Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed systems, data management”

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 271 records · Page 15

The ATLAS Workflow Management System Evolution in the LHC Run3 and towards the High-Luminosity LHC era

The ATLAS experiment has 18+ years of experience using workload management systems to deploy and develop workflows to process and to simulate data on the distributed computing infrastructure. Simulation, processing and analysis of LHC experiment data require the coordinated work of heterogeneous computing resources. In particular, the ATLAS experiment utilizes the resources of 250 computing centers worldwide, the power of supercomputing centres, and national, academic and commercial cloud computing resources. In this contribution, we present new techniques for cost-effectively improving efficiency introduced in workflow management system software. The evolution from a mesh framework to new types of computing facilities such as cloud and HPCs is described, as well as new types of production and analysis workflows.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A database management capability for Ada

The data requirements of mission critical defense systems have been increasing dramatically. Command and control, intelligence, logistics, and even weapons systems are being required to integrate, process, and share ever increasing volumes of information. To meet this need, systems are now being specified that incorporate data base management subsystems for handling storage and retrieval of information. It is expected that a large number of the next generation of mission critical systems will contain embedded data base management systems. Since the use of Ada has been mandated for most of these systems, it is important to address the issues of providing data base management capabilities that can be closely coupled with Ada. A comprehensive distributed data base management project has been investigated. The key deliverables of this project are three closely related prototype systems implemented in Ada. These three systems are discussed.

Chan, Arvola↗

Software and computing for Run 3 of the ATLAS experiment at the LHC

The ATLAS experiment has developed extensive software and distributed computing systems for Run 3 of the LHC. These systems are described in detail, including software infrastructure and workflows, distributed data and workload management, database infrastructure, and validation. The use of these systems to prepare the data for physics analysis and assess its quality are described, along with the software tools used for data analysis itself. An outlook for the development of these projects towards Run 4 is also provided.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Software Architecture for Intelligent Synthesis Environments

The NASA's Intelligent Synthesis Environment (ISE) program is a grand attempt to develop a system to transform the way complex artifacts are engineered. This paper discusses a "middleware" architecture for enabling the development of ISE. Desirable elements of such an Intelligent Synthesis Architecture (ISA) include remote invocation; plug-and-play applications; scripting of applications; management of design artifacts, tools, and artifact and tool attributes; common system services; system management; and systematic enforcement of policies. This paper argues that the ISA extend conventional distributed object technology (DOT) such as CORBA and Product Data Managers with flexible repositories of product and tool annotations and "plug-and-play" mechanisms for inserting "ility" or orthogonal concerns into the system. I describe the Object Infrastructure Framework, an Aspect Oriented Programming (AOP) environment for developing distributed systems that provides utility insertion and enables consistent annotation maintenance. This technology can be used to enforce policies such as maintaining the annotations of artifacts, particularly the provenance and access control rules of artifacts-, performing automatic datatype transformations between representations; supplying alternative servers of the same service; reporting on the status of jobs and the system; conveying privileges throughout an application; supporting long-lived transactions; maintaining version consistency; and providing software redundancy and mobility.

Filman, Robert E.↗

Use of glide-ins in CMS for production and analysis

With the evolution of various grid federations, the Condor glide-ins represent a key feature in providing a homogeneous pool of resources using late-binding technology. The CMS collaboration uses the glide-in based Workload Management System, glideinWMS, for production (ProdAgent) and distributed analysis (CRAB) of the data. The Condor glide-in daemons traverse to the worker nodes, submitted via Condor-G. Once activated, they preserve the Master-Worker relationships, with the worker first validating the execution environment on the worker node before pulling the jobs sequentially until the expiry of their lifetimes. The combination of late-binding and validation significantly reduces the overall failure rate visible to CMS physicists. We discuss the extensive use of the glideinWMS since the computing challenge, CCRC-08, in order to prepare for the forthcoming LHC data-taking period. The key features essential to the success of large-scale production and analysis on CMS resources across major grid federations, including EGEE, OSG and NorduGrid are outlined. Use of glide-ins via the CRAB server mechanism and ProdAgent, as well as first hand experience of using the next generation CREAM computing element within the CMS framework is discussed.

