Search NASA⌕ Search

SEARCH · Search NASA

Results for “Fault Tolerant Algorithms”

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.

409 records · Page 23

Navigation Strategy for the Mars 2001 Lander Mission

The Mars Surveyor Program (MSP) is an ongoing series of missions designed to robotically study, map and search for signs of life on the planet Mars. The MSP 2001 project will advance the effort by sending an orbiter, a lander and a rover to the red planet in the 2001 opportunity. Each vehicle will carry a science payload that will Investigate the Martian environment on both a global and on a local scale. Although this mission will not directly search for signs of life, or cache samples to be returned to Earth, it will demonstrate certain enabling technologies that will be utilized by the future Mars Sample Return missions. One technology that is needed for the Sample Return mission is the capability to place a vehicle on the surface within several kilometers of the targeted landing site. The MSP'01 Lander will take the first major step towards this type of precision landing at Mars. Significant reduction of the landed footprint will be achieved through two technology advances. The first, and most dramatic, is hypersonic aeromaneuvering; the second is improved approach navigation. As a result, the guided entry will produce in a footprint that is only tens of kilometers, which is an order of magnitude improvement over the Pathfinder and Mars Polar Lander ballistic entries. This reduction will significantly enhance scientific return by enabling the potential selection of otherwise unreachable landing sites with unique geologic interest and public appeal. A landed footprint reduction from hundreds to tens of kilometers is also a milestone on the path towards human exploration of Mars, where the desire is to place multiple vehicles within several hundred meters of the planned landing site. Hypersonic aeromaneuvering is an extension of the atmospheric flight goals of the previous landed missions, Pathfinder and Mars Polar Lander (MPL), that utilizes aerodynamic lift and an autonomous guidance algorithm while in the upper atmosphere. The onboard guidance algorithm will control the direction of the lift vector, via bank angle modulation, to keep the vehicle on the desired trajectory. While numerous autonomous guidance algorithms have been developed for use during hypersonic flight at Earth, this will be the first flight of an autonomously directed lifting entry vehicle at Mars. However, without sufficient control and knowledge of the atmospheric entry conditions, the guidance algorithm will not perform effectively. The goal of the interplanetary navigation strategy is to deliver the spacecraft to the desired entry condition with sufficient accuracy and knowledge to enable satisfactory guidance algorithm performance. Specifically, the entry flight path angle must not exceed 0.27 deg. to a 3 sigma confidence level. Entry errors will contribute directly to the size of the landed footprint and the most significant component is entry flight path angle. The size of the entry corridor is limited on the shallow side by integrated heating constraints, and on the steep side by deceleration (g-load) and terminal descent propellant. In order to meet this tight constraint it is necessary to place a targeting maneuver seven hours prior to the time of entry. At this time the trajectory knowledge will be quite accurate, and the effects of maneuver execution errors will be small. The drawback is that entry accuracy is dependent on the success of this final late maneuver. Because propulsive maneuvers are critical events, it is desirable to minimize their occurrence and provide the flight team with as much response time as possible in the event of a spacecraft fault. A mission critical maneuver at Entry - 7 hours does not provide much fault tolerance, and it is desirable to provide a strategy that minimizes reliance on this maneuver. This paper will focus on the Improvements in interplanetary navigation that will decrease entry errors and will reduce the landed footprint, even in the absence of aeromaneuvering. The easiest to take advantage of are Improvements In the knowledge of the Mars ephemeris and gravity field due to the MGS and MSP'98 missions. Improvements In data collection and reduction techniques such as "precislon ranging' and near-simultaneous tracking will also be utilized. In addition to precise trajectory control, a robust strategy for communications and flight operations must also be demonstrated. The result Is a navigation and communications strategy on approach that utilizes optimal maneuver placement to take advantage of trajectory knowledge, minimizes risk for the flight operations team, is responsive to spacecraft hardware limitations, and achieves the entry corridor. The MSP2001 mission Is managed at JPL under the auspices of the Mars Exploration Directorate. The spacecraft flight elements are built and managed by Lockheed-Martin Astronautics in Denver, Colorado.

