Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data Center Networks”

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 109 records · Page 6

Apparatus and method for data communication in an energy distribution network

A system for communicating information on an energy distribution network is disclosed. In one embodiment, the system includes a local supervisor on a communication network, wherein the local supervisor can collect data from one or more energy generation/monitoring devices. The system also includes a command center on the communication network, wherein the command center can generate one or more commands for controlling the one or more energy generation devices. The local supervisor can periodically transmit a data signal indicative of the data to the command center via a first channel of the communication network at a first interval. The local supervisor can also periodically transmit a request for a command to the command center via a second channel of the communication network at a second interval shorter than the first interval. This channel configuration provides effective data communication without a significant increase in the use of network resources.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Final report on work for Center for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas — Tools for Improved Data Logistics

This project focused on the use of Logistical Networking technology to address the challenges involved in rapid sharing of data from the the Center's gyrokinetic particle simulations, which can be on the order of terabytes per time step, among researchers at a number of geographically distributed locations. There is a great need to manage data on this scale in a flexible manner, with simulation code, file system, database and visualization functions requiring access. The project used distributed data management infrastructure based on Logistical Networking technology to address these issues in a way that maximized interoperability and achieved the levels of performance the required by the Center's application community. The work focused on the development and deployment of software tools and infrastructure for the storage and distribution of terascale datasets generated by simulations running at the National Center for Computational Science at Oak Ridge National Laboratory.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Evaluating Space Network (SN) scheduling operations concepts through statistical analysis

The Network Control Center (NCC) currently uses the NCC Data System (NCCDS) to schedule customer spacecraft communication requests for the Space Network (SN). The NCC/Request Oriented Scheduling Engine (NCC/ROSE), which implements an operational concept called flexible scheduling, is being tested as a potential replacement for the NCCDS scheduler in an effort to increase the efficiency of the NCC scheduling operations. This paper describes the high fidelity benchmark tests being conducted on NCC/ROSE, the evaluation techniques used to compare schedules, and the results of the tests. This testing will verify the increases in efficiency and productivity that can help the NCC meet the anticipated scheduling loads well into the next century.

Kwadrat, Carl↗

Complex Network Analysis and Intelligent Monitoring Platform

Data Products has particular interest in developing an efficient network analysis and monitoring system that utilizes advanced machine learning methods to mine complex network data of the type generated within large data centers, with an objective to provide tangible business-usable intelligence. The Laboratory is currently the lead institution for a U.S. Department of Energy Office of Science (DOE/SC) network research project called BigData Express (BDE). The project seeks to provide an orchestration service for high-performance data movement of data sets for large-scale science. This collaboration is believed to potentially be a highly symbiotic one, with Data Products platform development benefiting from the rich sets of network data available in the BDE development environment, and BDE benefiting from the Data Products machine learning analysis of BDE-generated data movement.

97 MATHEMATICS AND COMPUTING↗

Ethernet for Space Flight Applications

NASA's Goddard Space Flight Center (GSFC) is adapting current data networking technologies to fly on future spaceflight missions. The benefits of using commercially based networking standards and protocols have been widely discussed and are expected to include reduction in overall mission cost, shortened integration and test (I&T) schedules, increased operations flexibility, and hardware and software upgradeability/scalability with developments ongoing in the commercial world. The networking effort is a comprehensive one encompassing missions ranging from small University Explorer (UNEX) class spacecraft to large observatories such as the Next Generation Space Telescope (NGST). Mission aspects such as flight hardware and software, ground station hardware and software, operations, RF communications, and security (physical and electronic) are all being addressed to ensure a complete end-to-end system solution. One of the current networking development efforts at GSFC is the SpaceLAN (Spacecraft Local Area Network) project, development of a space-qualifiable Ethernet network. To this end we have purchased an IEEE 802.3-compatible 10/100/1000 Media Access Control (MAC) layer Intellectual Property (IP) core and are designing a network node interface (NNI) and associated network components such as a switch. These systems will ultimately allow the replacement of the typical MIL-STD-1553/1773 and custom interfaces that inhabit most spacecraft. In this paper we will describe our current Ethernet NNI development along with a novel new space qualified physical layer that will be used in place of the standard interfaces. We will outline our plans for development of space qualified network components that will allow future spacecraft to operate in significant radiation environments while using a single onboard network for reliable commanding and data transfer. There will be a brief discussion of some issues surrounding system implications of a flight Ethernet. Finally, we will show an onboard network architecture for a proposed new mission using Ethernet for science data transport.

