Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed training”

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 1,639 records · Page 91
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.

33 ADVANCED PROPULSION SYSTEMS↗
NASA NTRS2021

Aerosol and Cloud Detection Using Machine Learning Algorithms and Space-Based Lidar Data

Clouds and aerosols play a significant role in determining the overall atmospheric radiation budget, yet remain a key uncertainty in understanding and predicting the future climate system. In addition to their impact on the Earth’s climate system, aerosols from volcanic eruptions, wildfires, man-made pollution events and dust storms are hazardous to aviation safety and human health. Space-based lidar systems provide critical information about the vertical distributions of clouds and aerosols that greatly improve our understanding of the climate system. However, daytime data from backscatter lidars, such as the Cloud-Aerosol Transport System (CATS) on the International Space Station (ISS), must be averaged during science processing at the expense of spatial resolution to obtain sufficient signal-to-noise ratio (SNR) for accurately detecting atmospheric features. For example, 50% of all atmospheric features reported in daytime operational CATS data products require averaging to 60 km for detection. Furthermore, the single-wavelength nature of the CATS primary operation mode makes accurately typing these features challenging in complex scenes. This paper presents machine learning (ML) techniques that, when applied to CATS data, (1) increased the 1064 nm SNR by 75%, (2) increased the number of layers detected (any resolution) by 30%, and (3) enabled detection of 40% more atmospheric features during daytime operations at a horizontal resolution of 5 km compared to the 60 km horizontal resolution often required for daytime CATS operational data products. A Convolutional Neural Network (CNN) trained using CATS standard data products also demonstrated the potential for improved cloud-aerosol discrimination compared to the operational CATS algorithms for cloud edges and complex near-surface scenes during daytime.

lidar↗
DOE OSTI2024

Towards a Workforce Roadmap for Distributed Wind: Phase 1 - Identifying Needs and Barriers

Despite recent policy, research efforts, and resources available for utility-scale and offshore wind workforce development, the distributed wind (DW) industry has yet to make similar advances to address its workforce challenges. This report initiates the phased development of a DW workforce roadmap to provide a foundation for roadmap development. Phase 1, contained in this report, uses desk-based research on clean energy workforce approaches and a DW interested-party survey to discuss needs and barriers hindering the workforce from expanding. Findings are summarized into goals and solutions for Phase 2 of roadmap development, which identifies actors responsible for implementing solutions identified in Phase 1. Phase 1 results suggest that the sector's small size and limited growth motivate the short-term need for skilled workers or candidates with well-rounded and multifaceted abilities. Long-term expansion plans must diversify positions while capitalizing on existing utility-scale wind and offshore workforce efforts, as well as other renewable sector best practices where possible. The findings in this report can advance workforce development in the DW sector by aligning interested industry parties around common goals to address challenges. Training providers, installers, operators, manufacturers, federal agencies, national laboratories, academic partners, and labor unions can utilize the findings to help promote sustainable growth of the DW sector.

17 WIND ENERGY↗
DOE OSTI2025

Data efficiency assessment of generative adversarial networks in energy applications

This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performance when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Wyandotte Integrated Renewable Energy Strategy (WIRES 2) (Final Technical Report)

