Results for “Distributed computing, machine learning” — Page 2

DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗

DOE OSTI2023

Machine learning for modern power distribution systems: Progress and perspectives

The application of machine learning (ML) to power and energy systems (PES) is being researched at an astounding rate, resulting in a significant number of recent additions to the literature. As the infrastructure of electric power systems evolves, so does interest in deploying ML techniques to PES. However, despite growing interest, the limited number of reported real-world applications suggests that the gap between research and practice is yet to be fully bridged. To help highlight areas where this gap could be narrowed, this article discusses the challenges and opportunities in developing and adapting ML techniques for modern electric power systems, with a particular focus on power distribution systems. These systems play a crucial role in transforming the electric power sector and accommodating emerging distributed technologies to mitigate the impacts of climate change and accelerate the transition to a sustainable energy future. The objective of this article is not to provide an exhaustive overview of the state-of-the-art in the literature, but rather to make the topic accessible to readers with an engineering or computer science background and an interest in the field of ML for PES, thereby encouraging cross-disciplinary research in this rapidly developing field. To this end, the article discusses the ways in which ML can contribute to addressing the evolving operational challenges facing power distribution systems and identifies relevant application areas that exemplify the potential for ML to make near-term contributions. At the same time, key considerations for the practical implementation of ML in power distribution systems are discussed, along with suggestions for several potential future directions.

Marković, Marija (ORCID:0000000247839837)↗

DOE OSTI2020

Avatar Tools

Supervised machine learning is the process of using past experience to predict the future. "Ensembles" are a machine-learning meta-method that can be applied to most machine learning algorithms. Ensembles generally greatly improve accuracy, reduce or remove most of the design issues presented by machine learning, and are admirably suited to parallel and distributed computation. The Avatar Tools codes are an implementation of ensembles specifically for decision trees. Some features that distinguish Avatar Tools from other "ensembles for decision trees" codes are: (1) Does the bookkeeping necessary for out of bag (OOB) validation. (2) Can use OOB validation to automatically determine optimal ensemble size. (3) Provides an MPI-based parallel implementation, for distributed operation. (4) Provides convenient tools for cross-validation, to assess the accuracy provided by a training set. SAND2020-3858 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Siefert, Christopher↗

DOE OSTI2025

Harnessing distributed GPU computing for generalizable graph convolutional networks in power grid reliability assessments

Although machine learning (ML) has emerged as a powerful tool for rapidly assessing grid contingencies, prior studies have largely considered a static grid topology in their analyses. This limits their application, since they need to be re-trained for every new topology. Here, this paper explores the development of generalizable graph convolutional network (GCN) models by pre-training them across a range of grid topologies and contingency types. We found that a GCN model with auto-regressive moving average (ARMA) layers with a line graph representation of the grid offered the best predictive performance in predicting voltage magnitudes (VM) and voltage angles (VA). We introduced the concept of phantom nodes to consider disparate grid topologies with a varying number of nodes and lines. For pre-training the GCN ARMA model across a variety of topologies, distributed graphics processing unit (GPU) computing afforded us significant training scalability. The predictive performance of this model on grid topologies that were part of the training data is substantially better than the direct current (DC) approximation. Although direct application of the pre-trained model to topologies that are not part of the grid is not particularly satisfactory, fine-tuning with small amounts of data from a specific topology of interest significantly improves predictive performance. In general, this paper highlights the feasibility of training large-scale GNN models to assess the reliability of power grids by considering a wide variety of grid topologies and contingency types. With the advent of foundational models in ML and the exponential increase in GPU computing clusters, generalizable ML models will significantly enhance how utilities manage power systems and make decisions in real-time or near-real-time.

24 - POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

CGSim: A Simulation Framework for Large Scale Distributed Computing Environment

Large-scale distributed computing infrastructures such as the Worldwide LHC Computing Grid (WLCG) require comprehensive simulation tools for evaluating performance, testing new algorithms, and optimizing resource allocation strategies. However, existing simulators suffer from limited scalability, hardwired algorithms, lack of real-time monitoring, and inability to generate datasets suitable for modern machine learning approaches. We present CGSim, a simulation framework for large-scale distributed computing environments that addresses these limitations. Built upon the validated SimGrid simulation framework, CGSim provides high-level abstractions for modeling heterogeneous grid environments while maintaining accuracy and scalability. Key features include a modular plugin mechanism for testing custom workflow scheduling and data movement policies, interactive real-time visualization dashboards, and automatic generation of event-level datasets suitable for AI-assisted performance modeling. We demonstrate CGSim’s capabilities through a comprehensive evaluation using production ATLAS PanDA workloads, showing significant calibration accuracy improvements across WLCG computing sites. Scalability experiments show near-linear scaling for multi-site simulations, with distributed workloads achieving 6 × better performance compared to single-site execution. The framework enables researchers to simulate WLCG-scale infrastructures with hundreds of sites and thousands of concurrent jobs within practical time budget constraints on commodity hardware.

