approach for autonomously and intelligently reducing and managing data center power through real-time optimal control. Advances in microelectronics and software are enabling the opportunity to realize significant data center power savings through the implementation of autonomous power management control algorithms. The first step to realizing these savings was addressed in this study through the successful creation of a flexible and scalable mathematical model (equation) for data center behavior and the formulation of an acceptable low technical risk market introduction strategy leveraging commercial hardware and software familiar to the data center market. Follow-on Stage 3 Concept Development efforts include predictive modeling and simulation of algorithm performance, prototype demonstrations with representative data center equipment to verify requisite performance and continued commercial partnering agreement formation to ensure uninterrupted development, and deployment of the real-time optimal control algorithm. As a software implementable technique for reducing power consumption, the RTOC has two very desirable traits supporting rapid prototyping and ultimately widespread dissemination. First, very little capital is required for implementation. No major infrastructure modifications are required and there is no need to purchase expensive capital equipment. Second, the RTOC can be rolled out incrementally. Therefore, the effectiveness can be proven without a large scale initial roll out. Through the use of the Impact Projections Model provided by the DOE, monetary savings in excess of $100M in 2020 and billions by 2040 are predicted. In terms of energy savings, the model predicts a primary energy displacement of 260 trillion BTUs (33 trillion kWh), or a 50% reduction in server power consumption. The model also predicts a corresponding reduction of pollutants such as SO2 and NOx in excess of 100,000 metric tonnes assuming the RTOC is fully deployed. While additional development and prototyping is required to validate these predictions, the relative low cost and ease of implementation compared to large capital projects makes it an ideal candidate for further investigation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Structures and magnetic properties of iron silicide from adaptive genetic algorithm and first-principles calculations

We performed a systematic search for low-energy structures of binary iron silicide over a wide range of compositions using the crystal structure prediction method based on adaptive genetic algorithm. 36 structures with formation energies within 50 meV/atom (11 of them are within 20 meV) above the convex hull formed by experimentally known stable structures are predicted. Magnetic properties of these low-energy structures are investigated. Some of these structures can be promising candidates for rare-earth-free permanent magnet.

36 MATERIALS SCIENCE↗

Adaptive DIT-Based Fringe Tracking and Prediction at IOTA

An automatic fringe tracking system has been developed and implemented at the Infrared Optical Telescope Array (IOTA). In testing during May 2002, the system successfully minimized the optical path differences (OPDs) for all three baselines at IOTA. Based on sliding window discrete Fourier transform (DFT) calculations that were optimized for computational efficiency and robustness to atmospheric disturbances, the algorithm has also been tested extensively on off-line data. Implemented in ANSI C on the 266 MHZ PowerPC processor running the VxWorks real-time operating system, the algorithm runs in approximately 2.0 milliseconds per scan (including all three interferograms), using the science camera and piezo scanners to measure and correct the OPDs. Preliminary analysis on an extension of this algorithm indicates a potential for predictive tracking, although at present, real-time implementation of this extension would require significantly more computational capacity.

Wilson, Edward↗

A Multiphysics Multiscale Simulation Platform for Damage, Environmental Degradation, and Life Prediction of CMCs in Extreme Environments

This project successfully developed a multiphysics, multiscale computational framework to enhance the design and development of CMCs, with a focus on modeling highly nonlinear, time-dependent damage mechanisms and material degradation under extreme conditions, such as those experienced in turbine service environments. The project made significant advances in improving our understanding of progressive damage, oxidative degradation, and time-dependent inelastic deformation in CMCs, with particular attention to the role of uncertainties in predictions. Key outcomes include the integration of advanced material characterization, uncertainty quantification, and multiphysics constitutive models to predict the behavior of CMCs over their service life. A novel multiscale methodology was employed, which integrated microscale constituent behaviors with structural-scale responses, enabling the manufacturing defects in the microstructure that are prone to damage nucleation. Through the development of DL algorithms, the project advanced the prediction of damage initiation and crack propagation, taking into account the defect morphology and statistical variations across multiple scales. The framework was rigorously validated using thermomechanical experiments, which tested CMCs under various mechanical loadings at elevated temperatures, further enhancing the model's predictive capability. Overall, the research outcomes have provided a more accurate, reliable method for predicting CMC component life, significantly advancing material design, and improving component reliability in extreme environments. This work has strong implications for the optimization of turbine components and other high-performance applications where CMCs are used.

03 NATURAL GAS↗

Integrating multimodal data through interpretable heterogeneous ensembles

Motivation: Integrating multimodal data represents an effective approach to predicting biomedical characteristics, such as protein functions and disease outcomes. However, existing data integration approaches do not sufficiently address the heterogeneous semantics of multimodal data. In particular, early and intermediate approaches that rely on a uniform integrated representation reinforce the consensus among the modalities but may lose exclusive local information. The alternative late integration approach that can address this challenge has not been systematically studied for biomedical problems. Results: We propose Ensemble Integration (EI) as a novel systematic implementation of the late integration approach. EI infers local predictive models from the individual data modalities using appropriate algorithms and uses heterogeneous ensemble algorithms to integrate these local models into a global predictive model. We also propose a novel interpretation method for EI models. We tested EI on the problems of predicting protein function from multimodal STRING data and mortality due to coronavirus disease 2019 (COVID-19) from multimodal data in electronic health records. We found that EI accomplished its goal of producing significantly more accurate predictions than each individual modality. It also performed better than several established early integration methods for each of these problems. The interpretation of a representative EI model for COVID-19 mortality prediction identified several disease-relevant features, such as laboratory test (blood urea nitrogen and calcium) and vital sign measurements (minimum oxygen saturation) and demographics (age). These results demonstrated the effectiveness of the EI framework for biomedical data integration and predictive modeling.

59 BASIC BIOLOGICAL SCIENCES↗

Glassoformer: A Query-Sparse Transformer for Post-Fault Power Grid Voltage Prediction

Here, we propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLasso-former shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.

24 POWER TRANSMISSION AND DISTRIBUTION↗