Wyandotte Municipal Services (WMS), a Michigan Municipal Utility offering electric generation, transmission & distribution, water filtration & distribution and Broadband/Video sought to deploy a set of renewable energy projects for their Electric Utility that contributed to reducing the City’s environmental and energy impact, provided examples that would encourage businesses and citizens to adopt cleaner energy practices and help WMS meet the required renewable energy standards of the State of Michigan (10% in 2015, 15% in 2021). WMS generates and delivers roughly 280,000 megawatt hours (MWh) of electricity annually to more than 10,000 homes and 1,000 businesses within the City of Wyandotte. The Wyandotte Integrated Renewable Energy Strategy – WIRES 2 resulted in deployment of a set of community-scale micro-wind turbines, evaluation and installation of energy-efficient and low-maintenance light-emitting diode (LED) street lights and park lights in highly visible locations in the City and expansion of the geothermal heating and cooling district that already included residential geothermal systems, to include larger scale business/institutional systems at the Utility’s largest electric customer and at the City Library. Finally, WMS identified the need for job training in energy efficiency and renewable energy technologies to further develop a local skilled workforce in these areas. Partially funded by the grant, the wind turbine project provides a benchmark for WMS, local businesses and residents in the evaluation of utility-scale wind v. micro-wind in an urban environment as a renewable energy strategy. Also partially funded by the grant, the LED project benefited the City of Wyandotte by reducing load on the electric system for the public utility but also reduced City costs for streetlighting, parking lot lighting and park lighting without a compromise in security. The project also resulted in a visual success that has led to additional approvals for non-Grant related LED lighting installations resulting in further reduction in the electric load in the City. Commercial Geothermal installations resulted in the Utility being able to eliminate steam customers who formerly utilized the byproduct of steam from WMS electric production. Due to the reduction in natural gas prices and the overall reduction in market purchased power, it was no longer feasible for WMS to operate its Power Plant as a base load plant and to only operate on a market dispatch philosophy when market prices dictated that WMS could produce electricity cheaper than the market purchase price. This has resulted in fewer operating days for the WMS Power Plant, resulting in less environmental impact. WMS has now completely exited the steam business and the ability to offer a geothermal option to two (2) former steam customers (BASF-Wyandotte and the Bacon Memorial Library) allowed for that. In addition, peak loads have been shaved for these two (2) large customers due to the consistent temperature offered by geothermal heating and cooling, reducing the swings associated with thermostat changes caused by outside temperature changes during extreme high and low temperatures. Finally, energy efficiency and renewable energy college-level classes at Wayne County Community College allowed a group of interested students to pursue studies in those technologies through grant provided tuition, books and course materials. This effort provided a foundation of potential future employees not only for WMS but other energy efficiency/renewable energy employers such as Franklin Energy, a partner with WMS in energy optimization efforts with Wyandotte businesses.

17 WIND ENERGY↗
DOE OSTI2023

Hierarchical Data-Driven Protection for Microgrid with 100% Renewable Penetration: Preprint

The accurate detection and isolation of faults is critical for the reliable operation of microgrids (MGs). Traditional protection approaches are even more challenged for 100% renewable MGs because inverter-based resources (IBRs) are the only sources for fault current which are usually low and unpredictable/non-uniform. This calls for new protection scheme that can identify IBR fault responses and detect faults in MGs. Data-driven based protection can learn the pattern of IBR fault responses and make the correct decision to identify faults. Therefore, this paper presents a data-driven approach for fault localization in island MGs. The approach builds a training dataset of comprehensive fault scenarios that can be used to learn fault characteristics from processed measurements. The localization task is modeled as a binary classification problem at each relay, which simplifies the learning process. Then, a hierarchical decision mechanism is used to identify the fault location. The proposed approach is assessed using an exemplary MG with several grid-forming (GFM) and grid-following (GFL) inverters, where accurate estimation of fault location is achieved. The data-driven based protection approach developed in this paper provides a generic framework and useful guidance for power system protection engineers to achieve reliable protection for MGs with 100% renewables.

