Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “LEARNING SYSTEM”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Learning Management System User Requirements for the National Nuclear Security Administration's International Nuclear Safeguards Engagement Program

The National Nuclear Security Administration's (NNSA) International Nuclear Safeguards Engagement Program (INSEP) is considering investing in new tools that would allow the program to support its partner states from a distance. At the same time, the program is considering approaches that would allow several organizations, including NNSA, IAEA, national laboratories and contractor staff, to collaborate in the development and maintenance of instructional content. Software systems known as Learning Management Systems (LMSs) might represent a mechanism through which INSEP could accomplish these goals (collaborative development and remote support). To assess the usefulness of an LMS, INSEP has specified its needs for delivering online training and compared those needs to the capability of a range of LMSs. This comparison will allow INSEP to determine whether an LMS would be a useful tool and may set the stage for a "make-buy" decision in the future. The study team concluded that INSEP's content development and delivery needs align well with the capabilities of the leading LMSs on the market today and that that INSEP performance requirements allow for a customized approach using existing training portals that are already available to NNSA. Additional work would be required to specify the desired processes for developing online training and outreach materials, structuring the databases, specifying the data that should be collected, and detailing the desired system reports and documentation.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Consumer Guide to Small Wind Energy Systems

Learn how to use a small wind energy system to produce electricity to power your home. This fact sheet from Energy Saver includes information on how small wind energy systems can work for homes and how to determine whether your site is a good candidate for a small wind turbine.

small wind energy system, wind turbine, Energy Sav↗
DOE OSTI2020

MARBLE: A Multi-GPU Aware Job Scheduler for Deep Learning on HPC Systems

Deep learning (DL) has become a key tool for solving complex scientific problems. However, managing the multi-dimensional large-scale data associated with DL, especially atop extant multiple graphics processing units (GPUs) in modern supercomputers poses significant challenges. Moreover, the latest high-performance computing (HPC) architectures bring different performance trends in training throughput compared to the existing studies. Existing DL optimizations such as larger batch size and GPU locality-aware scheduling have little effect on improving DL training throughput performance due to fast CPU-to-GPU connections. Additionally, DL training on multiple GPUs scales sublinearly. Thus, simply adding more GPUs to a system is ineffective. To this end, we design MARBLE, a first-of-its-kind job scheduler, which considers the non-linear scalability of GPUs at the intra-node level to schedule an appropriate number of GPUs per node for a job. By sharing the GPU resources on a node with multiple DL jobs, MARBLE avoids low GPU utilization in current multi-GPU DL training on HPC systems. Our comprehensive evaluation in the Summit supercomputer shows that MARBLE is able to improve DL training performance by up to 48.3% compared to the popular Platform Load Sharing Facility (LSF) scheduler. Compared to the state-of-the-art of DL scheduler, Optimus, MARBLE reduces the job completion time by up to 47%.

Han, Jingoo↗
DOE OSTI2021

Machine Learning Reduced Order Model for Cost and Emission Assessment of a Pyrolysis System

Biomass pyrolysis is a promising approach for producing economic and environmentally-friendly fuels and bioproducts. Biomass pyrolysis experiments show that feedstock properties have a significant impact on product yields and composition. Scientists are developing detailed chemical reaction mechanisms to capture the relationships between biomass composition and pyrolysis yields. These mechanisms can be computationally intensive. In this study, we investigate the use of a machine learning reduced order model (ROM) for assessing the costs and emissions of a pyrolysis biorefinery. Here, we developed a Kriging-based ROM to predict pyrolysis yields of 314 feedstock samples based on the results of a detailed chemical kinetic pyrolysis mechanism. The ROM is integrated into a chemical process model for calculating mass and energy yields in a commercial-scale (2000 tonne/day) biorefinery. The ROM estimated biofuel yields of 65 to 130 gallons per ton of dry biomass. This results in biofuel minimum fuel-selling prices of $2.62 to $5.43 per gallon and emissions of -13.62 to 145 kg of CO 2 per MJ. The ROM achieved an average mean square error of 1.8e-20 and a mean absolute error of 0.53%. These results suggest that ROMs can facilitate rapid feedstock screening for biorefinery systems.