Webb, Evan↗

Become EV Friendly With Planning Resources for Charging Infrastructure

State and local governments are key to the successful build-out of a nationwide electric vehicle (EV) charging infrastructure network. Visit the Alternative Fuels Data Center for resources on EV infrastructure planning, including key considerations and best practices for navigating regulatory updates to streamline infrastructure build-out.

ADVANCED PROPULSION SYSTEMS↗

Providing a Service that Doubles the ISS Science Data Return

NASA’s missions rely on the Space Network to relay critical mission data to control centers and scientists here on Earth. The international Space Station is NASA’s most critical missions that relies on this network. The International Space Station plays a key role in the international science community, enabling human spaceflight, space and Earth science experiments, as well as technology demonstrations, in the space environment. The unique environment of the station’s approximately 250-mile-high orbit allows astronauts to conduct experiments which provide valuable insight in the fields of physics, biology, astronomy, meteorology and more. The station also transmits time-sensitive, mission-critical data like information about the crew’s health and the status of the station’s systems.

Barclay, Catherine B.↗

Do Neural Networks Trained with Topological Features Learn Different Internal Representations?

There is a growing body of work that leverages features extracted via topological data analysis to train machine learning models. While this field, sometimes known as topological machine learning (TML), has seen some notable successes, an understanding of how the process of learning from topological features differs from the process of learning from raw data is still limited. In this work, we begin to address one component of this larger issue by asking whether a model trained with topological features learns internal representations of data that are fundamentally different than those learned by a model trained with the original raw data. To quantify ``different'', we exploit two popular metrics that can be used to measure the similarity of the hidden representations of data within neural networks, neural stitching and centered kernel alignment. From these we draw a range of conclusions about how training with topological features does and does not change the representations that a model learns. Perhaps unsurprisingly, we find that structurally, the hidden representations of models trained and evaluated on topological features differ substantially compared to those trained and evaluated on the corresponding raw data. On the other hand, our experiments show that in some cases, these representations can be reconciled (at least to the degree required to solve the corresponding task) using a simple affine transformation. We conjecture that this means that neural networks trained on raw data may extract some limited topological features in the process of making predictions.

McGuire, Sarah L.↗

Design Concepts for a Small Space-Based GEO Relay Satellite for Missions Between Low Earth and near Earth Orbits

