Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 163 records · Page 9

A first large-scale flood inundation forecasting model

At present continental to global scale flood forecasting focusses on predicting at a point discharge, with little attention to the detail and accuracy of local scale inundation predictions. Yet, inundation is actually the variable of interest and all flood impacts are inherently local in nature. This paper proposes a first large scale flood inundation ensemble forecasting model that uses best available data and modeling approaches in data scarce areas and at continental scales. The model was built for the Lower Zambezi River in southeast Africa to demonstrate current flood inundation forecasting capabilities in large data-scarce regions. The inundation model domain has a surface area of approximately 170k km2. ECMWF meteorological data were used to force the VIC (Variable Infiltration Capacity) macro-scale hydrological model which simulated and routed daily flows to the input boundary locations of the 2-D hydrodynamic model. Efficient hydrodynamic modeling over large areas still requires model grid resolutions that are typically larger than the width of many river channels that play a key a role in flood wave propagation. We therefore employed a novel sub-grid channel scheme to describe the river network in detail whilst at the same time representing the floodplain at an appropriate and efficient scale. The modeling system was first calibrated using water levels on the main channel from the ICESat (Ice, Cloud, and land Elevation Satellite) laser altimeter and then applied to predict the February 2007 Mozambique floods. Model evaluation showed that simulated flood edge cells were within a distance of about 1 km (one model resolution) compared to an observed flood edge of the event. Our study highlights that physically plausible parameter values and satisfactory performance can be achieved at spatial scales ranging from tens to several hundreds of thousands of km2 and at model grid resolutions up to several km2. However, initial model test runs in forecast mode revealed that it is crucial to account for basin-wide hydrological response time when assessing lead time performances notwithstanding structural limitations in the hydrological model and possibly large inaccuracies in precipitation data.

hydrodynamic, hydrology, forecast, flood inundatio↗

Multimodal sensor fusion framework for residential building occupancy detection

For several years now, smart building energy systems have been a research area of intensive activity. In light of the increasing need for sustainable buildings and energy systems, this trend motivates an increasing need for a solution to reduce carbon dioxide emissions and improve energy efficiency. This work proposes a high-performing and transferable occupancy detection framework that combines sensor data from different data modalities, including time series environmental data (temperature, humidity, and illuminance), image data, and acoustic energy data using ensemble method. To draw out the best prediction performance in each modality, the proposed framework was developed, including various models that were designed to learn the occupancy patterns reflected in the physical data streams. To tackle the time series environmental data, we designed two variants of an occupancy detection spatiotemporal pattern network (Occ-STPN) that performs both feature level and decision level fusion, respectively. We also propose a new metric; the fading memory mean square error (FMMSE), that provides a fair evaluation and penalization of delayed occupancy predictions. Multiple open-sourced datasets, including the Electricity Consumption and Occupancy and the University of California, Irvine's (UCI) building occupancy detection dataset, along with our own real data collected from six different houses, were used to validate the algorithms' performance. The experimental results presented herein break down the performance for each sensing modality, and a detailed analysis of the performance is also discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Distributionally Robust Decentralized Volt-Var Control With Network Reconfiguration

Here, this paper presents a decentralized volt-var optimization (VVO) and network reconfiguration strategy to address the challenges arising from the growing integration of distributed energy resources, particularly photovoltaic (PV) generation units, in active distribution networks. To reconcile control measures with different time resolutions and empower local control centers to handle intermittency locally, the proposed approach leverages a two-stage distributionally robust optimization; decisions on slow-responding control measures and set points that link neighboring subnetworks are made in advance while considering all plausible distributions of uncertain PV outputs. We present a decomposition algorithm with an acceleration scheme for solving the proposed model. Numerical experiments on the IEEE 123 bus distribution system are given to demonstrate its outstanding out-of-sample performance and computational efficiency, which suggests that the proposed method can effectively localize uncertainty via risk-informed proactive timely decisions.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Machine Learning for Daily Forecasts of Arctic Sea Ice Motion: An Attribution Assessment of Model Predictive Skill

Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.