09 BIOMASS FUELS↗
DOE OSTI2025

Grey-Box System Identification of Grid-Forming Inverters

This paper demonstrates the use of grey-box system identification methods for simplifying and understanding the nonlinear power dynamics of grid-forming inverters (GFMs). The power and frequency outputs of complex high-order GFM models are fed into system identification software in order to fit them to a predetermined LTI system and learn system parameters such as (synthetic) inertia and droop constants. The same process is then run for a high-order synchronous generator model, and the outputs are fit to the same set of LTI equations. Simulation of a network of GFM inverters with diverse control architecture is also performed for the same process. The intent is threefold: first, to demonstrate the appropriateness of unified LTI models for describing the power and frequency dynamics of individual resources and connected networks, in order to facilitate analysis of larger heterogeneous networked systems; second, to discover the relationship between internal control parameters of GFMs and their externally observed values; and third, to validate that grey-box data-driven system identification techniques can be a valuable tool to discover the values of important parameters in the absence of explicit vendor models.

analytical models↗
DOE OSTI2024

Computer program product for classifying materials

Systems and methods for classifying materials utilizing one or more sensor systems, which may implement a machine learning system in order to identify or classify each of the materials, which may then be sorted into separate groups based on such an identification or classification. The machine learning system may utilize a neural network, and be previously trained to recognize and classify certain types of materials.

Kumar, Nalin↗
DOE OSTI2022

Quantum model learning agent: characterisation of quantum systems through machine learning

Accurate models of real quantum systems are important for investigating their behaviour, yet are difficult to distil empirically. Here, we report an algorithm—the quantum model learning agent (QMLA)—to reverse engineer Hamiltonian descriptions of a target system. We test the performance of QMLA on a number of simulated experiments, demonstrating several mechanisms for the design of candidate Hamiltonian models and simultaneously entertaining numerous hypotheses about the nature of the physical interactions governing the system under study. QMLA is shown to identify the true model in the majority of instances, when provided with limited a priori information, and control of the experimental setup. Our protocol can explore Ising, Heisenberg and Hubbard families of models in parallel, reliably identifying the family which best describes the system dynamics. We demonstrate QMLA operating on large model spaces by incorporating a genetic algorithm to formulate new hypothetical models. The selection of models whose features propagate to the next generation is based upon an objective function inspired by the Elo rating scheme, typically used to rate competitors in games such as chess and football. In all instances, our protocol finds models that exhibit F 1 score ≥ 0.88 when compared with the true model, and it precisely identifies the true model in 72% of cases, whilst exploring a space of over 250 000 potential models. By testing which interactions actually occur in the target system, QMLA is a viable tool for both the exploration of fundamental physics and the characterisation and calibration of quantum devices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Technoeconomic Analysis of Nuclear-Renewable Hybrid Energy Systems - Opportunities, Learnings, and Challenges

Tightly coupled nuclear-renewable hybrid energy systems (N-R HESs) are designed to both generate dispatchable electricity and produce at least one industrial product from nuclear and renewable energy sources. This presentation summarizes findings from NREL's technoeonomic assessment of several N-R HES configurations. It summarizes key conclusions and communicates the next steps in NREL's work on these technologies.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2022

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems: Preprint

We present the PowerGridworld software package to provide users with a light-weight, modular, and customizable framework for creating power systems-focused, multi-agent gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). While many frameworks exist for training multi-agent (MA) RL policies, none exist to rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning multi-agent RL policies using both OpenAI's MADDPG and RLLib's PPO algorithms where, in both cases, at least some subset of agents incorporate elements of the power flow solution at each time step as part of their reward (negative cost) structures.

