Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network performance forecasting”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Predictive Modeling and Diagnostic Monitoring of Extreme Science Workflows (Final Report)

This proposal addresses a critical issue of performance prediction identified in the report from the ASCR \Computational Modeling of Big Networks (COMBINE)" workshop: "end-to-end performance is not predictable due to a variety of factors. Even when some performance forecasts or predictions can be made, they often cannot explain the reasons why some predictions fail." We will develop new analytical models to predict the end-to-end performance of scientific workflows on DOE computing infrastructures, and use simulations and experimentation to validate and refine these models, as well as to pinpoint the sources of model inaccuracy. We will also use these models to help diagnose application and infrastructure problems, and to adapt the system based on this diagnosis. This section provides background in the areas relevant to the proposed work. RPI’s specific tasks within the Panorama project are as follows: (1) Develop Aspen-Simulation interface for Workflow Model Driven Simulation. (2) Validate manual performance models of two target workflow scenarios with empirical measurement and simulation. (3) Extend ROSS-Aspen API to simulate workflow descriptions when required. (4) Validate Aspen performance models of two target workflow scenarios with automatic performance model empirical measurement and simulation. (5) Design and implement final system to automatically generate Aspen performance models from workflow descriptions (including methods to compensate for limitations of Aspen analytical models). (6) Validate improved Aspen performance models with target workflow on production infrastructure. To date, all the project milestones assigned to us where reached within the best of our abilities over the course of the project performance period. Below describes the key outcome from our collaborative research in a system named, Durango .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feed-forward neural networks, fuzzy logic, and a local nonlinear predictor

Forecasting of aperiodic time series is a compelling challenge for science. In this work, we analyze aperiodic spectrophotometric data, proportional to the concentrations of two forms of a thermoreversible photochromic spiro-oxazine, that are generated when a cuvette containing a solution of the spiro-oxazine undergoes photoreaction and convection due to localized ultraviolet illumination. We construct the phase space for the system using Takens' theorem and we calculate the Lyapunov exponents and the correlation dimensions to ascertain the chaotic character of the time series. Finally, we predict the time series using three distinct methods: a feed-forward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2016

Development of a Neural Network-Based Renewable Energy Forecasting Framework for Process Industries

This paper presents a neural network-based forecasting framework for photovoltaic power (PV) generation as a decision-supporting tool to employ renewable energies in the process industry. The applicability of the proposed framework is illustrated by comparing its performance against other methodologies such as linear and nonlinear time series modelling approaches. A case study of an actual PV power plant in South Korea is presented.

14 SOLAR ENERGY↗
DOE OSTI2019

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for the monsoon region. We develop a deep neural network composed of a convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against the GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including (1) quantile mapping, (2) the support vector machine, and (3) the convolutional neural network. To test the robustness of the model and its applicability in practical forecasting, we apply the trained network for precipitation prediction forced by retrospective forecasts from the ECMWF model. Compared to the ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead times from 1 day up to 2 weeks. This superiority decreases with the forecast lead time, as the GCM’s skill in predicting atmospheric dynamics is diminished by the chaotic effect. Finally, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is only slightly worse than the observed precipitation forced simulation (NSE = 0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Comparison of Deterministic and Statistical Models for Water Quality Compliance Forecasting in the San Joaquin River Basin, California

