Search NASA⌕ Search

SEARCH · Search NASA

Results for “FORECASTS”

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 595 records · Page 33

AI/ML-Enhanced Wind Forecasts for Reducing Uncertainty in Prescribed Fire Planning

Prescribed fire is a vital tool for ecosystem management and wildfire risk reduction but its escalation is constrained by overly conservative burn windows because of uncertainties, for instance, in wind forecasts. This review describes the state of the art in weather product use by fire/smoke models and identifies three priority research gaps that artificial intelligence/machine learning (AI/ML) is well positioned to address: (1) spatial and temporal downscaling to meter-scale, sub-hourly wind fields; (2) bias correction for systematic model errors in complex terrain; and (3) robust uncertainty quantification to inform ensemble-based simulations. Emerging AI/ML techniques offer promising frameworks to address all three challenges. By providing high-resolution, bias-corrected, and probabilistic wind fields, AI/ML-enhanced forecasts will allow for expanded burn windows, improved ignition strategy design and a reduced reliance on expert intuition, especially when a prescribed fire is introduced into new areas.

54 ENVIRONMENTAL SCIENCES↗

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↗

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Incorporating Wind Generation Forecast Uncertainty into Power System Operation, Dispatch, and Unit Commitment Procedures

In this paper, an approach to evaluate the uncertainties of the balancing capacity, ramping capability, and ramp duration requirements is proposed. The approach includes three steps: forecast data acquisition, statistical analysis of retrospective information, and prediction of grid balancing requirements for a specified time horizon and a given confidence level. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on histogram analysis, incorporating sources of uncertainty 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 is developed to evaluate the look-ahead required generation performance envelope for the worst case scenario within a user-specified confidence level. A self-validation process is used to validate the accuracy of the confidence intervals. To demonstrate the validity of the developed uncertainty assessment methods and its impact on grid operation, a framework for integrating the proposed methods with an EMS system is developed. Demonstration through integration with an EMS system illustrates the applicability of the proposed methodology and the developed tool for actual grid operation and paves the road for integration with EMS systems from other vendors.

17 WIND ENERGY↗

Impact of Improved Solar Forecasts on Bulk Power System Operations in ISO-NE: Preprint

The diurnal nature of solar power is made uncertain by variable cloud cover and the influence of atmospheric conditions on irradiance scattering processes. Its forecasting has become increasingly important to the unit commitment and dispatch process for efficient scheduling of generators in power system operations. This study examines the value of improved solar power forecasting for the Independent System Operator-New England system. The results show how 25% solar power penetration reduces net electricity generation costs by 22.9%.

14 SOLAR ENERGY↗

Impact of Improved Solar Forecasts on Bulk Power System Operations in ISO-NE (Presentation)

The diurnal nature of solar power is made uncertain by variable cloud cover and the influence of atmospheric conditions on irradiance scattering processes. Its forecasting has become increasingly important to the unit commitment and dispatch process for efficient scheduling of generators in power system operations. This presentation is an overview of a study that examines the value of improved solar forecasts on Bulk Power System Operations.

14 SOLAR ENERGY↗

Considering the Variability of Soiling in Long-Term PV Performance Forecasting: Preprint

This study presents the development of a methodology for evaluating the variability associated with soiling on long-term PV forecasting. Independent engineering firms typically build P50 forecasts for large PV plants through the use of the PVsyst software, where monthly soiling losses are one of many inputs to the P50 model. Subsequently, long-term performance distributions, or Pvalues, are constructed through a Monte Carlo analysis that includes various factors such as: satellite irradiance modeling uncertainty, uncertainty in the PVsyst model, and long-term irradiance variability. Often the PVsyst model uncertainty is increased to account for sites with significant soiling concerns but no systematic method has been presented in the literature to specifically include soiling variability within Pvalues. In this work soiling information from 16 sites in the U.S. Southwest are combined with 20 years of rainfall data to generate 20 years of energy production with soiling losses and then subsequently generate Pvalues. The results show that the spread of Pvalues (P1-P99) can increase from 0-13% when interannual soiling variability is included.

interannual variability↗

Outage Forecast-Based Preventative Scheduling Model for Distribution System Resilience Enhancement: Preprint