artificial intelligence↗
DOE OSTI2021

DOE Award No.: DE-FE0023919 Phase 4 Scientific/Technical Report

This is the Phase 4 Report for the ‘Deepwater Methane Hydrate Characterization and Scientific Assessment or Genesis of Methane Hydrates in the Gulf of Mexico (GOM2)’ research project (DOE Award No. DE-FE0023919). The report summarizes activities from October 1, 2019 to September 30, 2020. The project is led by the University of Texas at Austin (UT). The project objective is to gain insight into the nature, formation, occurrence and physical properties of methane hydrate-bearing sediments for the purpose of methane hydrate resource appraisal through the planning and execution of drilling, coring, logging, testing and analytical activities that assess the geologic occurrence, regional context, and characteristics of marine methane hydrate deposits in the Gulf of Mexico outer continental shelf (OCS). We published a dedicated American Association of Petroleum Geologists Bulletin volume describing initial results from the UT-GOM2-1 expedition in Sept. 2020. This is part 1 of a multi-volume commitment by AAPG to this project. We further confirmed that the natural gas in hydrate at GC-955 was formed by primary microbial processes (>76.1 %). The in-situ effective permeability hydrate-bearing sandy silts at the GC-955 reservoir ranges from 0.1 md (1.0×10-16 m2) to 2.4 md (2.4×10-15m2) in cores with 83% to 93% hydrate saturation. The intrinsic permeability (the single phase permeability) is estimated from reconstituted samples to be ~12 md (1.2×10-14 m2) to ~41 md (4.1×10-14 m2). We used observation and models to interpret that the core degradation that is found in pressure cores is due to dissociation of the methane hydrate in the outer circumference of the core and dissolution of that methane into the fresh pore water that the core is stored with. We are designing approaches to minimize this core loss in the future. We spent an enormous amount of effort to further improve the ability of the pressure coring tool (the PCTB) to pressure seal correctly. We completed upgrading the upper section of the PCTB to address poor pressure. We successful tested the modifications at Geotek’s test facility in Salt Lake City (Bench Test II). We completed a Land Test of the PCTB at the Schlumberger Cameron Test and Training Facility (CTTF). The tool did not seal in 6 out of 7 tests and we clearly demonstrated that cuttings were wedging in the ball valve assembly, keeping the ball valve from sealing. We reproduced the failure mechanism observed during the land test at Salt Lake City and confirmed the sensitivity of the ball valve assembly to grit. Geotek designed and tested 9 modifications to address this issue and the PCTB is now 100% successfully sealing in the presence of grit. Our science expedition is scheduled for spring 2022 and we are fully focused on preparing for this. UT and Ohio State completed a Shallow Hazard Assessment report for each proposed UT-GOM2-2 drilling location, pursuant to 30 CFR 250.214(f) and 250.244 (f). The Shallow Hazard Reports will accompany the UT-GOM2-2 Exploration Plan that is submitted to BOEM, and completes the geological and geophysical analysis for UT-GOM2-2 permitting efforts. We updated the UT-GOM2-2 Operations Plan (Version 1). We completed the UT-GOM2-2 Science and Sample Distribution Plan (Version 1). We evaluated the scope, budget, and schedule that would result from using a commercial vessel. We developed detailed drilling schedule, mud volume, and resource estimates. We developed a vessel specification document and a well plan, and sent these documents to prospective vessel contractors.

03 NATURAL GAS↗
DOE OSTI2022

A Fast and Accurate Transient Stability Assessment Method Based on Deep Learning: WECC Case Study

Transient stability is one of the critical aspects of power system stability assessment. The increasing integration of inverter-based resources and the retirement of conventional synchronous generators result in the decreasing system inertia and growing complexity of system operating conditions. Using a few selected typical operating conditions cannot guarantee system transient stability in all operating conditions, and the time-domain simulation of all operating conditions requires tremendous time and is often infeasible. This paper proposes a more efficient transient stability assessment method based on deep learning. The binary search method is used to determine the critical clearing time (CCT) in creating training databased by time-domain simulation. This method is fast and accurate with 1 ms resolution. The buses whose CCTs are lower than 200 ms are considered critical buses. Buses close to each other are grouped based on their mutual admittance matrix to reduce the search space of the critical buses. This paper also proposes the generator feature normalization based on the physical model. Case study on the reduced 240-bus WECC system model demonstrates that the proposed method can predict CCT accurately and efficiently.

critical clearing time↗
DOE OSTI2024

NSA Site Science: Use of ARM Observations from Northern Alaska to Evaluate and Improve Prediction Capabilities

