Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Component Architecture”

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 55 records · Page 3

Report of the IMFIT Advisory Committee from the Meeting of 9/16/08 at General Atomics

The Committee commends and thanks the presenters and GA for providing clear and informative presentations. We present our responses to 5 questions raised in the Charge, as well as additional comments that may be useful for the project. (Question 1) The IMFIT framework is based on PYTHON and CCA; can IMFIT meet its long-term goals with this choice of language for framework? Our first recommendation is to change the terminology; it appears that the project is not really utilizing CCA (Common Component Architecture). The project is really about using Python to organize workflow among components that are spawned as processes via pipes from Python. We suggest that in describing the project, the team drop the designation 'CCA' and simply state that the IMFIT framework is based on using Python to control workflow among components. Concerning the specific question: we understand the principal goal of the project to be the development of an easy-to-use tool that efficiently integrates different physics modules to support experimental data analysis and modeling. Yes, Python and the workflow-based framework are appropriate choices for meeting this objective. The Committee, in examining the goal, discussed whether the IMFIT project was duplicative of other projects; there are several others in the U.S. and elsewhere with integrated modeling goals. In particular in the U.S., SWIM, PTRANSP, and the proto-FSP's. However this project occupies a reasonably unique niche through its emphases on integrating experimental data, use of existing components, its near-term focus, and the extent to which is targeted at experimentalist users. (Question 2) Will IMFIT benefit from the additional use of an interoperability language for framework such as BABEL? No, IMFIT is not really doing inter-language communication. In particular this will be the case as long as inter-component communication is via files--and that's OK so long as you aren't doing lots of short steps with communication at each step. (Question 3) IMFIT GUI is based on the public PyGTK toolkit; will IMFIT benefit from the additional use of other public Python graphic toolkits such as wxPython that is a cross-platform wrapper, or PyQt, or a commercial package such as IDL? PyGTK seems adequate for now. The team needs to decide if it needs more capability. Avoid licensed software that interferes with portability and the open-source goal (and thus in particular avoid IDL). (Question 4) Will IMFIT benefit from using a XML-RPC as alternative to sending files thru sockets? IMFIT could benefit by adopting some kind of self-describing format, such as XML or HDF5, but data can still be sent over sockets. This is part of a broader question: 'Should IMFIT adopt some kind of standard for communicating data between components?' To do anything other than what is done now requires modification of individual components (or convertors/wrappers). But moving to a self-describing standard is a good idea, which should be considered. You don't need to impose a standard, but you could decide on one and move toward it gradually, as the architecture doesn't impose a standard. But whether you adopt a standard and the pace of moving toward it is up to you. (Question 5) Will IMFIT benefit from any other available computational tool? (a) IMFIT would benefit from fuller use of an already incorporated tool--python language in the task execution specification, to enable desired features like branching; (b) If there is a high degree of data hierarchy, IMFIT should explore HDF5 as well as NETCDF and compare; (c) IMFIT would benefit from moving toward common data standards; (d) It would be useful for the IMFIT team to monitor developments in related projects such as the proto-FSP's and PTRANSP to ascertain if there are potentially useful tools.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Hydrogen Generation From Electrolysis