Mase, Robert A.↗

NASA Tech Briefs, November 1995

The contents include: 1) Mission Accomplished; 2) Resource Report: Marshall Space Flight Center; 3) NASA 1995 Software of the Year Award; 4) Microbolometers Based on Epitaxial YBa2Cu3O(sub 7-x) Thin Films; 5) Garnet Random-Access Memory; 6) Fabrication of SNS Weak Links on SOS Substrates; 7) High-Voltage MOSFET Switching Circuit; 8) Asymmetric Switching for a PWM H-Bridge Power Circuit; 9) Better Ohmic Contacts for InP Semiconductor Devices; 10) Low-Bandgap Thermovoltaic Materials and Devices; 11) Digital Frequency-Differencing Circuit; 12) Imaging Magnetometer; 13) Computer-Assisted Monitoring of a Complex System; 14) Buffered Telemetry Demodulator; 15) Compact Multifunction Inspection Head; 16) Optical Detection of Fractures in Ceramic Diaphragms; 17) Eddy-Current Detection of Cracks in Reinforced Carbon/Carbon; 18) Apparent Thermal Conductivity of Multilayer Insulation; 19) Optimizing Misch-Metal Compositions in Metal Hydride Anodes; 20) Device for Sampling Surface Contamination; 21) Probabilistic Failure Assessment for Fatigue; 22) Probabilistic Fatigue and Flaw-Propagation Analysis; 23) Windows Program for Driving the TDU-850 Printer; 24) Subband/Transform MATLAB Functions for Processing Images; 25) Computing Equilibrium Chemical Compositions; 26) Program Processes Thermocouple Readings; 27) ICAN-Second-Generation Integrated Composite Analyzer; 28) Integrated Composite Analyzer with Damping Capabilities; 29) Computing Efficiency of Transfer of Microwave Power; 30) Program Calculates Power Demands of Electronic Designs; 31) Cost-Estimation Program; 32) Program Estimates Areas Required by Electronic Designs; 33) Program to Balance Mapped Turbopump Assemblies; 34) BiblioTech; 35) Controlling Mirror Tilt With a Bimorph Actuator; 36) Burst-Disk Device Simulates Effect of Pyrotechnic Device; 37) Bearing-Mounting Concept Accommodates Thermal Expansion; 38) Parallel-Plate Acoustic Absorbers for Hot Environments; 39) Adjustable-Length Strut Withstands Large Cyclic Loads; 40) Tool Indicates Contact Angles in Bearing Raceways; 41) Gravity Slides With Magnetic Braking; 42) High-Torque, Lightweight, Pneumatically Driven Wrench for Small Spaces; 43) Device for Testing Compatibility of an O-Ring; 44) Magnetic Heat Pump Containing Flow Diverters; 45) Variable-Tilt Helicopter Rotor Mast; 46) "Beach-Ball" Robotic Rovers; 47) Apparatus Would Measure Temperatures of Ball Bearings; 48) Flexible Borescope for Inspecting Ducts; 49) Texturing Copper To Reduce Secondary Emission of Electrons; 50) Automated Laser Cutting in Three Dimensions; 51) Algorithm Helps Monitor Engine Operation; 52) Flexible Revision of Data-Processing Communications; 53) Software for Managing the Use of Land; 54) Thermal Strap Increases Cryocooling Efficiency; 55) Reversible Nut With Engagement Indication; 56) Control Algorithms for Kinematically Redundant Manipulators; 57) Computed Hydrogen-Flow Splits in a Rocket Engine; 58) Pressure and Thermal Modeling of Rocket Launches; 59) Field of View of a Spacecraft Antenna: Analysis and Software; 60) Digital Controller for Laser-Beam-Steering Subsystem; 61) More About Beam-Steering Subsystem for Laser Communication; 62) Digital Controller for Laser-Beam-Steering Subsystem: Part 2; 63) Interface Circuit Board for Space-Shuttle Communications; 64) Automated Planning of Spacecraft Telecommunications; 65) Artifacts of Spectral Analysis of Instrument Readings; 66) Neural-Network Controller for Vibration Suppression; 67) Adaptive Finite-Element Computation in Fracture Mechanics; 68) Attitude Control for the Cassini Spacecraft; 69) Analytical Model for Fluid Dynamics in a Microgravity Environment; 70) Study of Rocket-Engine Joints Bonded by NVCU/NARloy-Z; 71) Improved Silicon Nitride for Advanced Heat Engines; 72) Parameters for Welding Aluminum/Lithium Alloys; 73) Lightweight Composite Intertank Structure; 74) Foil Patches Seal Small Vacuum Leaks; 75) Data Base on Cables and Connectors; 76) Effect of Clock Mode on Radiation Hardnessf an ADC; and 77) Fault-Tolerant Control for a Robotic Inspection System.