Vatsavai, Sairam Sri [Brookhaven National Laborato↗

DOE OSTI2023

Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing

Abstract We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2022

Enabling machine learning-ready HPC ensembles with Merlin

With the growing complexity of computational and experimental facilities, many scientific researchers are turning to machine learning (ML) techniques to analyze large scale ensemble data. With complexities such as multi-component workflows, heterogeneous machine architectures, parallel file systems, and batch scheduling, care must be taken to facilitate this analysis in a high performance computing (HPC) environment. Here, we present Merlin, a workflow framework to enable large ML-friendly ensembles of scientific HPC simulations. By augmenting traditional HPC with distributed compute technologies, Merlin aims to lower the barrier for scientific subject matter experts to incorporate ML into their analysis. As a producer–consumer workflow model, Merlin enables multi-machine, cross-batch job, dynamically allocated yet persistent workflows capable of utilizing surge-compute resources. Key features of Merlin are a flexible HPC-centric interface, low per-task overhead, multi-tiered fault recovery, and a hierarchical sampling algorithm that allows for $\mathscr{O}$(N) task execution and $\mathscr{O}$(N ln N) task queuing to ensembles of millions of tasks. In addition to Merlin’s design, we test the algorithm’s performance in an HPC center and demonstrate the ability to enqueue 40 million simulations in 100 s, with a 30 millisecond per-task overhead that is independent of ensemble size. Finally, we describe some example applications that Merlin has enabled on leadership-class HPC resources, such as the ML-augmented optimization of nuclear fusion experiments and the calibration of infectious disease models to study the progression of and possible mitigation strategies for COVID-19.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Machine Learning Methods for Connection RTT and Loss Rate Estimation Using MPI Measurements Under Random Losses

Scientific computations are expected to be increasingly distributed across wide-area networks, and Message Passing Interface (MPI) has been shown to scale to support their communications over long distances. Application-level measurements of MPI operations reflect the connection Round-Trip Time (RTT) and loss rate, and machine learning methods have been previously developed to estimate them under deterministic periodic losses. In this paper, we consider more complex, random losses with unform, Poisson and Gaussian distributions. We study five disparate machine leaning methods, with linear and non-linear, and smooth and non-smooth properties, to estimate RTT and loss rate over 10Gbps connections with 0-366ms RTT. The diversity and complexity of these estimators combined with the randomness of losses and TCP’s non-linear response together rule out the selection of a single best among them; instead, we fuse them to retain their design diversity. Overall, the results show that accurate estimates can be generated at low loss rates but become inaccurate at loss rates 10% and higher, thereby illustrating both their strengths and limitations.

Generalization Bounds↗

NASA NTRSDate not supplied

NASA's Small Spacecraft and Distributed Systems: Development and Demonstration of Technologies Enabling Swarms and New Spacecraft Platforms with AI and Edge Computing