Small-scale (100-500 kg H2/day) electrolysis is an important step in increasing the use of hydrogen as fuel. Until there is a large population of hydrogen fueled vehicles, the smaller production systems will be the most cost-effective. Performing conceptual designs and analyses in this size range enables identification of issues and/or opportunities for improvement in approach on the path to 1500 kg H2/day and larger systems. The objectives of this program are to establish the possible pathways to cost effective larger Proton Exchange Membrane (PEM) water electrolysis systems and to identify areas where future research and development efforts have the opportunity for the greatest impact in terms of capital cost reduction and efficiency improvements. System design and analysis was conducted to determine the overall electrolysis system component architecture and develop a life cycle cost estimate. A design trade study identified subsystem components and configurations based on the trade-offs between system efficiency, cost and lifetime. Laboratory testing of components was conducted to optimize performance and decrease cost, and this data was used as input to modeling of system performance and cost. PEM electrolysis has historically been burdened by high capital costs and lower efficiency than required for large-scale hydrogen production. This was known going into the program and solutions to these issues were the focus of the work. The program provided insights to significant cost reduction and efficiency improvement opportunities for PEM electrolysis. The work performed revealed many improvement ideas that when utilized together can make significant progress towards the technical and cost targets of the DOE program. The cell stack capital cost requires reduction to approximately 25% of today’s technology. The pathway to achieve this is through part count reduction, use of thinner membranes, and catalyst loading reduction. Large-scale power supplies are available today that perform in a range of efficiencies, >95%, that are suitable for the overall operational goals. The balance of plant scales well both operationally and in terms of cost becoming a smaller portion of the overall cost equation as the systems get larger. Capital cost reduction of the cell stack power supplies is achievable by modifying the system configuration to have the cell stacks in electrical series driving up the DC bus voltage, thereby allowing the use of large-scale DC power supply technologies. The single power supply approach reduces cost. Elements of the cell stack cost reduction and efficiency improvement work performed in the early stage of the program is being continued in subsequent DOE sponsored programs and through internal investment by Proton. The results of the trade study of the 100 kg H2/day system have established a conceptual platform for design and development of a next generation electrolyzer for Proton. The advancements started by this program have the possibility of being realized in systems for the developing fueling markets in 2010 period.

08 HYDROGEN↗

Virtually-synchronous communication based on a weak failure suspector

Failure detectors (or, more accurately Failure Suspectors (FS)) appear to be a fundamental service upon which to build fault-tolerant, distributed applications. This paper shows that a FS with very weak semantics (i.e., that delivers failure and recovery information in no specific order) suffices to implement virtually-synchronous communication (VSC) in an asynchronous system subject to process crash failures and network partitions. The VSC paradigm is particularly useful in asynchronous systems and greatly simplifies building fault-tolerant applications that mask failures by replicating processes. We suggest a three-component architecture to implement virtually-synchronous communication: (1) at the lowest level, the FS component; (2) on top of it, a component (2a) that defines new views; and (3) a component (2b) that reliably multicasts messages within a view. The issues covered in this paper also lead to a better understanding of the various membership service semantics proposed in recent literature.

Schiper, Andre↗

A Component-Based Framework for Smoothed Particle Hydrodynamics Simulations of Reactive Fluid Flow in Porous Media.

The development of a framework to support smoothed particle hydrodynamics (SPH) simulations of fluid flow and transport in porous media is described. The framework is built using the Common Component Architecture (CCA) toolkit and supports SPH simulations using a variety of different SPH models and setup formats. The SPH simulation code is decomposed into independent components that represent self-contained units of functionality. Different physics models can be developed within the framework by re-implementing key components but no modification of other components is required. The model for defining components and developing abstract interfaces for them that support a high degree of modularity and minimal dependencies between components is discussed in detail.

99 GENERAL AND MISCELLANEOUS↗

The Integrated Plasma Simulator: A Flexible Python Framework for Coupled Multiphysics Simulation

High-fidelity coupled multiphysics simulations are an increasingly important aspect of computational science. In many domains, however, there has been very limited experience with simulations of this sort, therefore research in coupled multiphysics often requires computational frameworks with significant flexibility to respond to the changing directions of the physics and mathematics. This paper presents the Integrated Plasma Simulator (IPS), a framework designed for loosely coupled simulations of fusion plasmas. The IPS provides users with a simple component architecture into which a wide range of existing plasma physics codes can be inserted as components. Simulations can take advantage of multiple levels of parallelism supported in the IPS, and can be controlled by a high-level ``driver'' component, or by other coordination mechanisms, such as an asynchronous event service. We describe the requirements and design of the framework, and how they were implemented in the Python language. We also illustrate the flexibility of the framework by providing examples of different types of simulations that utilize various features of the IPS.

99 GENERAL AND MISCELLANEOUS↗

Design of Space Station era mass storage systems

The architecture, components, and technical approach for a Space Station era mass storage system prototype are described. The primary data storage needs call for such functions as line outage recording, rate buffering, data archiving, and level zero type processing. The prototype mass storage system hardware will be configurable to support three modes of operation at up to 300 Mbps. The system architecture consists of two distinct components: a configurable high-level mass storage control system and a basic storage kernal.