The main purpose of the Small Space-Based Geosynchronous Earth orbiting (GEO) satellite is to provide a space link to the user mission spacecraft for relaying data through ground networks to user Mission Control Centers. The Small Space Based Satellite (SSBS) will provide services comparable to those of a NASA Tracking Data Relay Satellite (TDRS) for the same type of links. The SSBS services will keep the user burden the same or lower than for TDRS and will support the same or higher data rates than those currently supported by TDRS. At present, TDRSS provides links and coverage below GEO; however, SSBS links and coverage capability to above GEO missions are being considered for the future, especially for Human Space Flight Missions (HSF). There is also a rising need for the capability to support high data rate links (exceeding 1 Gbps) for imaging applications. The communication payload on the SSBS will provide S/Ka-band single access links to the mission and a Ku-band link to the ground, with an optical communication payload as an option. To design the communication payload, various link budgets were analyzed and many possible operational scenarios examined. To reduce user burden, using a larger-sized antenna than is currently in use by TDRS was considered. Because of the SSBS design size, it was found that a SpaceX Falcon 9 rocket could deliver three SSBSs to GEO. This will greatly reduce the launch costs per satellite. Using electric propulsion was also evaluated versus using chemical propulsion; the power system size and time to orbit for various power systems were also considered. This paper will describe how the SSBS will meet future service requirements, concept of operations, and the design to meet NASA users' needs for below and above GEO missions. These users' needs not only address the observational mission requirements but also possible HSF missions to the year 2030. We will provide the trade-off analysis of the communication payload design in terms of the number of links looking above and below GEO; the detailed design of a GEO SSBS spacecraft bus and its accommodation of the communication payload, and a summary of the trade study that resulted in the selection of the Falcon 9 launch vehicle to deploy the SSBS and its impact on cost reductions per satellite. ======================================================================== Several initiatives have taken place within NASA1 and international space agencies2 to create a human exploration strategy for expanding human presence into the solar system; these initiatives have been driven by multiple factors to benefit Earth. Of the many elements in the strategy one stands out: to send robotic and human missions to destinations beyond Low Earth Orbit (LEO), including cis-lunar space, Near-Earth Asteroids (NEAs), the Moon, and Mars and its moons.3, 4 The time frame for human exploration to various destinations, based on the public information available,1,4 is shown in Figure 1. Advance planning is needed to define how future space communications services will be provided in the new budget environment to meet future space communications needs. The spacecraft for these missions can be dispersed anywhere from below LEO to beyond GEO, and to various destinations within the solar system. NASA's Space Communications and Navigation (SCaN) program office provides communication and tracking services to space missions during launch, in-orbit testing, and operation phases. Currently, SCaN's space networking relay satellites mainly provide services to users below GEO, at Near Earth Orbit (NEO), below LEO, and in deep space. The potential exists for using a space-based relay satellite, located in the vicinity of various solar system destinations, to provide communication space links to missions both below and above its orbit. Such relays can meet the needs of human exploration missions for maximum connectivity to Earth locations and for reduced latency. In the past, several studies assessed the ability of satellite-based relays working above GEO in conjunction with Earth ground stations. Many of these focused on the trade between space relay and direct-to-Earth station links5,6,7. Several others focused on top-level architecture based on relays at various destinations8,9,10,11,12. Much has changed in terms of microwave and optical technology since the publication of the referenced papers; Ka-band communication systems are being deployed, optical communication is being demonstrated, and spacecraft buses are becoming increasingly more functional and operational. A design concept study was undertaken to access the potential for deploying a Small Space-Based Satellite (SSBS) relay capable of serving missions between LEO and NEO. The needs of future human exploration missions were analyzed, and a notional relay-based architecture concept was generated as shown in Fig. 1. Relay satellites in Earth through cis-Lunar orbits are normally located in stable orbits requiring low fuel consumption. Relay satellites for Mars orbit are normally selected based on the mission requirement and projected fuel consumption. Relay satellites have extreme commonalities of functions between them, differing only in the redundancy and frequencies used; therefore, the relay satellite in GEO was selected for further analysis since it will be the first step in achieving a relay-based architecture for human exploration missions (see Fig.Figure 2). The mission design methodology developed by the Collaborative Modeling for Parametric Assessment of Space Systems (COMPASS) team13 was used to produce the satellite relay design and to perform various design trades. At the start of the activity, the team was provided with the detailed concept of the notional architecture and the system and communication payload drivers.

Relay Satellites↗

NSSDC provides network access to key data via NDADS

The National Space Science Data Center (NSSDC) is making a growing fraction of its most customer-desirable data electronically accessible via both the local and wide area networks. NSSDC is witnessing a great increase in its data dissemination owing to this network accessibility. To provide its customers the best data accessibility, the NSSDC makes data available from a nearline, mass storage system, the NSSDC Data Archive and Dissemination Service (NDADS). The NDADS, the initial version was made available in January 1992, is a customized system of hardware and software that provides users access to the nearline data via ANONYMOUS FTP, an e-mail interface (ARMS), and a C-based software library. In January 1992, the NDADS registered 416 requests for 1,957 files. By December of 1994, NDADS had been populated with 800 gigabytes of electronically accessible data and had registered 1458 requests for 20,887 files. In this report we describe the NDADS system, both hardware and software. Later in the report, we discuss some of the lessons that were learned as a result of operating NDADS, particularly in the area of ingest and dissemination.