99 GENERAL AND MISCELLANEOUS↗

Flight deck benefits of integrated data link communication

A fixed-base, piloted simulation study was conducted to determine the operational benefits that result when air traffic control (ATC) instructions are transmitted to the deck of a transport aircraft over a digital data link. The ATC instructions include altitude, airspeed, heading, radio frequency, and route assignment data. The interface between the flight deck and the data link was integrated with other subsystems of the airplane to facilitate data management. Data from the ATC instructions were distributed to the flight guidance and control system, the navigation system, and an automatically tuned communication radio. The co-pilot initiated the automation-assisted data distribution process. Digital communications and automated data distribution were compared with conventional voice radio communication and manual input of data into other subsystems of the simulated aircraft. Less time was required in the combined communication and data management process when data link ATC communication was integrated with the other subsystems. The test subjects, commercial airline pilots, provided favorable evaluations of both the digital communication and data management processes.

Waller, Marvin C.↗

The design of a petabyte archive and distribution system for the NASA ECS project

The NASA EOS Data and Information System (EOSDIS) Core System (ECS) will contain one of the largest data management systems ever built - the ECS Science and Data Processing System (SDPS). SDPS is designed to support long term Global Change Research by acquiring, producing, and storing earth science data, and by providing efficient means for accessing and manipulating that data. The first two releases of SDPS, Release A and Release B, will be operational in 1997 and 1998, respectively. Release B will be deployed at eight Distributed Active Archiving Centers (DAAC's). Individual DAAC's will archive different collections of earth science data, and will vary in archive capacity. The storage and management of these data collections is the responsibility of the SDPS Data Server subsystem. It is anticipated that by the year 2001, the Data Server subsystem at the Goddard DAAC must support a near-line data storage capacity of one petabyte. The development of SDPS is a system integration effort in which COTS products will be used in favor of custom components in very possible way. Some software and hardware capabilities required to meet ECS data volume and storage management requirements beyond 1999 are not yet supported by available COTS products. The ECS project will not undertake major custom development efforts to provide these capabilities. Instead, SDPS and its Data Server subsystem are designed to support initial implementations with current products, and provide an evolutionary framework that facilitates the introduction of advanced COTS products as they become available. This paper provides a high-level description of the Data Server subsystem design from a COTS integration standpoint, and discussed some of the major issues driving the design. The paper focuses on features of the design that will make the system scalable and adaptable to changing technologies.

Caulk, Parris M.↗

Distributed Resources for the Earth System Grid Advanced Management (DREAM)

The DREAM project was funded more than 3 years ago to design and implement a next-generation ESGF (Earth System Grid Federation) architecture which would be suitable for managing and accessing data and services resources on a distributed and scalable environment. In particular, the project intended to focus on the computing and visualization capabilities of the stack, which at the time were rather primitive. At the beginning, the team had the general notion that a better ESGF architecture could be built by modularizing each component, and redefining its interaction with other components by defining and exposing a well defined API. Although this was still the high level principle that guided the work, the DREAM project was able to accomplish its goals by leveraging new practices in IT that started just about 3 or 4 years ago: the advent of containerization technologies (specifically, Docker), the development of frameworks to manage containers at scale (Docker Swarm and Kubernetes), and their application to the commercial Cloud. Thanks to these new technologies, DREAM was able to improve the ESGF architecture (including its computing and visualization services) to a level of deployability and scalability beyond the original expectations. Overall, during its three-year lifespan, DREAM has undertaken innovative research work and prototyping: many of its solutions (the new containerized architecture, the Visus visualization engine, the Solr Cloud based search service) were handed over to the ESGF collaboration, which will make them operational and use them as their future software basis.