Horner, Ward P.↗

Raexplore: Enabling Rapid, Automated Architecture Exploration for Full Applications

We present Raexplore, a performance modeling framework for architecture exploration. Raexplore enables rapid, automated, and systematic search of architecture design space by combining hardware counter-based performance characterization and analytical performance modeling. We demonstrate Raexplore for two recent manycore processors IBM Blue- Gene/Q compute chip and Intel Xeon Phi, targeting a set of scientific applications. Our framework is able to capture complex interactions between architectural components including instruction pipeline, cache, and memory, and to achieve a 3–22% error for same-architecture and cross-architecture performance predictions. Furthermore, we apply our framework to assess the two processors, and discover and evaluate a list of architectural scaling options for future processor designs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

SpaceCubeX: A Framework for Evaluating Hybrid Multi-Core CPU FPGA DSP Architectures

The SpaceCubeX project is motivated by the need for high performance, modular, and scalable on-board processing to help scientists answer critical 21st century questions about global climate change, air quality, ocean health, and ecosystem dynamics, while adding new capabilities such as low-latency data products for extreme event warnings. These goals translate into on-board processing throughput requirements that are on the order of 100-1,000 more than those of previous Earth Science missions for standard processing, compression, storage, and downlink operations. To study possible future architectures to achieve these performance requirements, the SpaceCubeX project provides an evolvable testbed and framework that enables a focused design space exploration of candidate hybrid CPU/FPGA/DSP processing architectures. The framework includes ArchGen, an architecture generator tool populated with candidate architecture components, performance models, and IP cores, that allows an end user to specify the type, number, and connectivity of a hybrid architecture. The framework requires minimal extensions to integrate new processors, such as the anticipated High Performance Spaceflight Computer (HPSC), reducing time to initiate benchmarking by months. To evaluate the framework, we leverage a wide suite of high performance embedded computing benchmarks and Earth science scenarios to ensure robust architecture characterization. We report on our projects Year 1 efforts and demonstrate the capabilities across four simulation testbed models, a baseline SpaceCube 2.0 system, a dual ARM A9 processor system, a hybrid quad ARM A53 and FPGA system, and a hybrid quad ARM A53 and DSP system.

Hybrid Flight Architectures↗

Support for User Interfaces for Distributed Systems

An extensible Java(TradeMark) software framework supports the construction and operation of graphical user interfaces (GUIs) for distributed computing systems typified by ground control systems that send commands to, and receive telemetric data from, spacecraft. Heretofore, such GUIs have been custom built for each new system at considerable expense. In contrast, the present framework affords generic capabilities that can be shared by different distributed systems. Dynamic class loading, reflection, and other run-time capabilities of the Java language and JavaBeans component architecture enable the creation of a GUI for each new distributed computing system with a minimum of custom effort. By use of this framework, GUI components in control panels and menus can send commands to a particular distributed system with a minimum of system-specific code. The framework receives, decodes, processes, and displays telemetry data; custom telemetry data handling can be added for a particular system. The framework supports saving and later restoration of users configurations of control panels and telemetry displays with a minimum of effort in writing system-specific code. GUIs constructed within this framework can be deployed in any operating system with a Java run-time environment, without recompilation or code changes.