MATHEMATICS AND COMPUTING↗
DOE OSTI2020

DLHub: Simplifying publication, discovery, and use of machine learning models in science

Machine Learning (ML) has become a critical tool enabling new methods of analysis and driving deeper understanding of phenomena across scientific disciplines. There is a growing need for "learning systems" to support various phases in the ML lifecycle. While others have focused on supporting model development, training, and inference, few have focused on the unique challenges inherent in science, such as the need to publish and share models and to serve them on a range of available computing resources. In this paper, we present the Data and Learning Hub for science (DLHub), a learning system designed to support these use cases. Specifically, DLHub enables publication of models, with descriptive metadata, persistent identifiers, and flexible access control. It packages arbitrary models into portable servable containers, and enables low-latency, distributed serving of these models on heterogeneous compute resources. In this work, we show that DLHub supports low-latency model inference comparable to other model serving systems including TensorFlow Serving, SageMaker, and Clipper, and improved performance, by up to 95%, with batching and memoization enabled. We also show that DLHub can scale to concurrently serve models on 500 containers. Finally, we describe five case studies that highlight the use of DLHub for scientific applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Achieving Cyber-Resilience for Power Systems using a Learning, Model-Assisted Blockchain Framework

The secure integration and management of distributed energy resources (DER) and power aggregators in the electric grid requires secure communications and a physics-aware Command and Control (C2) strategy. A Blockchain (BC)-based overlay network was developed to provide a security layer for the existing power grid network that mitigates risks in current and legacy network and C2 protocols. By integrating a Model-Assisted Machine Learning (MAML) framework with a Secure Blockchain Overlay Network (SBON) a defense-in-depth strategy was achieved. In our approach, the MAML framework leveraged a smart contract framework to gather network data and learn the dynamics of DER to develop detection strategies for attacks targeting sensors and actuators used by DER. The MAML framework learned dynamical systems models for individual DERs to detect sensor attacks. For DER we utilized a Digital Twin (DT) to accelerate the learning process for a model resistant to stealthy attacks. The project created DT for PV inverters and BESS. The DTs were coupled with a model-assisted, data-driven learning of DER behavior. Specifically, we evaluated architectures for model-based learning with model-free fine-tuning. Additionally, differential privacy techniques were used to obfuscate data, while still allowing the computation of attack detection results based on obfuscated data. The SBON developed leverages a private permissioned blockchain network orchestrated with the Hyperledger Fabric framework. To connect the cyber world, which orchestrates the blockchain fabric, and the physical world where the power network resides, we developed a system implementation to enable the secure interaction of the physical world and the abstracted blockchain.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Artificial Intelligence and Machine Learning Applications in Modern Power Systems

Machine learning (ML) and artificial intelligence (AI) algorithms offer valuable tools for the analysis and interpretation of large datasets. These tools have the capability to uncover insights that may not be readily apparent within these datasets. In recent years, the integration of ML and AI has become increasingly prevalent in various applications within the power system domain. One of the earliest instances of machine learning in power systems can be traced back to demand forecasting, where artificial neural networks were employed for short-term load forecasting. In contemporary power systems, an abundance of high-resolution geospatial and temporal data is generated at various time intervals, ranging from sub-seconds (Phasor Measurement Units or PMUs) to seconds (Supervisory Control and Data Acquisition or SCADA), minutes (Process Information or PI), and extending to days, months, and years. These datasets contain valuable information concerning system reliability and performance. This information holds the potential to offer critical insights into system operations, as well as solutions for predicting and mitigating contingencies to prevent cascading outages. Despite the immense power of machine learning tools, system operators, planners, and utilities often exhibit hesitancy in fully embracing AI-enabled system operations and planning. This cautious approach persists, even as numerous diverse applications of machine learning continue to emerge in the realm of power systems. In this chapter, our focus will delve deep into ML and AI applications tailored for power systems. These applications aim to furnish system operators with enhanced situational awareness and augment their decision-making capabilities, especially during challenging operating conditions. Specific areas of interest encompass root cause analyses of electricity market datasets and the strategic selection of representative samples from vast power system databases for training ML/AI models. Finally, the chapter will conclude with a short discussion on the future of ML/AI in power systems and possible directions that the industry is moving towards.

power system applications, machine learning (ML), ↗
DOE OSTI2022

Generative memory for lifelong machine learning

Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.