Model selection for water quality forecasting depends on many factors including analyst expertise and cost, stakeholder involvement and expected performance. Water quality forecasting in arid river basins is especially challenging given the importance of protecting beneficial uses in these environments and the livelihood of agricultural communities. In the agriculture-dominated San Joaquin River Basin of California, real-time salinity management (RTSM) is a state-sanctioned program that helps to maximize allowable salt export while protecting existing basin beneficial uses of water supply. The RTSM strategy supplants the federal total maximum daily load (TMDL) approach that could impose fines associated with exceedances of monthly and annual salt load allocations of up to $1 million per year based on average year hydrology and salt load export limits. The essential components of the current program include the establishment of telemetered sensor networks, a web-based information system for sharing data, a basin-scale salt load assimilative capacity forecasting model and institutional entities tasked with performing weekly forecasts of river salt assimilative capacity and scheduling west-side drainage export of salt loads. Web-based information portals have been developed to share model input data and salt assimilative capacity forecasts together with increasing stakeholder awareness and involvement in water quality resource management activities in the river basin. Two modeling approaches have been developed simultaneously. The first relies on a statistical analysis of the relationship between flow and salt concentration at three compliance monitoring sites and the use of these regression relationships for forecasting. The second salt load forecasting approach is a customized application of the Watershed Analysis Risk Management Framework (WARMF), a watershed water quality simulation model that has been configured to estimate daily river salt assimilative capacity and to provide decision support for real-time salinity management at the watershed level. Analysis of the results from both model-based forecasting approaches over a period of five years shows that the regression-based forecasting model, run daily Monday to Friday each week, provided marginally better performance. However, the regression-based forecasting model assumes the same general relationship between flow and salinity which breaks down during extreme weather events such as droughts when water allocation cutbacks among stakeholders are not evenly distributed across the basin. A recent test case shows the utility of both models in dealing with an exceedance event at one compliance monitoring site recently introduced in 2020.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Predictive Model for Starlink Maritime Performance Using Multi-Horizon RandomForest

Low Earth orbit (LEO) satellite systems have become a crucial enabler of broadband access for maritime industries, where traditional networks are unavailable. However, the high mobility of LEO constellations and constantly changing weather conditions result in unpredictable link fluctuations, limiting the ability of maritime platforms to plan bandwidth usage proactively. To the best of our knowledge, no prior work has developed a short-term predictive model for maritime LEO connectivity using real experimental field measurements. This paper proposes a data-driven forecasting model that predicts future downlink throughput using multi-horizon RandomForest regression. The model is trained using real experimental coastal measurement data incorporating recent throughput history, network-layer indicators, and environmental variables. The proposed approach reduces mean absolute error by approximately 31% compared to a persistence baseline for 15-minute horizons. It maintains a measurable improvement at 30 minutes, despite increased stochasticity. These findings confirm that proactive bandwidth awareness is feasible on maritime platforms and can effectively support operational decisions such as adaptive streaming, routing, and resource scheduling. The performance gap between forecasting horizons also highlights the need for expanded offshore datasets to improve prediction robustness under harsher maritime environments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Online evolutionary neural architecture search for multivariate non-stationary time series forecasting

Time series forecasting (TSF) is one of the most important tasks in data science. TSF models are usually pre-trained with historical data and then applied on future unseen datapoints. However, real-world time series data is usually non-stationary and models trained offline usually face problems from data drift. Models trained and designed in an offline fashion can not quickly adapt to changes quickly or be deployed in real-time. To address these issues, this work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. These results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies. Additionally, results show that utilizing multiple populations of RNNs which are periodically repopulated provide significant performance improvements, allowing this online neural network architecture design and training to be successful.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Sub-City-Scale Air Quality Forecasts Combining Models, Satellites, and Surface Measures

Poor air quality is a global major concern, especially in cities with their higher emissions and large numbers of exposed people. Air quality monitoring has traditionally relied on ground-based measurements from a few accurate but expensive regulatory-grade monitors, leading to limited spatial data coverage. More recently, these have been supplemented with other data sources, including satellite observations of pollutants, atmospheric chemistry model simulations, and low-cost monitors allowing for denser spatial data collection at the expense of lower accuracy compared to regulatory-grade monitors. Each of these air quality data sources have their own benefits and drawbacks, and so there is an opportunity to combine these data together while respecting their relative strengths and weaknesses in order to generate a more comprehensive and detailed picture of local air quality. I will present our current work towards such a combination, with a focus on producing higher spatial resolution estimates and near-term forecasts of Nitrogen Dioxide in urban areas in the United States. Our method combines data from the GEOS Composition Forecasting (GEOS-CF) model system, TROPOMI tropospheric NO2 satellite data products, and ground measurements from the EPA regulatory monitoring network using a combination of simple intuitive relationships and machine learning techniques. I will show the performance of this proposed method in several urban areas in the United States, comparing it with baseline approaches using single data sources separately. Overall, we find that combining these disparate datasets together leads to more accurate air quality forecasts in the target areas than is possible using each data source separately.