Eychaner, Glenn↗

LOW-COST LED LUMINAIRE FOR GENERAL ILLUMINATION

During this two-year Solid-State Lighting (SSL) Manufacturing R&D project Cree developed novel light emitting diode (LED) technologies contributing to a cost-optimized, efficient LED troffer luminaire platform emitting at ~3500K correlated color temperature (CCT) at a color rendering index (CRI) of >90. To successfully achieve program goals, Cree used a comprehensive approach to address cost reduction of the various optical, thermal and electrical subsystems in the luminaire without impacting performance. These developments built on Cree’s high- brightness, low-cost LED platforms to design a novel LED component architecture that will enable low-cost troffer luminaire designs with high total system efficacy. The project scope included cost reductions to nearly all major troffer subsystems as well as assembly costs. For example, no thermal management components were included in the troffer, owing to the optimized distribution of compact low- to mid-power LEDs. It is estimated that a significant manufacturing cost savings will result relative to Cree’s conventional troffers at the start of the project. A chief project accomplishment was the successful development of a new compact, high-efficacy LED component geometry with a broad far-field intensity distribution and even color point vs. emission angle. After further optimization and testing for production, the Cree XQ series of LEDs resulted. XQ LEDs are currently utilized in Cree’s AR series troffers, and they are being considered for use in other platforms. The XQ lens geometry influenced the independent development of Cree’s XB-E and XB-G high-voltage LEDs, which also have a broad intensity distribution at high efficacy, and are finding wide implementation in Cree’s omnidirectional A-lamps.

Lowes, Ted↗

Framework for Integrating Science Data Processing Algorithms Into Process Control Systems

A software framework called PCS Task Wrapper is responsible for standardizing the setup, process initiation, execution, and file management tasks surrounding the execution of science data algorithms, which are referred to by NASA as Product Generation Executives (PGEs). PGEs codify a scientific algorithm, some step in the overall scientific process involved in a mission science workflow. The PCS Task Wrapper provides a stable operating environment to the underlying PGE during its execution lifecycle. If the PGE requires a file, or metadata regarding the file, the PCS Task Wrapper is responsible for delivering that information to the PGE in a manner that meets its requirements. If the PGE requires knowledge of upstream or downstream PGEs in a sequence of executions, that information is also made available. Finally, if information regarding disk space, or node information such as CPU availability, etc., is required, the PCS Task Wrapper provides this information to the underlying PGE. After this information is collected, the PGE is executed, and its output Product file and Metadata generation is managed via the PCS Task Wrapper framework. The innovation is responsible for marshalling output Products and Metadata back to a PCS File Management component for use in downstream data processing and pedigree. In support of this, the PCS Task Wrapper leverages the PCS Crawler Framework to ingest (during pipeline processing) the output Product files and Metadata produced by the PGE. The architectural components of the PCS Task Wrapper framework include PGE Task Instance, PGE Config File Builder, Config File Property Adder, Science PGE Config File Writer, and PCS Met file Writer. This innovative framework is really the unifying bridge between the execution of a step in the overall processing pipeline, and the available PCS component services as well as the information that they collectively manage.

Mattmann, Chris A.↗

Digital Architecture for a Trace Gas Sensor Platform

A digital architecture has been implemented for a trace gas sensor platform, as a companion to standard analog control electronics, which accommodates optical absorption whose fractional absorbance equivalent would result in excess error if assumed to be linear. In cases where the absorption (1-transmission) is not equivalent to the fractional absorbance within a few percent error, it is necessary to accommodate the actual measured absorption while reporting the measured concentration of a target analyte with reasonable accuracy. This requires incorporation of programmable intelligence into the sensor platform so that flexible interpretation of the acquired data may be accomplished. Several different digital component architectures were tested and implemented. Commercial off-the-shelf digital electronics including data acquisition cards (DAQs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), and microcontrollers have been used to achieve the desired outcome. The most completely integrated architecture achieved during the project used the CPLD along with a microcontroller. The CPLD provides the initial digital demodulation of the raw sensor signal, and then communicates over a parallel communications interface with a microcontroller. The microcontroller analyzes the digital signal from the CPLD, and applies a non-linear correction obtained through extensive data analysis at the various relevant EVA operating pressures. The microcontroller then presents the quantitatively accurate carbon dioxide partial pressure regardless of optical density. This technique could extend the linear dynamic range of typical absorption spectrometers, particularly those whose low end noise equivalent absorbance is below one-part-in-100,000. In the EVA application, it allows introduction of a path-length-enhancing architecture whose optical interference effects are well understood and quantified without sacrificing the dynamic range that allows quantitative detection at the higher carbon dioxide partial pressures. The digital components are compact and allow reasonably complete integration with separately developed analog control electronics without sacrificing size, mass, or power draw.