The Arctic is warming at a rate nearly double that of the rest of the planet, leading to profound changes in atmospheric, oceanic, and ice processes. The U.S. Department of Energy's (DOE) Atmospheric Radiation Measurement (ARM) user facility has played a significant role in Arctic research, operating observatories in Alaska's North Slope for over 25 years. These observatories provide a rich, and wide-reaching dataset that offers insight into atmospheric processes in northern Alaska. This report details the results of a nine-year research project (2015–2024) supported by the DOE Atmospheric Systems Research (ASR) program, that leverages data from ARM’s deployment of observing facilities at Utqiaġvik (known as the North Slope of Alaska, or NSA, site) and Oliktok Point, Alaska. The project was conducted in two phases: - Phase 1 (2015–2019): Focused on understanding key atmospheric processes at Oliktok Point, including cloud formation, high-latitude precipitation, aerosol-cloud interactions, and cloud properties. - Phase 2 (2019–2024): Extended the research to the broader North Slope region, using data from both Oliktok Point and Utqiaġvik. Topics explored included surface energy budgets, atmospheric stability, ice nucleation processes, and microphysics in Arctic clouds. The project resulted in numerous research products, including 50 peer-reviewed publications and dissertations, 169 presentations, and 10 data products. These products cover a variety of topics, including: - Cloud Macro- and Microphysical Properties: Arctic clouds play a crucial role in energy transfer, and accurate representation in models is critical. The study explored cloud transitions, ice crystal shapes, and dual-wavelength radar data to understand ice crystal habits and size distributions. - Aerosol Properties and Processes: The team examined aerosol sources in the Arctic, including industrial emissions and natural sources. Observations showed significant spatial gradients in aerosol concentrations due to human activities and wildfire smoke. The influence of aerosols on cloud formation and the surface energy budget was also assessed. - Aerosol-Cloud Interactions: Research revealed that aerosols might suppress cloud ice production, affecting cloud radiative forcing and precipitation. The impact of local industrial emissions on cloud properties was also investigated. - Contextualizing the North Slope of Alaska in the context of the broader Arctic: To understand broader trends, the project evaluated large-scale circulation patterns and the influence of weather systems on the Arctic. Studies indicated that large-scale processes play a significant role in temperature patterns and the timing of snowmelt. - Advancing ARM Observational and Modeling Capabilities: The project developed new radar data products and advanced measurement techniques, including clutter mitigation and drizzle detection. Uncrewed aerial systems (UAS) and tethered balloon systems (TBS) were deployed to gather detailed atmospheric data. Additionally, the project supported 10 early career scientists, providing training and mentorship to undergraduate interns, graduate students, postdoctoral researchers, and early career researchers. These efforts contributed to the advancement of ARM research capabilities and fostered a new generation of scientists skilled in Arctic atmospheric research. Ultimately, this ASR-supported project has provided valuable insights into Arctic atmospheric processes and their broader climate implications. Recommendations for future work include continuing support for long-term observing at Arctic locations to foster additional research, further exploration of aerosol-cloud interactions and the potential impacts of enhanced industrialization of the Arctic, and expanded use of uncrewed systems to gather data in this remote and harsh environment. Additionally, the data products developed by this work, and the data products developed through the ARM infrastructure, leave a treasure-trove of additional information that should be explored for many years to come to gain additional insight into physical processes in the Arctic atmosphere that drive the rapid changes occurring in at high latitudes and their global impact.

58 GEOSCIENCES↗
DOE OSTI2024

A Full-Stack Exploration of Language-Based Parallelism in Fortran 2023

This poster explores native parallel features in Fortran 2023 through the lens of supporting applications with libraries, compilers, and parallel runtimes. The language revision informally named Fortran 2008 introduced parallelism in the form of Single Program Multiple Data (SPMD) execution with two broad feature sets: (1) loop-level parallelism via do concurrent and (2) a Partitioned Global Address Space (PGAS) comprised of distributed “coarray” data structures. Fortran’s native parallelism has demonstrated high performance [1] and reduced the burden of inserting what sometimes amounts to more directives than code. Several compilers support both feature sets, typically by translating do concurrent into serial do loops annotated by parallel directives and by translating SPMD/PGAS features into direct calls to a communication library. Our research focuses primarily on two questions: (1) can the compiler’s parallel runtime library be developed in the language being compiled (Fortran) and (2) can we define an interface to the runtime that liberates compilers from being hardwired to one runtime and vice versa. We are answering these questions by developing the Parallel Runtime Interface for Fortran (PRIF) [2] and the Co-Array Fortran Framework of Efficient Interfaces to Network Environments (Caffeine) [3]. Caffeine is initially targeting adoption by LLVM Flang, a new open-source Fortran compiler developed by a broad community in industry, academia, and government labs. We are also exploring the use of these features in Inference-Engine, a deep learning library designed to facilitate neural network training and inference for high-performance computing applications written in modern Fortran.

Rasmussen, Katherine↗
DOE OSTI2026

A Parametric Reduced-Order Model for Inverter Short-Circuit Response in Protection Studies

This paper presents a reduced-order model (ROM) for grid-following (GFL) inverters that reproduces inverter fault current trajectories, including sub transients, transient, and steady-state phases, across a range of fault types, locations, and pre-fault operating points. . The proposed model is developed by: Constructing the positive- and negative-sequence current with parameterization fitted by large data training and fitting Validating using EMT simulation against EMT full model and demonstrating the ROM's capability to capture fault current magnitude, phase angle, and oscillatory transients. Building a standard EMT simulation platform library component for easy configuration and application.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Scalable and Energy-Efficient Methods for Interactive Exploration of Scientific Data