54 ENVIRONMENTAL SCIENCES↗

Connect the Dots: In Situ 4-D Seismic Monitoring of CO 2 Storage With Spatio-Temporal CNNs

4-D seismic imaging has been widely used in CO 2 sequestration projects to monitor the fluid flow in the volumetric subsurface region that is not sampled by wells. Ideally, real-time monitoring and near-future forecasting would provide site operators with great insights to understand the dynamics of the subsurface reservoir and assess any potential risks. However, due to obstacles such as high deployment cost, availability of acquisition equipment, exclusion zones around surface structures, only very sparse seismic imaging data can be obtained during monitoring. That leads to an unavoidable and growing knowledge gap over time. The operator needs to understand the fluid flow throughout the project lifetime and the seismic data are only available at a limited number of times. This is insufficient for understanding reservoir behavior. To overcome those challenges, we have developed spatio-temporal neural-network-based models that can produce high-fidelity interpolated or extrapolated images effectively and efficiently. Specifically, our models are built on an autoencoder, and incorporate the long short-term memory (LSTM) structure with a new loss function regularized by optical flow. We validate the performance of our models using real 4-D post-stack seismic imaging data acquired at the Sleipner CO 2 sequestration field. We employ two different strategies in evaluating our models. Numerically, we compare our models with different baseline approaches using classic pixel-based metrics. We also conduct a blind survey and collect a total of 20 responses from domain experts to evaluate the quality of data generated by our models. Finally, via both numerical and expert evaluation, we conclude that our models can produce high-quality 2-D/3-D seismic imaging data at a reasonable cost, offering the possibility of real-time monitoring or even near-future forecasting of the CO 2 storage reservoir.

4-D seismic imaging↗

Aerosol indirect effect on the grid-scale clouds in the two-way coupled WRF–CMAQ: model description, development, evaluation and regional analysis

This study implemented first, second and glaciation aerosol indirect effects (AIE) on resolved clouds in the two-way coupled Weather Research and Forecasting Community Multiscale Air Quality (WRF–CMAQ) modeling system by including parameterizations for both cloud drop and ice number concentrations on the basis of CMAQ-predicted aerosol distributions and WRF meteorological conditions. The performance of the newly developed WRF–CMAQ model, with alternate Community Atmospheric Model (CAM) and Rapid Radiative Transfer Model for GCMs (RRTMG) radiation schemes, was evaluated with observations from the Clouds and the See http://ceres.larc.nasa.gov/ . Earth's Radiant Energy System (CERES) satellite and surface monitoring networks (AQS, IMPROVE, CASTNET, STN, and PRISM) over the continental US (CONUS) (12 km resolution) and eastern Texas (4 km resolution) during August and September of 2006. The results at the Air Quality System (AQS) surface sites show that in August, the normalized mean bias (NMB) values for PM 2.5 over the eastern US (EUS) and the western US (WUS) are 5.3% (-0.1%) and 0.4% (-5.2%) for WRF–CMAQ/CAM (WRF–CMAQ/RRTMG), respectively. The evaluation of PM 2.5 chemical composition reveals that in August, WRF–CMAQ/CAM (WRF–CMAQ/RRTMG) consistently underestimated the observed SO 4 2- by -23.0% (-27.7%), -12.5% (-18.9%) and -7.9% (-14.8%) over the EUS at the Clean Air Status Trends Network (CASTNET), Interagency Monitoring of Protected Visual Environments (IMPROVE) and Speciated Trends Network (STN) sites, respectively. Both configurations (WRF–CMAQ/CAM, WRF–CMAQ/RRTMG) overestimated the observed mean organic carbon (OC), elemental carbon (EC) and and total carbon (TC) concentrations over the EUS in August at the IMPROVE sites. Both configurations generally underestimated the cloud field (shortwave cloud forcing, SWCF) over the CONUS in August due to the fact that the AIE on the subgrid convective clouds was not considered when the model simulations were run at the 12 km resolution. This is in agreement with the fact that both configurations captured SWCF and longwave cloud forcing (LWCF) very well for the 4 km simulation over eastern Texas, when all clouds were resolved by the finer resolution domain. The simulations of WRF–CMAQ/CAM and WRF–CMAQ/RRTMG show dramatic improvements for SWCF, LWCF, cloud optical depth (COD), cloud fractions and precipitation over the ocean relative to those of WRF default cases in August. The model performance in September is similar to that in August, except for a greater overestimation of PM 2.5 due to the overestimations of SO 4 2- , NH 4 + , NO 3 - , and TC over the EUS, less underestimation of clouds (SWCF) over the land areas due to the lower SWCF values, and fewer convective clouds in September. Finally, this work shows that inclusion of indirect aerosol effect treatments in WRF–CMAQ represents a significant advancement and milestone in air quality modeling and the development of integrated emissions control strategies for air quality management and climate change mitigation.

indirect aerosol forcing↗

Efficient Super-Resolution of Near-Surface Climate Modeling Using the Fourier Neural Operator