Source record↗

Control Algorithms and Simulated Environment Developed and Tested for Multiagent Robotics for Autonomous Inspection of Propulsion Systems

The NASA Glenn Research Center and academic partners are developing advanced multiagent robotic control algorithms that will enable the autonomous inspection and repair of future propulsion systems. In this application, on-wing engine inspections will be performed autonomously by large groups of cooperative miniature robots that will traverse the surfaces of engine components to search for damage. The eventual goal is to replace manual engine inspections that require expensive and time-consuming full engine teardowns and allow the early detection of problems that would otherwise result in catastrophic component failures. As a preliminary step toward the long-term realization of a practical working system, researchers are developing the technology to implement a proof-of-concept testbed demonstration. In a multiagent system, the individual agents are generally programmed with relatively simple controllers that define a limited set of behaviors. However, these behaviors are designed in such a way that, through the localized interaction among individual agents and between the agents and the environment, they result in self-organized, emergent group behavior that can solve a given complex problem, such as cooperative inspection. One advantage to the multiagent approach is that it allows for robustness and fault tolerance through redundancy in task handling. In addition, the relatively simple agent controllers demand minimal computational capability, which in turn allows for greater miniaturization of the robotic agents.

Wong, Edmond↗

Intelligent Systems for Self-Healing Electronics

For long duration missions it is imperative to be able to monitor and record critical information. The data acquisition systems used must therefore be fault tolerant. This usually meant having redundant copies of critical channels. Since each channel usually consists of various components, the parts count, cost, weight and complexity of the system could be very high. The Advanced Data Acquisition System (ADAS) has been developed as a proof of concept. The purpose was to demonstrate an architecture where individual spare parts can replace defective ones to repair a channel. By so doing entire channels do not need replication. This reduces the need of total redundancy and reduces the parts count. This has the added feature that in addition to spare parts, good components of a failed channel can be used as spares in another channel. In addition to reducing parts count and cost, this configuration, with an intelligent decision maker, can improve the reliability of the overall system. Another unique feature of ADAS is that it uses reconfigurable analog filters. These components can be programmed, by the smart system to meet the specific needs of the part they are to replace. This way one part can serve as spare for many different components. The hardware was built and now serves as a platform for developing intelligent algorithms. Another related project was a wireless data acquisition system. I was invited to participate in the meetings and issue suggestions. A brief description of this system will also be included.

Latino, Carl D.↗

SU-G-BRB-16: Vulnerabilities in the Gamma Metric

Purpose: To explore vulnerabilities in the gamma index metric that undermine its wide use as a radiation therapy quality assurance tool. Methods: 2D test field pairs (images) are created specifically to achieve high gamma passing rates, but to also include gross errors by exploiting the distance-to-agreement and percent-passing components of the metric. The first set has no requirement of clinical practicality, but is intended to expose vulnerabilities. The second set exposes clinically realistic vulnerabilities. To circumvent limitations inherent to user-specific tuning of prediction algorithms to match measurements, digital test cases are manually constructed, thereby mimicking high-quality image prediction. Results: With a 3 mm distance-to-agreement metric, changing field size by ±6 mm results in a gamma passing rate over 99%. For a uniform field, a lattice of passing points spaced 5 mm apart results in a passing rate of 100%. Exploiting the percent-passing component, a 10×10 cm{sup 2} field can have a 95% passing rate when an 8 cm{sup 2}=2.8×2.8 cm{sup 2} highly out-of-tolerance (e.g. zero dose) square is missing from the comparison image. For clinically realistic vulnerabilities, an arc plan for which a 2D image is created can have a >95% passing rate solely due to agreement in the lateral spillage, with the failing 5% in the critical target region. A field with an integrated boost (e.g whole brain plus small metastases) could neglect the metastases entirely, yet still pass with a 95% threshold. All the failure modes described would be visually apparent on a gamma-map image. Conclusion: The %gamma<1 metric has significant vulnerabilities. High passing rates can obscure critical faults in hypothetical and delivered radiation doses. Great caution should be used with gamma as a QA metric; users should inspect the gamma-map. Visual analysis of gamma-maps may be impractical for cine acquisition.