The main scientific contributions of this project are the following novel concepts for multidimensional arrays: shape-based similarity join (SIGMOD 2016), incremental view maintenance (SIGMOD 2017), user-defined stencil functions (HPDC 2017), and distributed caching for in-situ processing (SSDBM 2018). Building on our collaboration with the astrophysics group at LBNL, we applied these techniques to the data generated in the Palomar Transient Factory (PTF) astronomical survey. They played a pivotal role in the first-ever observation of a neutron star merger, which produces gravitational waves and turns out to be the origin of heavy elements, including gold. This has lead to a Science magazine article that has received extensive media coverage on ACM TechNews, Slashdot, FiveThirtyEight, and Quanta Magazine, among others. Additionally, two other articles detailing related aspects of the same discovery have been published in the Astrophysical Journal Letters journal. These publications have more than 3,000 citations according to Google Scholar (as of February 2022). This cross-disciplinary collaboration provided very good opportunities to apply database techniques to real-life scientific problems. The fact that they facilitated major discoveries in astrophysics proves the importance of our research. In addition to the work on multidimensional array databases, this project has also developed stochastic gradient descent (SGD) optimization algorithms for training large scale machine learning models, methods for querying in-situ data, and a database query optimizer based on sketch synopses.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Using containers to speed up development, to run integration tests and to teach about distributed systems

GlideinWMS is a workload manager provisioning resources for many experiments including CMS and DUNE. The software is distributed both as native packages and specialized production containers. Following an approach used in other communities like web development we built our workspaces, system-like containers to ease development and testing. Developers can change the source tree or check out a different branch and quickly reconfigure the services to see the effect of their changes. In this paper, we’ll talk about what differentiates workspaces from other containers. We’ll describe our base system composed of three containers. A one-node cluster including a compute element and a batch system. A GlideinWMS Factory controlling pilot jobs. And a scheduler and Frontend, to submit jobs and provision resources. Additional containers can be used for optional components. This system can easily run on a laptop and we’ll share our evaluation of different container runtimes, with an eye for ease of use and performance. Finally, we’ll talk about our experience as developers and with students. The GlideinWMS workspaces are easily integrated with IDEs like VS Code, simplifying debugging and allowing development and testing of the system also when offline. They simplified the training and onboarding of new team members and Summer interns. And they were useful in workshops where students could have first-hand experience with the mechanisms and components that, in production, run millions of jobs.

Mambelli, Marco↗
DOE OSTI2025

Using Containers to Speed Up Development, to Run Integration Tests and to Teach About Distributed Systems

GlideinWMS is a workload manager provisioning resources for many experiments, including CMS and DUNE. The software is distributed both as native packages and specialized production containers. Following an approach used in other communities like web development, we built our workspaces, system-like containers to ease development and testing. Developers can change the source tree or check out a different branch and quickly reconfigure the services to see the effect of their changes. In this paper, we will talk about what differentiates workspaces from other containers. We will describe our base system, composed of three containers: a one-node cluster including a compute element and a batch system, a GlideinWMS Factory controlling pilot jobs, and a scheduler and Frontend to submit jobs and provision resources. Additional containers can be used for optional components. This system can easily run on a laptop, and we will share our evaluation of different container runtimes, with an eye for ease of use and performance. Finally, we will talk about our experience as developers and with students. The GlideinWMS workspaces are easily integrated with IDEs like VS Code, simplifying debugging and allowing development and testing of the system even when offline. They simplified the training and onboarding of new team members and summer interns. And they were useful in workshops where students could have first-hand experience with the mechanisms and components that, in production, run millions of jobs.

Mambelli, Marco [Fermilab] (ORCID:0000000294892681↗
NASA NTRS2016

Patterns of Activity in A Global Model of A Solar Active Region

In this work we investigate the global activity patterns predicted from a model active region heated by distributions of nanoflares that have a range of frequencies. What differs is the average frequency of the distributions. The activity patterns are manifested in time lag maps of narrow-band instrument channel pairs. We combine hydrodynamic and forward modeling codes with a magnetic field extrapolation to create a model active region and apply the time lag method to synthetic observations. Our aim is not to reproduce a particular set of observations in detail, but to recover some typical properties and patterns observed in active regions. Our key findings are the following. (1) Cooling dominates the time lag signature and the time lags between the channel pairs are generally consistent with observed values. (2) Shorter coronal loops in the core cool more quickly than longer loops at the periphery. (3) All channel pairs show zero time lag when the line of sight passes through coronal loop footpoints. (4) There is strong evidence that plasma must be re-energized on a timescale comparable to the cooling timescale to reproduce the observed coronal activity, but it is likely that a relatively broad spectrum of heating frequencies are operating across active regions. (5) Due to their highly dynamic nature, we find nanoflare trains produce zero time lags along entire flux tubes in our model active region that are seen between the same channel pairs in observed active regions.