Downscaling methods are critical in efficiently generating high-resolution atmospheric data. However, state-of-the-art statistical or dynamical downscaling techniques either suffer from the high computational cost of running a physical model or require high-resolution data to develop a downscaling tool. Here, we demonstrate a recently proposed zero-shot super-resolution method, the Fourier neural operator (FNO), to efficiently perform downscaling without the need for high-resolution data. Because the FNO learns dynamics in Fourier space, FNO is a resolution-invariant emulator; it can be trained at a coarse resolution and produces emulation at any high resolution. We applied FNO to downscale a 4-km resolution Weather Research and Forecasting (WRF) Model simulation of near-surface heat-related variables over the Great Lakes region. The FNO is driven by the atmospheric forcings, and topographic features used in the WRF model at the same resolution. We incorporated a physics-constrained loss in FNO by using the Clausius-Clapeyron relation to better constrain the relations among the emulated states. Trained on merely 600 WRF snapshots at 4-km resolution, the FNO shows comparable performance with a widely used convolutional network, U-Net, achieving averaged modified Kling-Gupta Efficiency of 0.88 and 0.94 on the test dataset for temperature and pressure, respectively. We then employed the FNO to produce 1-km emulations to reproduce the fine climate features. Further, by taking the WRF simulation as ground truth, we show consistent performances at the two resolutions, suggesting the reliability of FNO in producing high-resolution dynamics. Our study demonstrates the potential of using FNO for zero-shot super-resolution in generating first-order estimation on atmospheric modeling.

54 ENVIRONMENTAL SCIENCES↗

MPC4CLR (Model-Predictive-Control-for-Critical-Load-Restoration-in-Power-Distribution-Systems) [SWR-22-24]

Model predictive control (MPC) is a system or process control technique for making decisions under uncertainty via rolling look-ahead optimizations at each control step where only the current step decisions are applied, and the rest are discarded. In this work, we developed an MPC for a critical load restoration (CLR) in power distribution systems to recover system service (electricity delivery) following an extreme event-triggered substation outage. The method considers the problem of controlling distributed energy resources (DERs) of the distribution system with the objective of achieving maximum load pick up while satisfying distribution network flow and voltage constraints. A linearized optimal power flow (OPF) model is employed to represent the physics of the network. The problem formulation is augmented with a ramping (up) reserve product for the DERs to ensure improved and upward monotonic load restoration as time evolves. Simulation analysis and performance tests are performed using a modified IEEE 13-bus test feeder integrated with wind, solar, microturbine, and energy storage battery. The software is developed using various software packages in Julia and Python. The MPC model is implemented using the JuMP optimization language in Julia while the data analytics including renewable generation and load demand forecasts, running the MPC simulation and visualizations is performed in Python.

Eseye, Abinet Tesfaye↗

A comparison of model validation approaches for echo state networks using climate model replicates

As global temperatures continue to rise, climate mitigation strategies such as stratospheric aerosol injections (SAI) are increasingly discussed, but the downstream effects of these strategies are not well understood. As such, there is interest in developing statistical methods to quantify the evolution of climate variable relationships during the time period surrounding an SAI. Feature importance applied to echo state network (ESN) models has been proposed as a way to understand the effects of SAI using a data-driven model. This approach depends on the ESN fitting the data well. If not, the feature importance may place importance on features that are not representative of the underlying relationships. Typically, time series prediction models such as ESNs are assessed using out-of-sample performance metrics that divide the times series into separate training and testing sets. However, this model assessment approach is geared towards forecasting applications and not scenarios such as the motivating SAI example where the objective is using a data driven model to capture variable relationships. Here, in this paper, we demonstrate a novel use of climate model replicates to investigate the applicability of the commonly used repeated hold-out model assessment approach for the SAI application. Simulations of an SAI are generated using a simplified climate model, and different initialization conditions are used to provide independent training and testing sets containing the same SAI event. The climate model replicates enable out-of-sample measures of model performance, which are compared to the single time series hold-out validation approach. For our case study, it is found that the repeated hold-out sample performance is comparable, but conservative, to the replicate out-of-sample performance when the training set contains enough time after the aerosol injection.