Behnke, Jeanne↗

Optimizing End-to-End Big Data Transfers over Terabits Network Infrastructure

While future terabit networks hold the promise of significantly improving big-data motion among geographically distributed data centers, significant challenges must be overcome even on today's 100 gigabit networks to realize end-to-end performance. Multiple bottlenecks exist along the end-to-end path from source to sink, for instance, the data storage infrastructure at both the source and sink and its interplay with the wide-area network are increasingly the bottleneck to achieving high performance. In this study, we identify the issues that lead to congestion on the path of an end-to-end data transfer in the terabit network environment, and we present a new bulk data movement framework for terabit networks, called LADS. LADS exploits the underlying storage layout at each endpoint to maximize throughput without negatively impacting the performance of shared storage resources for other users. LADS also uses the Common Communication Interface (CCI) in lieu of the sockets interface to benefit from hardware-level zero-copy, and operating system bypass capabilities when available. It can further improve data transfer performance under congestion on the end systems using buffering at the source using flash storage. With our evaluations, we show that LADS can avoid congested storage elements within the shared storage resource, improving input/output bandwidth, and data transfer rates across the high speed networks. We also investigate the performance degradation problems of LADS due to I/O contention on the parallel file system (PFS), when multiple LADS tools share the PFS. We design and evaluate a meta-scheduler to coordinate multiple I/O streams while sharing the PFS, to minimize the I/O contention on the PFS. Finally, with our evaluations, we observe that LADS with meta-scheduling can further improve the performance by up to 14 percent relative to LADS without meta-scheduling.

97 MATHEMATICS AND COMPUTING↗

Future SDN-HPON Control Plane Architecture and Protocol for On-Demand Terabit End-to-End Extreme-Scale Science Applications

The UC Davis team conducted architecture, algorithm and experimental studies for next generation ultra-high-bandwidth optical networks in support of extreme-scale science applications. In particular, over the course of this 3-year project, the UC Davis team achieved the following main accomplishments: Designed a network architecture for automated multi-domain service provisioning: Designed information exchange schemes between autonomous systems (domains) Designed application programming interfaces to orchestrate resource reservation in data centers, high performance computation facilities, and communication networks belonging to different autonomous systems Experimentally assessed the multi-domain network architecture in a distributed field trial set-up connecting premises in three continents Designed a broker-based orchestrated multi-domain optical networking framework supporting observe-analyze-act cycle based cognitive inter-domain service provisioning: Designed an inter-domain operation mechanism, e.g., topology abstraction, for the broker plane and domain managers to collaboratively accomplish inter-domain service provisioning while respecting the autonomy of each administrative domain Designed an alien wavelength monitoring scheme and an artificial neural network based optical signal-to-noise ratio estimator for quality-of-transmission aware inter-domain service provisioning Developed a deep neural network based multi-domain traffic predictor and a cognitive routing and spectrum assignment algorithm to realize knowledge-based autonomous traffic engineering in multi-domain networks Implemented an optical signal-to-noise ratio estimator and traffic predictor with Google’s Tensor flow and assessed their performance using experimental and synthetic data Demonstrated the benefits of the proposed cognitive schemes with experiments ona two-domain elastic optical network testbed and evaluations on a six-domain simulation framework Built a two-domain software-defined networking control plane testbed using the ONOS platform and demonstrated the workflow of broker and domain manager cooperation, including hierarchical performance monitoring, topology abstraction and cognitive resource allocation. Designed self-learning cognitive service provisioning schemes using advanced machine learning technologies: Designed a self-taught anomaly detection framework for optical networks, including an unsupervised data clustering module for pattern recognition, a supervised data regression and classification module for online anomaly detection, and the system operation principle Experimentally validated the effectiveness of the self-taught anomaly detection framework with various failure/anomaly scenarios. Designed a self-learning autonomic routing, modulation and spectrum assignment (RMSA) provisioning framework for elastic optical networks with deep reinforcement learning. Designed effective modeling and training mechanisms for the self-learning RMSA framework Conducted extensive numerical simulations with various traffic patterns and topologies to verify the advantage of the self-learning RMSA framework.