Distribution system resilience enhancement is an important topic to ensure customers have access to the power supply during extreme events. In fact, certain weather-related extreme events can be predicted ahead of time. Therefore, it is important to investigate how to predict grid outages using extreme weather forecasts, and how outage predictions can be incorporated into distribution system resilience enhancement. In this paper, a preventative scheduling model for distribution systems is proposed. The model targets at allocating resources, especially mobile responsive resources such as mobile backup generators and mobile energy storage systems, to prepare for an extreme event in the day-ahead context. To achieve efficient resource allocation and scheduling, a machine learning-based outage prediction module is developed to predict vulnerable or risky segments of the distribution system based on historical operating records and extreme weather event forecasts. By integrating the outage prediction results into the scheduling model, optimal resource allocation can be derived to help distribution systems prepare for an upcoming event and improve resilience performance. A real distribution feeder in North Carolina, U.S. is used in the case study to validate the proposed approach.

distributed energy resources↗

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decompose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep-learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high-level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for a one-year lead hourly load below $5\%$ MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM: Preprint

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decompose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep-learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high-level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for a one-year lead hourly load below 5% MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗

Outage Forecast-Based Preventative Scheduling Model for Distribution System Resilience Enhancement

Distribution system resilience enhancement is an important topic to ensure customers have access to power supply during extreme events. In fact, certain weather-related extreme events can be predicted ahead of time. Therefore, it is important to investigate how to predict grid outages using extreme weather forecasts, and how outage predictions can be incorporated into distribution system resilience enhancement. In this paper, a preventative scheduling model for distribution systems is proposed. The model targets at allocating resources, especially mobile responsive resources such as mobile backup generators and mobile energy storage systems, to prepare for an extreme event in the day-ahead context. To achieve efficient resource allocation and scheduling, a machine learning-based outage prediction module is developed to predict vulnerable or risky segments of the distribution system based on historical operating records and extreme weather event forecast. By integrating the outage prediction results into the scheduling model, optimal resource allocation can be derived to help distribution systems prepare for an upcoming event and improve resilience performance. A real distribution feeder in North Carolina, U.S. is used in the case study to validate the proposed approach.

distributed energy resources↗

Impact of Three-Phase Relative Permeability and Hysteresis Models on Forecasts of Storage Associated With CO 2 -EOR

Geological CO 2 sequestration in conjunction with enhanced oil recovery (CO 2 -EOR) includes complex multiphase flow processes compared to CO 2 storage in deep saline aquifers. Two of the most critical factors affecting multiphase flow in CO 2 -EOR are three-phase relative permeability and associated hysteresis, both of which are difficult to measure and are usually represented by numerical interpolation models. The purpose of this research is to improve understanding of (1) the relative impacts of different three-phase relative permeability models and hysteresis models on CO 2 trapping mechanisms, and (2) uncertainty associated with these two factors. Four different three-phase relative permeability models and three hysteresis models were applied to simulations of an active CO 2 -EOR site, the SACROC unit located in western Texas. To eliminate potential bias of deterministic parameters, we utilized a sequential Gaussian simulation technique to generate 50 realizations to describe heterogeneity of porosity and permeability, based on data obtained from well logs and seismic survey. Simulation results of forecasted CO 2 storage suggested that (1) the choice of three-phase relative permeability model and hysteresis model led to noticeable impacts on forecasted CO 2 sequestration capacity; (2) impacts of three-phase relative permeability models and hysteresis models on CO 2 trapping are small during the CO 2 -EOR injection period, and increase during the post-EOR CO 2 injection period; (3) the specific choice of hysteresis model is more important relative to the choice of three-phase relative permeability model; and (4) using the recommended three-phase WAG (Water-Alternating-Gas) hysteresis model may increase the impact of three-phase relative permeability models and uncertainty due to heterogeneity.