Nadamuni Raghavan, Aswin↗
DOE OSTI2019

On the Susceptibility of Deep Neural Networks to Natural Perturbations

Deep learning systems are increasingly being adopted for safety critical tasks such as autonomous driving. These systems can be exposed to adverse weather conditions such as fog, rain and snow. Vulnerability of deep learning systems to synthetic adversarial attacks has been extensively studied and demonstrated, but the impact of natural weather conditions on these systems has not been studied in detail. In this paper, we study the effects of fog on classification accuracy of the popular Inception deep learning model. We use stereo images from the Cityscapes dataset and computer graphics techniques to mimic realistic naturally occurring fog. We show that the Inception deep learning model is vulnerable to the addition of fog in images.

Ozdag, Mesut↗
DOE OSTI2020

Using Machine Learning to Identify Optimum Prospects for Offshore Geologic CO 2 Storage and Enhanced Oil Recovery in the Gulf of Mexico

The SECARB Offshore Partnership is a government-industry partnership focused on assembling the knowledge base required for secure, long-term, large-scale CO 2 subsea storage in saline formations and mature oil reservoirs. The SECARB Offshore Partnership is evaluating potential storage opportunities in the Central and Eastern planning areas of the outer continental shelf (OCS) of the Gulf of Mexico. The evaluation focuses on active and depleted oil and gas fields and potentially associated CO 2 -enhanced oil recovery (CO 2 -EOR), as well as, deep saline storage resources. As part of Subtask 3.0 (Offshore Storage Resources Characterization) and Subtask 4.0 (Risk Assessment, Simulation, and Modeling), Oklahoma State University (OSU) is developing a machine learning system that employs the SAS Institute’s Viya platform with visual data mining and machine learning to identify and characterize optimum prospects for enhanced oil recovery and stacked storage in saline reservoirs. This report summarizes this effort to date and discusses the many variables that can be used to characterize these storage objectives, as well as, the design vision of the Viya machine learning system.

02 PETROLEUM↗
DOE OSTI2023

Machine Learning Based System for Automated Estimation of Crystal Unit Cell Parameters from X-ray Diffraction Powder Patterns (MLCell) v0.1

This software uses machine learning models to perform inference on X-ray diffraction powder patterns, output from a diffractometer, to estimate all 6 unit cell parameters of crystalline lattices. Novel aspects of this software originated from the incorporation of concepts from crystallography to an ML-based approach; The resulting method achieves new performance capabilities without significant loss of accuracy and with less computationally intensive models.

Oklejas, Vanessa↗
DOE OSTI2019

Scalable Deep Learning via I/O Analysis and Optimization

Scalable deep neural network training has been gaining prominence because of the increasing importance of deep learning in a multitude of scientific and commercial domains. Consequently, a number of researchers have investigated techniques to optimize deep learning systems. Much of the prior work has focused on runtime and algorithmic enhancements to optimize the computation and communication. Despite these enhancements, however, deep learning systems still suffer from scalability limitations, particularly with respect to data I/O. This situation is especially true for training models where the computation can be effectively parallelized, leaving I/O as the major bottleneck. In fact, our analysis shows that I/O can take up to 90% of the total training time. Thus, in this article, we first analyze LMDB, the most widely used I/O subsystem of deep learning frameworks, to understand the causes of this I/O inefficiency. Based on our analysis, we propose LMDBIO—an optimized I/O plugin for scalable deep learning. LMDBIO includes six novel optimizations that together address the various shortcomings in existing I/O for deep learning. Lastly, our experimental results show that LMDBIO significantly outperforms LMDB in all cases and improves overall application performance by up to 65-fold on a 9,216-core system.

97 MATHEMATICS AND COMPUTING↗