42 ENGINEERING↗

Rapid Calculation of Max-Min Fair Rates for Multi-Commodity Flows in Fat-Tree Networks

Max-min fairness is often used in the performance modeling of interconnection networks. Existing methods to compute max-min fair rates for multi-commodity flows have high complexity and are computationally infeasible for large networks. In this paper, we show that by considering topological features, this problem can be solved efficiently for the fat-tree topology that is widely used in data centers and high performance compute clusters. Several efficient new algorithms are developed for this problem, including a parallel algorithm that can take advantage of multi-core and shared-memory architectures. Using these algorithms, we demonstrate that it is possible to find the max-min fair rate allocation for multi-commodity flows in fat-tree networks that support tens of thousands of nodes. We evaluate the run-time performance of the proposed algorithms and show improvement in orders of magnitude over the previously best known method. Finally, we further demonstrate a new application of max-min fair rate allocation that is only computationally feasible using our new algorithms.

97 MATHEMATICS AND COMPUTING↗

LADS: Optimizing Data Transfers using Layout-Aware Data Scheduling

While future terabit networks hold the promise of signifi- cantly improving big-data motion among geographically distributed data centers, significant challenges must be overcome even on today s 100 gigabit networks to real- ize end-to-end performance. Multiple bottlenecks exist along the end-to-end path from source to sink. Data stor- age infrastructure at both the source and sink and its in- terplay with the wide-area network are increasingly the bottleneck to achieving high performance. In this paper, we identify the issues that lead to congestion on the path of an end-to-end data transfer in the terabit network en- vironment, and we present a new bulk data movement framework called LADS for terabit networks. LADS ex- ploits the underlying storage layout at each endpoint to maximize throughput without negatively impacting the performance of shared storage resources for other users. LADS also uses the Common Communication Interface (CCI) in lieu of the sockets interface to use zero-copy, OS-bypass hardware when available. It can further im- prove data transfer performance under congestion on the end systems using buffering at the source using flash storage. With our evaluations, we show that LADS can avoid congested storage elements within the shared stor- age resource, improving I/O bandwidth, and data transfer rates across the high speed networks.

Data Management↗

SU-E-T-52: Beam Data Comparison for 20 Linear Accelerators in One Network

Purpose: To compare photon beam data for the 20 Varian linear accelerators (TrueBeam, iX, and EX models) in use at five centers in the same network with the intent to model with one set of beam data in Eclipsec. Methods: Varian linear accelerators, TrueBeam (3), 21 EX, iX, and Trilogy (14), and 6 EX (3), installed between 1999 and 2014 have their 6 MV and 15 MV x-ray beams reevaluated. Full commissioning, including output factors (St), percent depth doses (PDD), and off-axis profiles, was recently performed for a TrueBeam with a cc04 ion chamber in an IBA Blue phantom. Similarly, a subset of beam data for each of the other accelerators was measured recently as follows: for 3×3, 10×10, and 30×30 cm{sup 2} field sizes, flatness and penumbra (80–20%) were measured at dmax and 10 cm depths, PDD were measured at 10 and 20 cm depths, and St were measured at 5 cm depth. Measurement results for all machines were compared. Results: For 15 high-energy (6 and 15 MV) and 3 low-energy machines (6MV only): 1) PDD agreed within 1.4% at 10 and 20 cm depths; 2) penumbra agreed within 1.0 mm at dmax and 10 cm depths; 3) flatness was within 1.3% at dmax and 10 cm depths; and 4) with exception of the three low energy machines, output factors were within 1.1% and 0.5% for 3×3 and 30×30 cm{sup 2}, respectively. Measurement uncertainty, not quantified here, accounts for some of these differences. Conclusion: Measured beam data from 15 high-energy Varian linacs are consistent enough that they can be classified using one beam data set in Eclipse. Two additional high-energy machines are removed from this group until their data are further confirmed. Three low-energy machines will be in a separate class based upon differences in output factors (St)