Air quality↗
NASA NTRS2008

Performance of a Local Mesoscale Model with Data Denial

Forecasters at the 45th Weather Squadron (45 WS) use observations from the Kennedy Space Center (KSC) and Cape Canaveral Air Force Station (CCAFS) wind tower network and daily rawinsonde observations (RAOB) to issue and verify wind advisories, watches, and warnings for operations. They are also used by the Spaceflight Meteorology Group and Melbourne, Florida National Weather Service to initialize locally run mesoscale models. Due to impending budget cuts, some or all of the mainland wind towers and RAOBs may be eliminated, The loss of these data may significantly impact the forecast capability of the 45 WS and SMG. The Applied Meteorology Unit (AMU) was tasked to conduct an objective independent modeling study to determine how important these observations are to the accuracy of the model output used by the forecasters as input to their forecasts. To accomplish this, the AMU performed a sensitivity study using the Weather Research and Forecasting (WRF) model run with and without KSC/CCAFS wind tower and CCAFS RAOB observations and assessed the accuracy of model forecasts by comparing them to the observations.

Watson, Leela↗
DOE OSTI2025

Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models

Accurate solar Photovoltaic (PV) power forecasting is important for enhancing both the performance and economic feasibility of PV systems. This study evaluates several deep learning models, including Dense Neural Networks (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid LSTMCNN model, for predicting PV power production one day in advance. Prior to optimization, the models exhibited relatively high errors, with the best model (DNN) achieving a Root Mean Square Error (RMSE) of 31.13 kW and a coefficient of determination (R 2 ) of 62.15 %. After employing Bayesian optimization, the LSTM-CNN model demonstrated the best performance, with the RMSE reduced to 9.79 kW and R 2 improved to 97.62 %, showcasing significant enhancement in predictive accuracy. Here, the economic evaluation considered three cases: rewards for underestimation (0.08 USD/kWh), no rewards, and penalties for both over-and underestimation (120 % of the utility tariff). In the rewards scenario, the LSTM-CNN model reduced the Levelized Cost of Electricity (LCOE) by 4 %, while in the penalty scenario, a backup diesel generator would have increased the LCOE by 49 %. Additionally, the LSTM-CNN model minimized financial losses, achieving the lowest penalties and maximizing net cash flow compared to other models, demonstrating its overall technical and economic superiority.

Deep learning↗
DOE OSTI2024

AIRES-NODE

This software package performs time series forecasting for engineering systems using neural controlled differential equations. Neural controlled differential equations are continuous time analogues to recurrent neural networks. AIRES-NODE is particularly well suited for dynamic systems which are subject to external forcing terms and time-dependent boundary conditions. AIRES-NODE provides an encoder-decoder architecture which allows for variable-length forecasts to be made and is not limited to a fixed time step size when forecasting. Additionally, by utilizing a novel combination of a variational autoencoder and neural controlled differential equations, the AIRES-NODE package is capable of producing probabilistic future forecasts.

Gurecky, William [Oak Ridge National Laboratory (O↗
NASA NTRS1997

Characterizing the Relationships Among Lightning and Storm Parameters: Lightning as a Proxy Variable

We have gained important insights from prior studies that have suggested relationships between lightning and storm growth, decay, convective rain flux, vertical distribution of storm mass and echo volume in the region, and storm energetics. A study was initiated in the Summer of 1996 to determine how total (in-cloud plus ground) lightning observations might provide added knowledge to the forecaster in the determination and identification of severe thunderstorms and weather hazards in real-time. The Melbourne Weather Office was selected as a primary site to conduct this study because Melbourne is the only site in the world with continuous and open access to total lightning (LDAR) data and a Doppler (WSR-88D) radar. A Lightning Imaging Sensor Data Applications Demonstration (LISDAD) system was integrated into the forecaster's workstation during the Summer 1996 to allow the forecaster to interact in real-time with the multi-sensor data being displayed. LISDAD currently ingests LDAR data, the cloud-to-ground National Lightning Detection Network (NLDN) data, and the Melbourne radar data in f real-time. The interactive features provide the duty forecaster the ability to perform quick diagnostics on storm cells of interest. Upon selection of a storm cell, a pop-up box appears displaying the time-history of various storm parameters (e.g., maximum radar reflectivity, height of maximum reflectivity, echo-top height, NLDN and LDAR lightning flash rates, storm-based vertically integrated liquid water content). This product is archived to aid on detailed post-analysis.