60 APPLIED LIFE SCIENCES↗

Modular Quantum Processor with an All-to-All Reconfigurable Router

Superconducting qubits provide a promising approach to large-scale fault-tolerant quantum computing. However, qubit connectivity on a planar surface is typically restricted to only a few neighboring qubits. Achieving longer-range and more flexible connectivity, which is particularly appealing in light of recent developments in error-correcting codes, however, usually involves complex multilayer packaging and external cabling, which is resource intensive and can impose fidelity limitations. Here, we propose and realize a high-speed on-chip quantum processor that supports reconfigurable all-to-all coupling with a large on-off ratio. We implement the design in a four-node quantum processor, built with a modular design comprising a wiring substrate coupled to two separate qubit-bearing substrates, each including two single-qubit nodes. We use this device to demonstrate reconfigurable controlled-𝑍 gates across all qubit pairs, with a benchmarked average fidelity of 96.00% ± 0.08% and best fidelity of 97.14% ± 0.07%, limited mainly by dephasing in the qubits. We also generate multiqubit entanglement, distributed across the separate modules, demonstrating GHZ-3 and GHZ-4 states with fidelities of 88.15% ± 0.24% and 75.18% ± 0.11%, respectively. This approach promises efficient scaling to larger-scale quantum circuits and offers a pathway for implementing quantum algorithms and error-correction schemes that benefit from enhanced qubit connectivity.

Quantum circuits↗

Programmer-guided reliability for extreme-scale applications

We present “programmer-guided reliability” (PGR) as a systematic conceptual approach to address the expected rise in soft errors in coming extreme-scale systems at the application level. The approach involves instrumentation of the application with code to detect data corruption errors. The location and nature of these error detectors are at the discretion of the programmer, who uses their knowledge and experience with the problem domain, the application, the solution algorithms, etc., to determine the most vulnerable areas of the code and the most appropriate ways to detect data corruption. To illustrate the approach, we provide examples of error detectors from four different benchmark-scale applications. We also describe a simple control framework that allows for runtime configuration of the error detectors without recompilation of the application, as well as dynamic reconfiguration during the execution of the application. Lastly, we discuss a number of future directions building on the basic PGR approach, including the incorporation of some general error detectors into the programming environment in order to make them more easily usable by the programmer.

97 MATHEMATICS AND COMPUTING↗

Energy Proportionality and Performance in Data Parallel Computing Clusters

Energy consumption in datacenters has recently become a major concern due to the rising operational costs andscalability issues. Recent solutions to this problem propose the principle of energy proportionality, i.e., the amount of energy consumedby the server nodes must be proportional to the amount of work performed. For data parallelism and fault tolerancepurposes, most common file systems used in MapReduce-type clusters maintain a set of replicas for each data block. A coveringset is a group of nodes that together contain at least one replica of the data blocks needed for performing computing tasks. In thiswork, we develop and analyze algorithms to maintain energy proportionality by discovering a covering set that minimizesenergy consumption while placing the remaining nodes in lowpower standby mode. Our algorithms can also discover coveringsets in heterogeneous computing environments. In order to allow more data parallelism, we generalize our algorithms so that itcan discover k-covering sets, i.e., a set of nodes that contain at least k replicas of the data blocks. Our experimental results showthat we can achieve substantial energy saving without significant performance loss in diverse cluster configurations and workingenvironments.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA Tech Briefs, January 2013