NASA’s Small Spacecraft & Distributed Systems (SSDS) within the Research and Technology Mission Directorate (RTMD) expands U.S. capability to execute unique missions through targeted investment, rapid development, and flight demonstration of small spacecraft technologies applicable to exploration, science and the commercial space sector. SSDS strategically invests in technology development and on-orbit demonstrations executed across NASA, other government agencies, industry, and academia. The program’s University SmallSat Technology Partnerships initiative awards academic researchers with the opportunity to collaborate with NASA to mature innovative technology. Capabilities aligned with RTMD’s technology shortfalls and interests - power, processing, propulsion, sensors, communications, autonomous navigation, architectures, and advanced applications like artificial intelligence (AI), machine learning, and edge computing - are prioritized in SSDS investments. These investments enable distributed, autonomous, and cooperative small spacecraft systems that support swarm missions extending beyond low Earth orbit into cislunar and deep space. This paper highlights representative SSDS flight demonstrations that mature these capabilities to enable a future operational infrastructure needed to support sustained exploration of the Moon and beyond. SSDS’s investment strategy emphasizes rapid development and on-orbit demonstration to validate spacecraft technologies required for swarms and distributed mission architectures. The Starling swarm technology demonstration mission exemplifies this approach by advancing distributed spacecraft autonomy, cooperative operations, and space situational awareness. Extended flight testing and ongoing studies of next generation swarm configurations and on-orbit space traffic monitoring and management continue to inform future swarm designs. DiskSat’s four-spacecraft demonstration mission represents SSDS’s strategic vision to expand the design space for future small spacecraft through its commitment to advance novel platform concepts that can impact how science is performed on orbit. Continuing to invest in future platforms, the notional PY12 concept is a 12-spacecraft swarm hosting neuromorphic processors and is envisioned as an on-orbit testbed for AI, edge computing, and positioning, navigation and timing technologies. SSDS also invests in single-spacecraft technology demonstrations that underpin the success of future swarm missions and accelerate the availability of validated technologies across the small spacecraft ecosystem. Examples of such demonstrations include Pathfinder Technology Demonstrator-3 (PTD-3), which performed high-rate optical communications; PTD-R, which demonstrated a camera capable of simultaneous ultraviolet and short-wave infrared optical sensing; and CAPSTONE, the Cislunar Autonomous Positioning System Technology and Operations Navigation Experiment, which validated autonomous navigation in cislunar space. Collectively, SSDS-funded demonstrations advance capabilities across swarms and illustrate a coordinated investment strategy to mature high-impact technologies required for autonomous, distributed, and cooperative small spacecraft systems for low Earth orbit, cislunar, and deep space applications. Technology demonstrations strengthen SSDS partnerships with industry, academia, and other government agencies, and promote small spacecraft community adoption of capabilities required to close technical gaps for swarm missions.

Jan Stupl↗

NASA NTRSDate not supplied

NASA's Small Spacecraft and Distributed Systems: Development and Demonstration of Technologies Enabling Swarms and New Spacecraft Platforms with AI and Edge Computing

NASA’s Small Spacecraft & Distributed Systems (SSDS) within the Research and Technology Mission Directorate (RTMD) expands U.S. capability to execute unique missions through targeted investment, rapid development, and flight demonstration of small spacecraft technologies applicable to exploration, science and the commercial space sector. SSDS strategically invests in technology development and on-orbit demonstrations executed across NASA, other government agencies, industry, and academia. The program’s University SmallSat Technology Partnerships initiative awards academic researchers with the opportunity to collaborate with NASA to mature innovative technology. Capabilities aligned with RTMD’s technology shortfalls and interests - power, processing, propulsion, sensors, communications, autonomous navigation, architectures, and advanced applications like artificial intelligence (AI), machine learning, and edge computing - are prioritized in SSDS investments. These investments enable distributed, autonomous, and cooperative small spacecraft systems that support swarm missions extending beyond low Earth orbit into cislunar and deep space. This paper highlights representative SSDS flight demonstrations that mature these capabilities to enable a future operational infrastructure needed to support sustained exploration of the Moon and beyond. SSDS’s investment strategy emphasizes rapid development and on-orbit demonstration to validate spacecraft technologies required for swarms and distributed mission architectures. The Starling swarm technology demonstration mission exemplifies this approach by advancing distributed spacecraft autonomy, cooperative operations, and space situational awareness. Extended flight testing and ongoing studies of next generation swarm configurations and on-orbit space traffic monitoring and management continue to inform future swarm designs. DiskSat’s four-spacecraft demonstration mission represents SSDS’s strategic vision to expand the design space for future small spacecraft through its commitment to advance novel platform concepts that can impact how science is performed on orbit. Continuing to invest in future platforms, the notional PY12 concept is a 12-spacecraft swarm hosting neuromorphic processors and is envisioned as an on-orbit testbed for AI, edge computing, and positioning, navigation and timing technologies. SSDS also invests in single-spacecraft technology demonstrations that underpin the success of future swarm missions and accelerate the availability of validated technologies across the small spacecraft ecosystem. Examples of such demonstrations include Pathfinder Technology Demonstrator-3 (PTD-3), which performed high-rate optical communications; PTD-R, which demonstrated a camera capable of simultaneous ultraviolet and short-wave infrared optical sensing; and CAPSTONE, the Cislunar Autonomous Positioning System Technology and Operations Navigation Experiment, which validated autonomous navigation in cislunar space. Collectively, SSDS-funded demonstrations advance capabilities across swarms and illustrate a coordinated investment strategy to mature high-impact technologies required for autonomous, distributed, and cooperative small spacecraft systems for low Earth orbit, cislunar, and deep space applications. Technology demonstrations strengthen SSDS partnerships with industry, academia, and other government agencies, and promote small spacecraft community adoption of capabilities required to close technical gaps for swarm missions.