42 ENGINEERING↗

Analyzing Distributed Functions in an Integrated Hazard Analysis

Large scale integration of today's aerospace systems is achievable through the use of distributed systems. Validating the safety of distributed systems is significantly more difficult as compared to centralized systems because of the complexity of the interactions between simultaneously active components. Integrated hazard analysis (IHA), a process used to identify unacceptable risks and to provide a means of controlling them, can be applied to either centralized or distributed systems. IHA, though, must be tailored to fit the particular system being analyzed. Distributed systems, for instance, must be analyzed for hazards in terms of the functions that rely on them. This paper will describe systems-oriented IHA techniques (as opposed to traditional failure-event or reliability techniques) that should be employed for distributed systems in aerospace environments. Special considerations will be addressed when dealing with specific distributed systems such as active thermal control, electrical power, command and data handling, and software systems (including the interaction with fault management systems). Because of the significance of second-order effects in large scale distributed systems, the paper will also describe how to analyze secondary functions to secondary functions through the use of channelization.

Morris, A. Terry↗

Space Station Freedom ground data system: Design and operations

Over the previous year the Space Station Freedom (SSF) Program (SSFP) ground data distribution system has become independent of a number of data systems that were to have been provided by other National Aeronautics and Space Administration (NASA) programs. Consequently, the SSFP has outlined the basic architecture of a new data system dedicated to supporting SSF requirements. This has been accomplished through a complete redesign of the ground network and a reallocation of selected functions. There are a number of aspects of the new ground data distribution system that are unique among NASA programs. These considerations make SSF ground data distribution one of the most extensive and complex data management challenges encountered in the arena of Space Operations. A description of this system comprises the main focus of the paper.

Dunning, Richard A., Jr.↗

AN INTELLIGENT SENSOR FRAMEWORK FOR THE POWER GRID

The number of sensors connected to the electric power system is expected to grow by several orders of magnitude by 2020. However, the information networks which will transmit and analyze the resulting data are ill-equipped to handle the resulting volume with reliable real-time delivery. Without the ability to manage and use this data, deploying sensors such as phasor measurement units in the transmission system and smart meters in the distribution system will not result in the desired improvements in the power grid. The ability to exploit the massive data being generated by new sensors would allow for more efficient flow of power and increased survivability of the grid. Additionally, the power systems of today are not capable of managing two-way power flow to accommodate distributed generation capabilities due to concerns about system stability and lack of system flexibility. The research that we are performing creates a framework to add 'intelligence' to the sensors and actuators being used today in the electric power system. Sensors that use our framework will be capable of sharing information through the various layers of the electric power system to enable two-way information flow to help facilitate integration of distributed resources. Several techniques are considered including use of peer-to-peer communication as well as distributed agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NELS 2.0 - A general system for enterprise wide information management

NELS, the NASA Electronic Library System, is an information management tool for creating distributed repositories of documents, drawings, and code for use and reuse by the aerospace community. The NELS retrieval engine can load metadata and source files of full text objects, perform natural language queries to retrieve ranked objects, and create links to connect user interfaces. For flexibility, the NELS architecture has layered interfaces between the application program and the stored library information. The session manager provides the interface functions for development of NELS applications. The data manager is an interface between session manager and the structured data system. The center of the structured data system is the Wide Area Information Server. This system architecture provides access to information across heterogeneous platforms in a distributed environment. There are presently three user interfaces that connect to the NELS engine; an X-Windows interface, and ASCII interface and the Spatial Data Management System. This paper describes the design and operation of NELS as an information management tool and repository.

Smith, Stephanie L.↗

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Abstract Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN models on HPC systems to predict material properties of millions of molecules. We use HydraGNN, our in-house library for large-scale GCNN training, leveraging distributed data parallelism in PyTorch. We use ADIOS, a high-performance data management framework for efficient storage and reading of large molecular graph data. We perform parallel training on two open-source large-scale graph datasets to build a GCNN predictor for an important quantum property known as the HOMO-LUMO gap. We measure the scalability, accuracy, and convergence of our approach on two DOE supercomputers: the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF) and the Perlmutter system at the National Energy Research Scientific Computing Center (NERSC). We present our experimental results with HydraGNN showing (i) reduction of data loading time up to 4.2 times compared with a conventional method and (ii) linear scaling performance for training up to 1024 GPUs on both Summit and Perlmutter.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Network interface unit design options performance analysis

