Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 901 records · Page 50

Empirical Comparison of Machine Learning Approaches for Black-Box Modeling of Power Conversion System Dynamics

Inverter-based resources are key components in modern power systems, but accurately modeling their complex behavior can be challenging. Standard, generic converter models often oversimplify inverter dynamics, leading to significant errors in predicting performance. In this work, we compare several data-driven machine learning (ML) approaches for inverter modeling, performing experiments on power conversion systems, systematically varying input conditions, and recording the resulting voltages and currents. The ML models were then trained on this measured data to capture the inverter's dynamic response and to predict the inverter's output current. A performance comparison between the four ML models under study is conducted, laying the foundation for future work on hardware implementation for real-time inference.

30 DIRECT ENERGY CONVERSION↗

Event Detection and Classification Using Machine Learning Applied to PMU Data for the Western US Power System

Smart grid technology enhances our comprehension and reliability of the power grid, leveraging Phasor Measurement Unit (PMU) data—time-synchronized, high-frequency measurements gathered across the US power grid. This paper employs machine learning techniques to effectively analyze the vast PMU data in Wide Area Monitoring Systems (WAMS) for power grid event detection and classification. Analyzing several months of real-world PMU data, the paper focuses on machine learning for fast, precise event detection and classification, corroborated by utility event logs. Practical challenges like feature extraction, dimensionality reduction, and model selection are addressed. A novel feature yielding improved results is discovered, and a supplementary algorithm for detecting small power grid faults is developed. The final algorithm is validated using a month-long real PMU data set, demonstrating its capability in accurately identifying power grid events in near real-time.

machine learning, event detection, PMU↗

Presentation: Sensor Anomaly Detection for Nuclear Reactor Systems Utilizing Linear Regression and K-Means Unsupervised Machine Learning: An overview of methods and results

This presentation is a culmination of work which has occurred over the course of a 10-week internship. Anomaly detection methods must be both robust enough to detect subtle anomalies yet not so sensitive to report false positives, which would result significant loss of revenue. Methods currently being developed for autonomous systems are often pursuing a Digital Twin method, which will look at the entire system and model it as a whole. This presentation, however, focuses less on direct application to an NPP, rather acting as a proof of concept for the methods developed. For the project, we look to develop methods to analyze steady-state data and report anomalies.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

SECURED: Simulator-Enhanced Control and Understanding of Reactor systems for cyber-Event Defense

The study discusses a learning approach for analyzing cyber-events in reactor systems using integrated hardware and personal computer simulator models. Key points include the rise in cyber-attacks and their sophistication in industrial control systems (ICS), the necessity for awareness, understanding, resource allocation, and preparation to combat these threats, and the digital transformation of old and new nuclear plants, increasing their exposure to cyber threats. It highlights the cyber vulnerabilities of advanced reactor systems, which rely on digital instrumentation and control for operations and safety functions, making them susceptible to cyber-attacks. The approach involves demonstrating reactor system plant ICS cyber-attacks under various operational conditions utilizing tools like simulator models and hardware-based kits. A strategic solution approach tailored to critical infrastructure is emphasized, along with community engagement for public and government support, adopting effective learning approaches, and the preparation for anticipated future challenges. The presentation concludes with a call to action to address challenges, leverage opportunities, and advance through lesson learning in cybersecurity for nuclear energy systems.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

PV Systems Reliability and Outreach

The project purpose was to collaborate with the Electric Power Research Institute (EPRI) to reach out to the photovoltaic (PV) industry to cooperate, collaborate and facilitate establishment and access to PV plant data for use in the Photovoltaic Reliability Operations and Maintenance (PVROM) database. Sandia National Laboratories (SNL) and EPRI conducted this outreach to expand and accelerate the implementation of PVROM by gathering more data for analyzing trends, with a goal of accelerating the adoption of PV systems as a primary power generation source in the United States. SNL and EPRI analyzed the data from the PVROM database to assess industry trends in operations and maintenance (O&M) and develop guidelines for the industry. More specifically, this project was intended to leverage SNL’s expertise in PV plant reliability data collection and analysis, with data sharing partners that own or operate PV systems who wanted to learn about rigorous reliabilitybased data collection to track issues over time and improve O&M activities. The partnership also worked to host multiple workshops as part of the SNL/EPRI PV Systems Symposium to gather industry feedback on O&M process improvement and data standards, and share insights learned from the collaboration between SNL and EPRI in the area of PV system reliability. Additional outreach included multiple ‘expert elicitation’ interviews led by EPRI to gather best practices and paths forward for improving/standardizing PV plant O&M and asset management practices. Technical accomplishments included further development of the PVROM database process, sharing best practices for reliability data collection and improving industry understanding of existing O&M practices, important knowledge, and new and novel techniques for benefitting EPRI utility partners and the broader PV industry. Improved reliability at a PV power plant leads to a lower levelized cost of energy (LCOE), which is reflected most directly in its operating expenses. Electric utilities that utilize PV as a larger share of plants they own and operate are interested in having a high degree of availability or ‘uptime’, similar to other power generation sources in their service area. Having low cost, reliable PV generation can lead to fewer costs that need to be recovered by the utility over the lifetime of the power plant, and less regulatory uncertainty when considering bulk transmission and distribution system reliability. The public and taxpayers benefit by the electric utility passing through lower electricity costs.