42 ENGINEERING↗

Comparison of Observations and Predictions of Daytime Planetary-Boundary-Layer Heights and Surface Meteorological Variables in the Columbia River Gorge and Basin During the Second Wind Forecast Improvement Project

The second Wind Forecast Improvement Project (WFIP2) is an 18-month field campaign in the Pacific Northwest U.S.A., whose goal is to improve the accuracy of numerical-weather-prediction forecasts in complex terrain. The WFIP2 campaign involved the deployment of a large suite of in situ and remote sensing instrumentation, including eight 915-MHz wind-profiling radars, and surface meteorological stations. The evolution and annual variability of the daytime convective planetary-boundary-layer (PBL) height is investigated using the wind-profiling radars. Three models with different horizontal grid spacing are evaluated: the Rapid Refresh, the High-Resolution Rapid Refresh, and its nested version. The results are used to assess errors in the prediction of PBL height within the experimental and control versions of the models, with the experimental versions including changes and additions to the model parametrizations developed during the field campaign, and the control version using the parametrizations present in the National Oceanic and Atmospheric Administration/National Centers for Environmental Prediction operational version of the models at the start of the project. Results show that the high-resolution models outperform the low-resolution versions, the experimental versions perform better compared with the control versions, model PBL height estimations are more accurate on cloud-free days, and model estimates of the PBL height growth rate are more accurate than model estimates of the rate of decay. Finally, using surface sensors, we assess surface meteorological variables, finding improved surface irradiance and, to a lesser extent, improved 2-m temperature in the experimental version of the model.

54 ENVIRONMENTAL SCIENCES↗

Should Sea-Ice Modeling Tools Designed for Climate Research Be Used for Short-Term Forecasting?

In theory, the same sea-ice models could be used for both research and operations, but in practice, differences in scientific and software requirements and computational and human resources complicate the matter. Although sea-ice modeling tools developed for climate studies and other research applications produce output of interest to operational forecast users, such as ice motion, convergence, and internal ice pressure, the relevant spatial and temporal scales may not be sufficiently resolved. For instance, sea-ice research codes are typically run with horizontal resolution of more than 3 km, while mariners need information on scales less than 300 m. Certain sea-ice processes and coupled feedbacks that are critical to simulating the Earth system may not be relevant on these scales; and therefore, the most important model upgrades for improving sea-ice predictions might be made in the atmosphere and ocean components of coupled models or in their coupling mechanisms, rather than in the sea-ice model itself. This paper discusses some of the challenges in applying sea-ice modeling tools developed for research purposes for operational forecasting on short time scales, and highlights promising new directions in sea-ice modeling.

54 ENVIRONMENTAL SCIENCES↗

Roadmap and Benchmarking: Privacy in Federated Load Forecasting

Data-driven techniques for energy demand forecasting continue to emerge with promising impacts on distribution grid planning. However, the development of robust and generalizable machine learning models requires that representative high quality training data are available. Distributed energy resources have begun to embed intelligence, gathering large amounts of data on customer demand, behavior, and household devices that are connected to the grid. Though utilities aggregate meter-level demand data for load shaping, demand response, outage management, reliability planning, and billing applications, there lies an inherent privacy concern in sharing consumption data that may identify individual consumer behavioral patterns. Hence, while sharing the data is crucial, the private sensitive customer data must be safeguarded from being exposed or manipulated. In this study, we propose a roadmap for implementing a based privacy preserving framework to support the advancement of data-driven analytics in data-sensitive distributed energy resources environments. The roadmap incorporates federated learning–a distributed training framework, differential privacy–a statistical framework that provides guarantees to safeguard the leakage of sensitive data, secure multiparty computation and homomorphic encryption– techniques for encrypting model gradients and applying secure aggregation on the server. Moreover, we perform baseline experiments on the federated short-term load forecasting (STLF) task using open-source residential load profile datasets, offering insights into the challenges of integrating differential privacy into federated learning.

Abebe, Waqwoya [Oak Ridge National Laboratory (ORN↗

Adaptive Algebraic Derivative Estimation for Battery Electric Buses Energy Consumption Forecasting

The limited service life of onboard batteries for EVs is a challenge, underscoring the need for real-time battery usage prediction. This paper proposes an adaptive Algebraic Derivative Estimation (ADE) approach for forecasting the energy consumption of battery electric buses. By dynamically adjusting the sliding window length, the adaptive ADE retains the fixed-length ADE’s key advantage—namely, operating online without reliance on extensive historical datasets—while substantially bolstering forecast accuracy by actively trading estimation bias off estimation variance. Comparative experiments against both the conventional ADE with a fixed length and a representative machine learning algorithm, XGBoost, were conducted, with performance evaluated via root mean square error, mean absolute error, and the coefficient of determination. The results demonstrate that the proposed approach significantly outperforms baseline methods.

Cui, Tianyang [The University of Texas at Dallas]↗