Goodman, S. J.↗
DOE OSTI2021

Gaussian Process Regression for Aggregate Baseline Load Forecasting

Demand response (DR) is one of the most effective ways to maintain the reliability and improve the flexibility of power systems. Accurate forecasts of baseline loads are essential for DR programs. In the era of big data, machine learning-based approaches present a unique opportunity for baseline load forecasting. Thus, this paper presents a machine learning-based approach using a relatively less explored algorithm, Gaussian process regression (GPR), to forecast aggregate baseline loads. As such, a dataset was generated using a set of EnergyPlus simulations. Using the generated dataset, a GPR-based forecasting model was developed. In addition, support vector regression (SVR)-, artificial neural network (ANN)-, and averaging-based models were developed as baseline models for comparison. These models were compared in terms of accuracy, simplicity, and integrity. The prediction performance of the models showed that the GPR-based model is more accurate and reliable than the others. Such high performance shows the potential of the GPR in baseline load forecasting. GPR, therefore, can be used for DR applications.

Amasyali, Kadir↗
DOE OSTI2021

Attention Network Forecasts Time-to-Failure in Laboratory Shear Experiments

Rocks under stress deform by creep mechanisms that include formation and slip on small-scale internal cracks. Intragranular cracks and slip along grain contacts release energy as elastic waves termed acoustic emissions (AE). AEs are thought to contain predictive information that can be used for fault failure forecasting. Here, we present a method using unsupervised classification and an attention network to forecast labquakes using AE waveform features. Our data were generated in a laboratory setting using a biaxial shearing device with granular fault gouge intended to mimic the conditions of tectonic faults. Here, we analyzed the temporal evolution of AEs generated throughout several hundred laboratory earthquake cycles. We used a Conscience Self-Organizing Map (CSOM) to perform topologically ordered vector quantization based on waveform properties. The resulting map was used to interactively cluster AEs. We examined the clusters over time to identify those with predictive ability. Finally, we used a variety of LSTM and attention-based networks to test the predictive power of the AE clusters. By tracking cumulative waveform features over the seismic cycle, the network is able to forecast the time-to-failure (TTF) of lab earthquakes. Our results show that analyzing the data to isolate predictive signals and using a more sophisticated network architecture are key to robustly forecasting labquakes. In the future, this method could be applied on tectonic faults to monitor earthquakes and augment early warning systems.

58 GEOSCIENCES↗
DOE OSTI2023

Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles

Classical problems in computational physics such as data-driven forecasting and signal reconstruction from sparse sensors have recently seen an explosion in deep neural network (DNN) based algorithmic approaches. However, most DNN models do not provide uncertainty estimates, which are crucial for establishing the trustworthiness of these techniques in downstream decision making tasks and scenarios. In recent years, ensemble-based methods have achieved significant success for the uncertainty quantification in DNNs on a number of benchmark problems. However, their performance on real-world applications remains under-explored. In this work, we present an automated approach to DNN discovery and demonstrate how this may also be utilized for ensemble-based uncertainty quantification. Specifically, we propose the use of a scalable neural and hyperparameter architecture search for discovering an ensemble of DNN models for complex dynamical systems. We highlight how the proposed method not only discovers high-performing neural network ensembles for our tasks, but also quantifies uncertainty seamlessly. This is achieved by using genetic algorithms and Bayesian optimization for sampling the search space of neural network architectures and hyperparameters. Subsequently, a model selection approach is used to identify candidate models for an ensemble set construction. Afterwards, a variance decomposition approach is used to estimate the uncertainty of the predictions from the ensemble. We demonstrate the feasibility of this framework for two tasks — forecasting from historical data and flow reconstruction from sparse sensors for the sea-surface temperature. In conclusion, we demonstrate superior performance from the ensemble in contrast with individual high-performing models and other benchmarks.