14 SOLAR ENERGY↗

A step towards the final frontier: Lessons learned from acceptance testing of the first HPE/Cray EX 3000 system at ORNL

Summary In this article, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800‐node supercomputers, Fawbush and Miller, with access to two independent and identical lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom's Meteorological Office's Unified Model and 4‐dimensional variational data assimilation. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Verónica G.↗

Multi-Agent Safe Policy Learning for Power Management of Networked Microgrids

This paper presents a supervised multi-agent safe policy learning (SMAS-PL) method for optimal power management of networked microgrids (MGs) in distribution systems. While unconstrained reinforcement learning (RL) algorithms are black-box decision models that could fail to satisfy grid operational constraints, our proposed method considers AC power flow equations and other operational limits. Accordingly, the training process employs the gradient information of operational constraints to ensure that the optimal control policy functions generate safe and feasible decisions. Furthermore, we have developed a distributed consensus-based optimization approach to train the agents’ policy functions while maintaining MGs’ privacy and data ownership boundaries. After training, the learned optimal policy functions can be safely used by the MGs to dispatch their local resources, without the need to solve a complex optimization problem from scratch. Lastly, numerical experiments have been devised to verify the performance of the proposed method.

, policy gradient↗

A Step Towards the Final Frontier: Lessons Learned from Acceptance Testing of the First HPE/Cray EX 3000 System at ORNL

In this paper, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800-node supercomputers, Fawbush and Miller, with access to two independent and identical Lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager (HPCM) software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom’s Meteorological Office’s Unified Model (UM) and 4DVAR. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility (OLCF) portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed Lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Veronica↗

Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning

Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real-time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR-GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine-Learning Assessed Rapid Geodetic Earthquake model (M-LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M-LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real-time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes.

58 GEOSCIENCES↗

GraphAlign: Graph-Enabled Machine Learning for Seismic Event Filtering

This report summarizes results from a 2 year effort to improve the current automated seismic event processing system by leveraging machine learning models that can operated over the inherent graph data structure of a seismic sensor network. Specifically, the GraphAlign project seeks to utilize prior information on which stations are more likely to detect signals originating from particular geographic regions to inform event filtering. To date, the GraphAlign team has developed a Graphical Neural Network (GNN) model to filter out false events generated by the Global Associator (GA) algorithm. The algorithm operates directly on waveform data that has been associated to an event by building a variable sized graph of station waveforms nodes with edge relations to an event location node. This builds off of previous work where random forest models were used to do the same task using hand crafted features. The GNN model performance was analyzed using an 8 week IMS/IDC dataset, and it was demonstrated that the GNN outperforms the random forest baseline. We provide additional error analysis of which events the GNN model performs well and poorly against concluded by future directions for improvements.

58 GEOSCIENCES↗

Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systems

Self-healing capability is a critical factor for a resilient distribution system, which requires intelligent agents to automatically perform service restoration online, including network reconfiguration and reactive power dispatch. Here, the article proposes the imitation learning framework for training such an agent, where the agent will interact with an expert built based on the mixed-integer program to learn its optimal policy, and therefore significantly improve the training efficiency compared with exploration-dominant reinforcement learning (RL) methods. This significantly improved training efficiency makes the training problem under N-k scenarios tractable. A hybrid policy network is proposed to handle tie-line operations and reactive power dispatch simultaneously to further improve the restoration performance. The 33-bus and 119-bus systems with N-k disturbances are employed to conduct the training. The results indicate that the proposed method outperforms traditional RL algorithms such as the deep-Q network.

42 ENGINEERING↗

Application Characterization at Scale: Lessons learned from developing a distributed Open Community Runtime system for High Performance Computing

Since 2012, the U.S. Department of Energy’s X-Stack program has been developing solutions including runtime systems, programming models, languages, compilers, and tools for the Exascale system software to address crucial performance and power requirements. Fine grain programming models and runtime systems show a great potential to efficiently utilize the underlying hardware. Thus, they are essential to many X-Stack efforts. An abundant amount of small tasks can better utilize the vast parallelism available on current and future machines. Moreover, finer tasks can recover faster and adapt better, due to a decrease in state and control. Nevertheless, current applications have been written to exploit old paradigms (such as Communicating Sequential Processor and Bulk Synchronous Parallel processing). To fully utilize the advantages of these new systems, applications need to be adapted to these new paradigms. As part of the applications’ porting process, in-depth characterization studies, focused on both application characteristics and runtime features, need to take place to fully understand the application performance bottlenecks and how to resolve them. This paper presents a characterization study for a novel high performance runtime system, called the Open Community Runtime, using key HPC kernels as its vehicle. This study has the following contributions: one of the first high performance, fine grain, distributed memory runtime system implementing the OCR standard (version 0.99a); and a characterization study of key HPC kernels in terms of runtime primitives running on both intra and inter node environments. Running on a general purpose cluster, we have found up to 1635x relative speed-up for a parallel tiled Cholesky Kernels on 128 nodes with 16 cores each and a 1864x relative speed-up for a parallel tiled Smith-Waterman kernel on 128 nodes with 30 cores.

Application characterization↗

Exploring Machine Learning Techniques For Dynamic Modeling on Future Exascale Systems

Future exascale systems must be optimized for both power and performance at scale in order to achieve DOE’s goal of a sustained petaflop within 20 Megawatts by 2022 [1]. Massive parallelism of the future systems combined with complex memory hierarchies will form a barrier to efficient application and architecture design. These challenges are exacerbated with emerging complex architectures such as GPGPUs and Intel Xeon Phi as parallelism increases orders of magnitude and system power consumption can easily triple or quadruple. Therefore, we need techniques that can reduce the search space for optimization, isolate power-performance bottlenecks, identify root causes for software/hardware inefficiency, and effectively direct runtime scheduling.

Song, Shuaiwen↗