07 ISOTOPE AND RADIATION SOURCES↗

Optimal environmental and economic performance trade-offs for fifth generation district heating and cooling network topologies with waste heat recovery

Network topology greatly influences both the economic and environmental performance of fifth generation district heating and cooling (5GDHC) systems. In this study the optimal trade-offs between the environmental and economic performance of 5GDHC network topologies for a five-building district with waste heat recovery were explored. A life cycle assessment method was used to calculate the total life cycle CO 2 emissions (LCCO2) associated with the installation and operation of various network topologies. Twelve months of empirical data from a data center cooling system were analyzed to assess its suitability for integration into a 5GDHC system. The most suitable method for utilizing this waste heat was selected based on the ambient loop warm pipe setpoint, waste heat temperature, and district energy system configuration. A multi-objective optimization algorithm was used to select the 5GDHC network topology that provided the optimal trade-off between LCCO2 and life cycle cost (LCC). A trade-off parameter was employed to weigh the importance of each objective in the selection process. The results showed waste heat from the data center was suitable for integration into the 5GDHC system due to its availability and consistent temperature profile. When return temperatures of 25 °C or higher were available from the liquid-cooled system, direct pre-heating of the ambient loop warm pipe was found to be the most effective waste heat integration method. The selection of the network topology that provided the optimal trade-off between LCCO2 and LCC (optimal trade-off topology) was highly dependent on factors such as fuel prices, CO 2 prices, electricity CO 2 emissions factors, availability of waste heat, embodied CO 2 emissions associated with network installation and network infrastructure costs. Optimal trade-off topologies produced substantial LCCO2 reductions relative to corresponding LCC increases. LCCO2 reduction to LCC increase ratios from 5.78 to 117.79 were identified with CO 2 offset costs ranging from 4.77 to 60.08 ($/tCO 2 e).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Secure Peer-to-Peer Networks for Scientific Information Sharing

The most common means of remote scientific collaboration today includes the trio of e-mail for electronic communication, FTP for file sharing, and personalized Web sites for dissemination of papers and research results. With the growth of broadband Internet, there has been a desire to share large files (movies, files, scientific data files) over the Internet. Email has limits on the size of files that can be attached and transmitted. FTP is often used to share large files, but this requires the user to set up an FTP site for which it is hard to set group privileges, it is not straightforward for everyone, and the content is not searchable. Peer-to-peer technology (P2P), which has been overwhelmingly successful in popular content distribution, is the basis for development of a scientific collaboratory called Scientific Peer Network (SciPerNet). This technology combines social networking with P2P file sharing. SciPerNet will be a standalone application, written in Java and Swing, thus insuring portability to a number of different platforms. Some of the features include user authentication, search capability, seamless integration with a data center, the ability to create groups and social networks, and on-line chat. In contrast to P2P networks such as Gnutella, Bit Torrent, and others, SciPerNet incorporates three design elements that are critical to application of P2P for scientific purposes: User authentication, Data integrity validation, Reliable searching SciPerNet also provides a complementary solution to virtual observatories by enabling distributed collaboration and sharing of downloaded and/or processed data among scientists. This will, in turn, increase scientific returns from NASA missions. As such, SciPerNet can serve a two-fold purpose for NASA: a cost-savings software as well as a productivity tool for scientists working with data from NASA missions.

Karimabadi, Homa↗