Deep ensembles↗
NASA NTRS2009

Observation Denial and Performance of a Local Mesoscale Model

.Forecasters at the 45th Weather Squadron (45 WS) use observations from the Kennedy Space Center (KSC) and Cape Canaveral Air Force Station (CCAFS) wind tower network and the CCAFS (XMR) daily rawinsonde observations (RAOB) to issue and verify wind advisories and warnings for operations. These observations are also used by the National Weather Service (NWS) Spaceflight Meteorology Group (SMG) in Houston, Texas and the NWS Melbourne, Florida (NWS MLB) to initialize their locally-run mesoscale models. In addition, SMG uses these observations to support shuttle landings at the Shuttle Landing Facility (SLF). Due to impending budget cuts, some or all of the wind towers on the east-central Florida mainland and the XMR RAOBs may be eliminated. The locations of the mainland towers and XMR RAOB site are shown in Figure 1. The loss of these data may impact the forecast capability of the 45 WS, SMG and NWS MLB.

Watson, Leela R.↗
NASA NTRS2005

An Analysis of Peak Wind Speed Data from Collocated Mechanical and Ultrasonic Anemometers

This study focuses on a comparison of peak wind speeds reported by mechanical and ultrasonic anemometers at Cape Canaveral Air Force Station and Kennedy Space Center (CCAFS/KSC) on the east central coast of Florida and Vandenberg Air Force Base (VAFB) on the central coast of California. The legacy mechanical wind instruments on CCAFS/KSC and VAFB weather towers are being changed from propeller-and-vane (CCAFS/KSC) and cup-and-vane (VAFB) sensors to ultrasonic sensors under the Range Standardization and Automation (RSA) program. The wind tower networks on KSC/CCAFS and VAFB have 41 and 27 towers, respectively. Launch Weather Officers, forecasters, and Range Safety analysts at both locations need to understand the performance of the new wind sensors for a myriad of reasons that include weather warnings, watches, advisories, special ground processing operations, launch pad exposure forecasts, user Launch Commit Criteria (LCC) forecasts and evaluations, and toxic dispersion support. The Legacy sensors measure wind speed and direction mechanically. The ultrasonic RSA sensors have no moving parts. Ultrasonic sensors were originally developed to measure very light winds (Lewis and Dover 2004). The technology has evolved and now ultrasonic sensors provide reliable wind data over a broad range of wind speeds. However, because ultrasonic sensors respond more quickly than mechanical sensors to rapid fluctuations in speed, characteristic of gusty wind conditions, comparisons of data from the two sensor types have shown differences in the statistics of peak wind speeds (Lewis and Dover 2004). The 45th Weather Squadron (45 WS) and the 30 WS requested the Applied Meteorology Unit (AMU) to compare data from RSA and Legacy sensors to determine if there are significant differences in peak wind speed information from the two systems.

Short, David A.↗
DOE OSTI2024

Reduced‐Order Probabilistic Emulation of Physics‐Based Ring Current Models: Application to RAM‐SCB Particle Flux

Abstract In this work, we address the computational challenge of large‐scale physics‐based simulation models for the ring current. Reduced computational cost allows for significantly faster than real‐time forecasting, enhancing our ability to predict and respond to dynamic changes in the ring current, valuable for space weather monitoring and mitigation efforts. Additionally, it can also be used for a comprehensive investigation of the system. Thus, we aim to create an emulator for the Ring current‐Atmosphere interactions Model with Self‐Consistent magnetic field (RAM‐SCB) particle flux that not only improves efficiency but also facilitates forecasting with reliable estimates of prediction uncertainties. The probabilistic emulator is built upon the methodology developed by Licata and Mehta (2023), https://doi.org/10.1029/2022sw003345 . A novel discrete sampling is used to identify 30 simulation periods over 20 years of solar and geomagnetic activity. Focusing on a subset of particle flux, we use Principal Component Analysis for dimensionality reduction and Long Short‐Term Memory (LSTM) neural networks to perform dynamic modeling. Hyperparameter space was explored extensively resulting in about 5% median symmetric accuracy across all data sets for one‐step dynamic prediction. Using a hierarchical ensemble of LSTMs, we have developed a reduced‐order probabilistic emulator (ROPE) tailored for time‐series forecasting of particle flux in the ring current. This ROPE offers accurate predictions of omnidirectional flux at a single energy with no pitch angle information, providing robust predictions on the test set with an error score below 11% and calibration scores under 8% with bias under 2% providing a significant speed up as compared to the full RAM‐SCB run.

79 ASTRONOMY AND ASTROPHYSICS↗