54 ENVIRONMENTAL SCIENCES↗

On the effectiveness of neural operators at zero-shot weather downscaling

Machine-learning (ML) methods have shown great potential for weather downscaling. These data-driven approaches provide a more efficient alternative for producing high-resolution weather datasets and forecasts compared to physics-based numerical simulations. Neural operators, which learn solution operators for a family of partial differential equations, have shown great success in scientific ML applications involving physics-driven datasets. Neural operators are grid-resolution-invariant and are often evaluated on higher grid resolutions than they are trained on, i.e., zero-shot super-resolution. Given their promising zero-shot super-resolution performance on dynamical systems emulation, we present a critical investigation of their zero-shot weather downscaling capabilities, which is when models are tasked with producing high-resolution outputs using higher upsampling factors than are seen during training. To this end, we create two realistic downscaling experiments with challenging upsampling factors (e.g., 8x and 15x) across data from different simulations: the European Centre for Medium-Range Weather Forecasts Reanalysis version 5 (ERA5) and the Wind Integration National Dataset Toolkit. While neural operator-based downscaling models perform better than interpolation and a simple convolutional baseline, we show the surprising performance of an approach that combines a powerful transformer-based model with parameter-free interpolation at zero-shot weather downscaling. We find that this Swin-Transformer-based approach mostly outperforms models with neural operator layers in terms of average error metrics, whereas an Enhanced Super-Resolution Generative Adversarial Network-based approach is better than most models in terms of capturing the physics of the ground truth data. We suggest their use in future work as strong baselines.

17 WIND ENERGY↗

Device Classification for Industrial Control Systems Using Predicted Traffic Features

To achieve a secure interconnected Industrial Control System (ICS) architecture, security practitioners depend on accurate identification of network host behavior. However, accurate machine learning based host identification methods depends on the availability of significant quantities of network traffic data, which can be difficult to obtain due to system constraints such as network security, data confidentiality, and physical location. In this work, we propose a network traffic feature prediction method based on a generative model, which achieves high host identification accuracy. Furthermore, we develop a joint training algorithm to improve host identification performance compared to separate training of the generative model and the classifier responsible for host identification.

97 MATHEMATICS AND COMPUTING↗

Microstructure and Performance of Nano-WC Particle-Strengthened Ni Coatings by Electro-brush Plating

Nano-WC particle-strengthened Ni composite coatings were prepared by electro-brush plating. A series of artificial neural network models was developed for the analysis and prediction of the coating performance. The microstructure and phase structure were studied with SEM, XRD and EDS. Nano-WC particles as the hard phase were distributed evenly and dispersed in the coatings, which was conducive to the hardness enhancement of the coatings. Additionally, nano-WC particles as microballs inserted in the coatings could reduce the friction when wear of the coating surface occurred. Furthermore, the addition of nano-WC particles delayed the time of crack initiation and propagation in the coatings, which increased the service lifetime when they worked in a thermal shock environment.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

SU-E-J-115: Using Markov Chain Modeling to Elucidate Patterns in Breast Cancer Metastasis Over Time and Space

Purpose: Traditionally, breast cancer metastasis is described as a process wherein cancer cells spread from the breast to multiple organ systems via hematogenous and lymphatic routes. Mapping organ specific patterns of cancer spread over time is essential to understanding metastatic progression. In order to better predict sites of metastases, here we demonstrate modeling of the patterned migration of metastasis. Methods: We reviewed the clinical history of 453 breast cancer patients from Memorial Sloan Kettering Cancer Center who were non-metastatic at diagnosis but developed metastasis over time. We used the variables of organ site of metastases as well as time to create a Markov chain model of metastasis. We illustrate the probabilities of metastasis occurring at a given anatomic site together with the probability of spread to additional sites. Results: Based on the clinical histories of 453 breast cancer patients who developed metastasis, we have learned (i) how to create the Markov transition matrix governing the probabilities of cancer progression from site to site; (ii) how to create a systemic network diagram governing disease progression modeled as a random walk on a directed graph; (iii) how to classify metastatic sites as ‘sponges’ that tend to only receive cancer cells or ‘spreaders’ that receive and release them; (iv) how to model the time-scales of disease progression as a Weibull probability distribution function; (v) how to perform Monte Carlo simulations of disease progression; and (vi) how to interpret disease progression as an entropy-increasing stochastic process. Conclusion: Based on our modeling, metastatic spread may follow predictable pathways. Mapping metastasis not simply by organ site, but by function as either a ‘spreader’ or ‘sponge’ fundamentally reframes our understanding of metastatic processes. This model serves as a novel platform from which we may integrate the evolving genomic landscape that drives cancer metastasis. PS-OC Trans-Network Project Grant Award for “Data Assimilation and ensemble statistical forecasting methods applied to the MSKCC longitudinal metastatic breast cancer cohort.”.