Jan Stupl↗

DOE OSTI2023

The globus compute dataset: An open function-as-a-service dataset from the edge to the cloud

Here we present a unique function-as-a-service (FaaS) dataset capturing the use of the Globus Compute (previously funcX) platform. Globus Compute implements a federated model via which users may deploy endpoints on arbitrary remote computers, from the edge to high performance computing (HPC) cluster, and they may then invoke Python functions on those endpoints via a reliable cloud -hosted service. The dataset covers 31 weeks and includes 2121472 task submissions from 252 users executed on 580 remote computing endpoints. It includes 277386 registered functions. We describe the dataset and various observations, some that are similar to other FaaS datasets, for example, that 74% of tasks run for less than 1 s, and some that are unique to Globus Compute, for example, that endpoints are used in different ways and that the majority of functions are related to scientific computing and machine learning. To the best of our knowledge, this dataset represents the first federated FaaS dataset that includes user workloads, distributed computing endpoints, and analysis of registered function bodies. We expect the dataset to be useful for researching FaaS architectures, workload modeling, container warming, and other distributed computing architectures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Flexible Machine Learning-Based Cyberattack Detection Using Spatiotemporal Patterns for Distribution Systems

This letter develops a flexible machine learning detection method for cyberattacks in distribution systems considering spatiotemporal patterns. Spatiotemporal patterns are recognized by the graph Laplacian based on system-wide measurements. A flexible Bayes classifier (BC) is used to train spatiotemporal patterns which could be violated when cyberattacks occur. Cyberattacks are detected by using flexible BCs online. The effectiveness of the developed method is demonstrated through standard IEEE 13- and 123-node test feeders.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Risk-Informed Condition Evaluation of Solar-centered Energy Generation and Distribution Networks through Bayesian Learning and Inference

We develop a methodology based on Bayesian inference over Probabilistic Graphical Models (PGMs) to understand and quantify risk in solar-centered grids using targeted measurements and learned system behavior. Being non-prescriptive but, rather, able to infer system behavior and, ultimately, address risk queries from data, our machine learning-type paradigm is tailored for diverse topologies and threat scenarios often associated with distributed energy generation and photovoltaic distributed energy resources (PV-DERs) in particular. We describe algorithmic processes for: (i) learning the structure of PGMs that result from attack-prone PV-DER-proliferated distribution systems, (ii) quantifying cause-effect relationships, and (iii) evaluating risk queries based on diverse evidence. The contributions are illustrated on a residential grid subject to output impairment attacks on its PV-DER infrastructure.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

RuralAI in Tomato Farming: Integrated Sensor System, Distributed Computing, and Hierarchical Federated Learning for Crop Health Monitoring

Precision horticulture is evolving due to scalable sensor deployment and machine learning (ML) integration. These advancements boost the operational efficiency of individual farms, balancing the benefits of analytics with autonomy requirements. However, given concerns that affect wide geographic regions (e.g., climate change), there is a need to apply models that span farms. Federated learning (FL) has emerged as a potential solution. FL enables decentralized ML across different farms without sharing private data. Traditional FL assumes simple two-tier network topologies and, thus, falls short of operating on more complex networks found in real-world agricultural scenarios. Networks vary across crops and farms and encompass various sensor data modes, extending across jurisdictions. New hierarchical FL (HFL) approaches are needed for more efficient and context-sensitive model sharing, accommodating regulations across multiple jurisdictions. Here, we present the RuralAI architecture deployment for tomato crop monitoring, featuring sensor field units for soil, crop, and weather data collection. HFL with personalization is used to offer localized and adaptive insights. Model management, aggregation, and transfers are facilitated via a flexible approach, enabling seamless communication between local devices, edge nodes, and the cloud.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Reduced Order Model of Transactive Bidding Loads