Gonzales, Paula↗

COSMIC DAWN: Distributed Analysis of Wireless at Nextscale

Distributed Analysis of Wireless at Nextscale (DAWN) is a novel simulation framework for large-scale design-space exploration (DSE) of unmodified software-defined radio (SDR) applications interacting in a scalable, high-fidelity, virtual physics environment. The software-defined nature of the coupled software-physics simulation leverages hardware emulation to permit in-depth examination and modification of not only the electromagnetic environment, including each signal in flight, but also the precise state of system software and components. DAWN supports modular, customizable physics environments allowing realistic propagation effects so that computationally efficient empirical models, reduced order/surrogate models, or large-scale, high-fidelity, site-specific simulations can be used as a propagation medium based on scenario requirements. This paper introduces DAWN’s design and initial implementation, detailing key architectural components, including the Physics Realization Engine (PhyRE), Runtime Infrastructure for Simulation Environments (RISE), and the design space exploration (DSE) suite. It concludes with demonstrations using unmodified 4G/LTE software available from srsRAN on computing resources ranging from a small cluster to ORNL’s Frontier Exascale system.

Wise, Mike [ORNL] (ORCID:0000000266120641)↗

Hypervelocity Impact Performance of 3D Printed Aluminum Panels

With the continued development of additive manufacturing methods, control over the shape of ligaments, cell regularity, and macroscopic shape can all be easily tuned. This capability allows for tailoring of component architecture and promotes potential mass savings in a space vehicle structure. Additionally, it allows one the flexibility of combining structural elements such as MMOD protection and vehicle stiffness for launch loads for an overall mass reduction. At NASA JSC this technology is being explored in many different ways with the goal being a multifunctional structural component. For this study, four different types of aluminum panels have been 3D printed for testing, three being of a body centric cubic (BCC) lattice structure core and one being kelvin cell structure core. All samples have a 5.33 cm (0.05”) nominally thick aluminum face sheet printed on the front and back side of each panel, with all core materials having a 5.08 cm (2.0”) nominal thickness (see Table 1 for test sample summary and Figures 1 – 2 for sample illustrations). These tests will evaluate the performance of 3D printed aluminum panels under hypervelocity impact (HVI) conditions. The hypervelocity impact tests are being conducted at the JSC White Sands Test Facility (WSTF) Remote Hypervelocity Test Laboratory (RHTL), located in Las Cruces, New Mexico. All tests will be conducted with a 3.4mm Al 2017-T4 sphere at 6.8 km/s impacting at 0° to surface normal (i.e., impacting with no obliquity). Each sample will be trapped between two metal frames, with gasket material residing between the sample and frame, which will be the shipping and testing configuration for all tests. There will be an Al 2017-T4 witness plate staged 5.08 cm (2.0”) from each sample to capture signature of debris, if the rear face sheet of the sample were to perforate from the HVI test event.

Davis, B. A.↗

Implementing High Performance Remote Method Invocation in CCA

We report our effort in engineering a high performance remote method invocation (RMI) mechanism for the Common Component Architecture (CCA). This mechanism provides a highly efficient and easy-to-use mechanism for distributed computing in CCA, enabling CCA applications to effectively leverage parallel systems to accelerate computations. This work is built on the previous work of Babel RMI. Babel is a high performance language interoperability tool that is used in CCA for scientific application writers to share, reuse, and compose applications from software components written in different programming languages. Babel provides a transparent and flexible RMI framework for distributed computing. However, the existing Babel RMI implementation is built on top of TCP and does not provide the level of performance required to distribute fine-grained tasks. We observed that the main reason the TCP based RMI does not perform well is because it does not utilize the high performance interconnect hardware on a cluster efficiently. We have implemented a high performance RMI protocol, HPCRMI. HPCRMI achieves low latency by building on top of a low-level portable communication library, Aggregated Remote Message Copy Interface (ARMCI), and minimizing communication for each RMI call. Our design allows a RMI operation to be completed by only two RDMA operations. We also aggressively optimize our system to reduce copying. In this paper, we discuss the design and our experimental evaluation of this protocol. Our experimental results show that our protocol can improve RMI performance by an order of magnitude.