60 APPLIED LIFE SCIENCES↗

Modelling and Simulation of a Thermoelectric Heat Pump with Micro-Channel Heat Transfer

Thermoelectric heat pumps (TEHPs) have advantages of modularity and simple design for heating and cooling in some applications. Models of thermoelectric (TE) heat pumps are widely studied. Nevertheless, most existing modeling work focuses on the TE material or air-sourced TE modules. TEHP modeling, especially the relationship between modules and heat exchangers, has not been comprehensively conducted. This work presents a water-to-water TEHP modeling framework that combines Goldsmid’s approach for TE material performance, Gnielinski’s correlation for convective heat transfer, and thermal balance theory for heat exchange networks. This combined framework provides an accurate theoretical analysis of the water-to-water TEHP system. Subsequently, the framework was used to empirically determine TE material properties (electric resistivity, thermal conductivity, and Seebeck coefficient) that minimize modeling errors versus experimentally observed values from the literature. Finally, an additional set of experimental TEHP data was used to validate the model, all with relative absolute deviations of approximately 10% when predicting heating capacity and 10%–20% when forecasting cooling capacity at a 30 K temperature lift. For future work, people can further develop models of TEHPs with an air-based heat sink on one side and water channels on the other side.

Wan, Hanlong↗

Convolutional neural networks for intra-hour solar forecasting based on sky image sequences

Accurate and timely solar forecasts play an increasingly critical role in power systems. Compared to longer forecasting timescales, very short-term solar forecasting has lagged behind in both research and practice. In this paper, we propose deep convolutional neural networks (CNNs) to provide operational intra-hour (10-minute-ahead to 60-minute-ahead) solar forecasts. We develop two CNN structures inspired by a widely-used CNN architecture. The CNNs are tailored to our solar forecasting regression tasks and rely solely on sky image sequences. Case studies based on six years of data (over 150,000 data points) demonstrate that the best CNN model has forecast skill scores of 20%-39% over the naive persistence of cloudiness benchmark, even at these very short timescales. The CNNs also have consistently superior performance when compared to shallow machine learning models with meteorological predictors, where the improvement averages around 7%. The sensitivity analyses show that the sky image length, resolution, and weather conditions have impacts on the deep learning model accuracy. In our intra-hour problem with specific setups, two sky images with a 10-minute 128 x 128 resolution yield the most accurate forecasts. Current limitations, future work, and deployment challenges and solutions are also discussed.

14 SOLAR ENERGY↗

Flexibility Requirements for Energy Systems with Renewable Generation under Forecast Uncertainties

Energy systems with high fractions of renewable energy-based resources require adequate assets providing flexibility in electricity usage to maximize the benefits of renewable energy. In this paper, we provide an analytical approach to estimate the flexibility requirements of such energy systems, with forecast uncertainties in both demand and generation. Our analytical results show that even with forecast errors, the expected system operating cost decreases with an increase in the amount of flexibility capacity -- however, there is an inflection point, beyond which addition of further flexibility capacity does not reduce expected system cost any further. Additionally, an enumeration-based approach is presented to estimate the maximum flexibility capacity needed to optimize the operating cost. Numerical experiments conducted on a network-abstracted modified IEEE 30-bus system are used for empirical validation and gaining additional insights on the effect of prosumers' willingness to offer flexibility on the dispatch performance.

Bhattacharya, Saptarshi↗

Forecasting Battery Electrode Performance via Electrochemical Fluorescence Microscopy and Machine-Learning

Predicting lithium-ion battery performance is hindered by microscale electrode heterogeneities invisible to conventional diagnostics. Here, we combine electrochemical fluorescence microscopy (EFM), which maps electronic connectivity by visualizing an electrofluorophore reaction distribution, with a multitask ElasticNet regression to forecast discharge capacity from spatial heterogeneity. Analyzing 196 images from six pilot-scale LiNi 0.5 Mn 0.3 Co 0.2 O 2 cathodes with varying carbon loadings, we extract 62 descriptors that capture morphology and texture. A compact five-feature model predicts capacity across eight discharge rates, achieving a per-target R 2 of up to 0.63 and an overall R 2 of 0.92, with a mean absolute percentage error of less than 2%. This performance rivals impedance-based approaches while avoiding their reliance on postformation data and incomplete electronic network information. Our facile and rapid, image-driven method may enable electrode quality control upstream of costly cell assembly to offer a transformative tool for data-driven battery research and manufacturing.

battery electrodes↗

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

97 MATHEMATICS AND COMPUTING↗