Bradshaw, S. J.↗
DOE OSTI2021

Unbundling Smart Meter Services Through Spatio-Temporal Decomposition Agents in DER-rich Environment

Smart meters and the advanced metering infrastructure (AMI) facilitate distribution system operators (DSOs) to gather information on energy consumption at the customer level. With the increasing penetration of building-level intermittent distributed energy resources (DERs) behind the meter, DER information is not available to DSOs. At the same time, smart meter enables users to participate in grid, with real-time information. Information for behind the meter is needed by user to coordinate building level assets for maximum benefits. The concept of unbundled smart meter (USM) needs agents to decompose smart meter measurements to provide service to DSO as well as customers. In this paper, we propose a Spatio-Temporal Decomposition Agent (STDA) for USM based on Artificial Intelligence (AI). STDA can help users optimize their energy usage, help DSO to utilize building assets for the grid operation. The energy usage strategy developed by STDA is suitable for different users, and can be customized by deep learning (DL) models according to the different energy consumption habits of each user. The power prediction performance results of various DL models and evaluation using a set of data from a Hawaii utility is presented. Furthermore, STDA integration with Home Energy management Systems (HEMS) to manage resources is presented and validated. STDA pre-processes the measurements before model training, and provides the spatio-temporal decomposed forecasting.

42 ENGINEERING↗
DOE OSTI2020

Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning

Nowadays, data generated by large-scale scientific experiments are on the scale of petabytes per month. These data are transferred through dedicated high-bandwidth networks across distributed collaboration sites for processing, storage, and analysis. Like general purpose networks, research networks experience attacks. However, monitoring traffic in such high-bandwidth network environments is challenging with conventional deep packet inspection (DPI)- based network intrusion detection systems (NIDS). Recently, machine learning (ML) algorithms have shown potential in detecting anomalous patterns with better generalizability and faster speed. Compared to the general purpose networks, traffic movement in research network is less volatile and more likely to benefit from the ML-based anomaly analysis. We present ThunderSecure, an efficient AI-powered system for detecting anomalies in 100G research networks. ThunderSecure implements a high-throughput packet processing infrastructure using multi-cores and GPUs. It takes time-series statistics from a variety of network measurements and uses 2D Convolutional Neural Network (CNN) to explore both spatial and temporal dependencies in network data stream. Patterns of science data traffic are learned with a one-class neural network, which blends an Adversarial Autoencoder (AAE) with Gaussian mixture density estimation. Testing traffic flows exhibiting significant deviations from the learned baseline of normality are marked as anomalies. We trained ThunderSecure on hundreds of billions of science data packets recorded from a 100G research network at Fermi National Accelerator Laboratory. The detection performance was evaluated on traffic captured from the same research network days and weeks after the training with different types of attack flows injected. To the best of our knowledge, this is the first ML work in the area of network anomaly detection that has been validated on such extreme scale datasets. Results show that ThunderSecure can recognize science data traffic that are captured long after the training and make nearly certain detection on those with anomalous flows injected, even in the case when the anomaly-to-normal mixing ratio is 0.1%.

Gong, Qian↗
DOE OSTI2023

Machine Learning in Power System Operations: Training Data

Reliability and stability of the electric grid today has depended upon operations of the grid which include the protective relay. Today, the electricity sector faces new challenges with the shift of generation resource characteristics away from the traditional “big iron” generation to inverter-based resources (IBR) which shift the physics and assumption used in grid operation and protection. These changing conditions represent new challenges for protective relays (identification of faults) and increased challenges for protection engineers (correct settings and configuration, reduction of mis-operations), both issues recognized in research and industry. Finding new approaches to reduce mis-operations in relaying and new approaches to fault identification is critical to grid operations. Using today’s modern technology of embedded systems, edge computing, machine learning (ML), and communications we can help address challenges and augment and improve on existing power system operations methodologies.

24 POWER TRANSMISSION AND DISTRIBUTION↗