99 GENERAL AND MISCELLANEOUS↗

DGaaS: GPU as a Service on Distributed Computing System

In the rapidly evolving landscape of scientific computing, Graphics Processing Units (GPUs) have become indispensable for their unparalleled ability to handle parallel tasks in complex calculations, simulations, and data analysis. Their utility is further magnified in machine learning and AI applications, where they significantly accelerate model training and predictive analytics. Within this context, the Triton Inference Server emerges as a pivotal open-source tool, specializing in AI inferencing and optimizing GPU utilization across various platforms and frameworks. This paper presents an in-depth study on distributed High Throughput Computing (HTC), specifically focusing on the HTCondor framework and its resource provisioning tools, GlideinWMS and HEPCloud. These systems enable large-scale scientific experiments like CMS and DUNE to efficiently access and utilize vast computational resources. The paper explores the core architectural components of GlideinWMS, including jobs, user pools, and worker nodes, and discusses their integration with GPUs and the Triton server. The primary aim of this research is to develop a solution that optimizes GPU utilization by leveraging Glideins and containers. This approach allows computational jobs, particularly those involving AI models, to use GPUs only when essential, thereby facilitating efficient sharing of limited GPU resources. To validate this architecture, the study conducted three key tests involving custom scripts, container-based servers, and Triton server deployments. However, the study faces challenges, notably in locating the Triton server and ensuring secure remote access. To address these issues, future work will focus on developing a proxy mechanism and enhancing security protocols. In conclusion, this study offers a comprehensive roadmap for effective and efficient GPU utilization in distributed High Throughput Computing. It aims to contribute significantly to the scientific community by solving pressing problems and implementing robust solutions in collaboration with the GlideinWMS and HEPCloud teams. The research sets the stage for a more efficient, scalable, and cost-effective paradigm in scientific computing.

97 MATHEMATICS AND COMPUTING↗

The Invasive Species Forecasting System

The Invasive Species Forecasting System (ISFS) provides computational support for the generic work processes found in many regional-scale ecosystem modeling applications. Decision support tools built using ISFS allow a user to load point occurrence field sample data for a plant species of interest and quickly generate habitat suitability maps for geographic regions of management concern, such as a national park, monument, forest, or refuge. This type of decision product helps resource managers plan invasive species protection, monitoring, and control strategies for the lands they manage. Until now, scientists and resource managers have lacked the data-assembly and computing capabilities to produce these maps quickly and cost efficiently. ISFS focuses on regional-scale habitat suitability modeling for invasive terrestrial plants. ISFS s component architecture emphasizes simplicity and adaptability. Its core services can be easily adapted to produce model-based decision support tools tailored to particular parks, monuments, forests, refuges, and related management units. ISFS can be used to build standalone run-time tools that require no connection to the Internet, as well as fully Internet-based decision support applications. ISFS provides the core data structures, operating system interfaces, network interfaces, and inter-component constraints comprising the canonical workflow for habitat suitability modeling. The predictors, analysis methods, and geographic extents involved in any particular model run are elements of the user space and arbitrarily configurable by the user. ISFS provides small, lightweight, readily hardened core components of general utility. These components can be adapted to unanticipated uses, are tailorable, and require at most a loosely coupled, nonproprietary connection to the Web. Users can invoke capabilities from a command line; programmers can integrate ISFS's core components into more complex systems and services. Taken together, these features enable a degree of decentralization and distributed ownership that have helped other types of scientific information services succeed in recent years.

Schnase, John↗

Lunar architecture and urbanism

Human civilization and architecture have defined each other for over 5000 years on Earth. Even in the novel environment of space, persistent issues of human urbanism will eclipse, within a historically short time, the technical challenges of space settlement that dominate our current view. By adding modern topics in space engineering, planetology, life support, human factors, material invention, and conservation to their already renaissance array of expertise, urban designers can responsibly apply ancient, proven standards to the exciting new opportunities afforded by space. Inescapable facts about the Moon set real boundaries within which tenable lunar urbanism and its component architecture must eventually develop.

Sherwood, Brent↗