An analysis is presented of three design options for the Space Station Freedom (SSF) onboard Data Management System (DMS) Network Interface Unit (NIU). The NIU provides the interface from the Fiber Distributed Data Interface (FDDI) local area network (LAN) to the DMS processing elements. The FDDI LAN provides the primary means for command and control and low and medium rate telemetry data transfers on board the SSF. The results of this analysis provide the basis for the implementation of the NIU.

Miller, Frank W.↗

Evolution of Information Management at the GSFC Earth Sciences (GES) Data and Information Services Center (DISC): 2006-2007

Increasingly sophisticated National Aeronautics and Space Administration (NASA) Earth science missions have driven their associated data and data management systems from providing simple point-to-point archiving and retrieval to performing user-responsive distributed multisensor information extraction. To fully maximize the use of remote-sensor-generated Earth science data, NASA recognized the need for data systems that provide data access and manipulation capabilities responsive to research brought forth by advancing scientific analysis and the need to maximize the use and usability of the data. The decision by NASA to purposely evolve the Earth Observing System Data and Information System (EOSDIS) at the Goddard Space Flight Center (GSFC) Earth Sciences (GES) Data and Information Services Center (DISC) and other information management facilities was timely and appropriate. The GES DISC evolution was focused on replacing the EOSDIS Core System (ECS) by reusing the In-house developed disk-based Simple, Scalable, Script-based Science Product Archive (S4PA) data management system and migrating data to the disk archives. Transition was completed in December 2007

Kempler, Steven↗

Catalyzing deep decarbonization with federated battery diagnosis and prognosis for better data management in energy storage systems

Industrial data analytics methods play a central role in improving energy storage performance and efficiency, impacting the future of electrified transportation and renewable electricity generation. However, significant challenges hinder the large-scale deployment of batteries. Conventional methods rely on centralized collection and processing of fleet-level data, leading to database size issues and privacy concerns due to potential data breaches. To enable scalable deployment of battery management systems, this article proposes a federated battery diagnosis and prognosis model, which distributes the processing of battery standard current-voltage-time-usage data in a privacy-preserving manner. Instead of transferring the raw data, this approach communicates only the locally processed parameters, thus reducing communication load and preserving data confidentiality. The federated model offers a paradigm shift in battery health management through privacy-preserving distributed methods for battery data processing and lifetime prediction, ensuring the reliable and sustainable deployment of lithium-ion batteries in a rapidly evolving world.

asset health management↗

Distributed science operations for JPL planetary missions

Advances in spacecraft, flight instruments, and ground systems provide an impetus and an opportunity for scientific investigation teams to take direct control of their instruments' operations and data collection while at the same time, providing a cost effective and flexible approach in support of increasingly complex science missions. Operations of science instruments have generally been integrated into planetary flight and ground systems at a very detailed level. That approach has been successful, but the cost of incorporating instrument expertise into the central mission operations system has been high. This paper discusses an approach to simplify planetary science operations by distributing instrument computing and data management tasks from the central mission operations system to each investigator's home center of observational expertise. Some early results of this operations concept will be presented based on the Mars Observer (MO) Project experience and Cassini Project plans.

Benson, Richard D.↗

Space station data management system - A common GSE test interface for systems testing and verification

This paper examines the fundamental problems and goals associated with test, verification, and flight-certification of man-rated distributed data systems. First, a summary of the characteristics of modern computer systems that affect the testing process is provided. Then, verification requirements are expressed in terms of an overall test philosophy for distributed computer systems. This test philosophy stems from previous experience that was gained with centralized systems (Apollo and the Space Shuttle), and deals directly with the new problems that verification of distributed systems may present. Finally, a description of potential hardware and software tools to help solve these problems is provided.

Martinez, Pedro A.↗