Transactive energy (TE) has been identified to provide better grid efficiency and reliability by market-based transactive exchanges between energy producers and energy consumers. Simulations of TE systems are crucial to evaluate the benefits and impacts of different transactive mechanisms. However, such simulations can be time consuming due to the information exchange between various participants and complex co-simulation environments. In this paper, we develop a reduced order model to speed up the simulation of transactive systems in TE simulation platform (TESP) while achieving very low error between the reduced order and full model results. Specifically, the developed reduced order model consists of an aggregate responsive load agent which utilizes two Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTMs) to enable transactive elements to collectively participate in the TE system. The proposed aggregate responsive load (ARL) agent is able to produce similar transactive behaviors to the full simulation model while achieving significant simulation time reduction. Finally, we also show that the developed model enables generalization of simulation results across different dates and across different number of loads included in the simulations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

An Intelligent Distributed Ledger Construction Algorithm for IoT

Blockchain is the next generation of secure data management that creates near-immutable decentralized storage. Secure cryptography created a niche for blockchain to provide alternatives to well-known security compromises. However, design bottlenecks with traditional blockchain data structures scale poorly with increased network usage and are extremely computation-intensive. This made the technology difficult to combine with limited devices, like those in Internet of Things networks. In protocols like IOTA, replacement of blockchain's linked-list queue processing with a lightweight dynamic ledger showed remarkable throughput performance increase. However, current stochastic algorithms for ledger construction suffer distinct trade-offs between efficiency and security. This work proposed a machine-learning approach with a multi-arm bandit that resolved these issues and was designed for auditing on limited devices. This algorithm was tested in a reinforcement-learning environment simulating the IOTA ledger's construction with a decision tree. This study showed through regret analysis and experimentation that this approach was secure against impulse manipulation attacks while remaining energy-efficient. Although the IOTA protocol was a pioneer for lightweight distributed ledgers, it is expected that future blockchain protocols will adopt techniques similar to those presented in this work.

multi-arm bandit↗

DOE OSTI2023

Building the I (Interoperability) of FAIR for performance reproducibility of large-scale composable workflows in RECUP

Abstract-Scientific computing communities increasingly run their experiments using complex data- and compute-intensive workflows that utilize distributed and heterogeneous architectures targeting numerical simulations and machine learning, often executed on the Department of Energy Leadership Computing Facilities (LCFs). We argue that a principled, systematic approach to implementing FAIR principles at scale, including fine-grained metadata extraction and organization, can help with the numerous challenges to performance reproducibility posed by such workflows. We extract workflow patterns, propose a set of tools to manage the entire life cycle of performance metadata, and aggregate them in an HPC-ready framework for reproducibility (RECUP). We describe the challenges in making these tools interoperable, preliminary work, and lessons learned from this experiment.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

A machine-learning framework for the simulation of nuclear deflection of Planet-Killer-Asteroids

Here, as detection capabilities in astronomy have dramatically improved over the last two decades, concerns over Planet-Killer-Asteroids (PKAs) have become widespread, with nuclear weapons being proposed to destroy or deflect asteroids that are on a short-term projected collision course with Earth. Two main mitigation strategies have been proposed: • Case 1: Break up an incoming asteroid into smaller pieces that will disperse widely, resulting in smaller-scale, less detrimental, Earth-impacts or • Case 2: Deflect an incoming asteroid trajectory to avoid collision altogether. While the two strategies are not mutually exclusive, deflection is a safer strategy, ideally by harnessing all of the released energy from a nuclear device to move the asteroid as a rigid body. However, this case may not be always possible, since the strength of the energy release may break up the asteroid. In this work, the dynamical response of a PKA to a series of ultra-high energy impulses, such as those generated by nuclear devices, is formulated. A rapid iterative Discrete Element Method (DEM) method is developed to describe the deflection and potential breakup of the PKA as a function of a material bonding strength parameter within the asteroid and the magnitude of the applied impulse. The use of DEM allows for fragmentation of the PKA and the ability to compute the trajectories and distribution of the resulting debris field. Finally, a machine-learning algorithm is then developed and combined with the DEM approach to optimize the pulsation strategy for maximum possible safety and success.

42 ENGINEERING↗