Topics include: Single-Photon-Sensitive HgCdTe Avalanche Photodiode Detector; Surface-Enhanced Raman Scattering Using Silica Whispering-Gallery Mode Resonators; 3D Hail Size Distribution Interpolation/Extrapolation Algorithm; Color-Changing Sensors for Detecting the Presence of Hypergolic Fuels; Artificial Intelligence Software for Assessing Postural Stability; Transformers: Shape-Changing Space Systems Built with Robotic Textiles; Fibrillar Adhesive for Climbing Robots; Using Pre-Melted Phase Change Material to Keep Payloads in Space Warm for Hours without Power; Development of a Centrifugal Technique for the Microbial Bioburden Analysis of Freon (CFC-11); Microwave Sinterator Freeform Additive Construction System (MS-FACS); DSP/FPGA Design for a High-Speed Programmable S-Band Space Transceiver; On-Chip Power-Combining for High-Power Schottky Diode-Based Frequency Multipliers; FPGA Vision Data Architecture; Memory Circuit Fault Simulator; Ultra-Compact Transputer-Based Controller for High-Level, Multi-Axis Coordination; Regolith Advanced Surface Systems Operations Robot Excavator; Magnetically Actuated Seal; Hybrid Electrostatic/Flextensional Mirror for Lightweight, Large-Aperture, and Cryogenic Space Telescopes; System for Contributing and Discovering Derived Mission and Science Data; Remote Viewer for Maritime Robotics Software; Stackfile Database; Reachability Maps for In Situ Operations; JPL Space Telecommunications Radio System Operating Environment; RFI-SIM: RFI Simulation Package; ION Configuration Editor; Dtest Testing Software; IMPaCT - Integration of Missions, Programs, and Core Technologies; Integrated Systems Health Management (ISHM) Toolkit; Wind-Driven Wireless Networked System of Mobile Sensors for Mars Exploration; In Situ Solid Particle Generator; Analysis of the Effects of Streamwise Lift Distribution on Sonic Boom Signature; Rad-Tolerant, Thermally Stable, High-Speed Fiber-Optic Network for Harsh Environments; Towed Subsurface Optical Communications Buoy; High-Collection-Efficiency Fluorescence Detection Cell; Ultra-Compact, Superconducting Spectrometer-on-a-Chip at Submillimeter Wavelengths; UV Resonant Raman Spectrometer with Multi-Line Laser Excitation; Medicine Delivery Device with Integrated Sterilization and Detection; Ionospheric Simulation System for Satellite Observations and Global Assimilative Model Experiments - ISOGAME; Airborne Tomographic Swath Ice Sounding Processing System; flexplan: Mission Planning System for the Lunar Reconnaissance Orbiter; Estimating Torque Imparted on Spacecraft Using Telemetry; PowderSim: Lagrangian Discrete and Mesh-Free Continuum Simulation Code for Cohesive Soils; Multiple-Frame Detection of Subpixel Targets in Thermal Image Sequences; Metric Learning to Enhance Hyperspectral Image Segmentation; Basic Operational Robotics Instructional System; Sheet Membrane Spacesuit Water Membrane Evaporator; Advanced Materials and Manufacturing for Low-Cost, High-Performance Liquid Rocket Combustion Chambers; Motor Qualification for Long-Duration Mars Missions.

Source record↗

Modular Battery Charge Controller

A new approach to masterless, distributed, digital-charge control for batteries requiring charge control has been developed and implemented. This approach is required in battery chemistries that need cell-level charge control for safety and is characterized by the use of one controller per cell, resulting in redundant sensors for critical components, such as voltage, temperature, and current. The charge controllers in a given battery interact in a masterless fashion for the purpose of cell balancing, charge control, and state-of-charge estimation. This makes the battery system invariably fault-tolerant. The solution to the single-fault failure, due to the use of a single charge controller (CC), was solved by implementing one CC per cell and linking them via an isolated communication bus [e.g., controller area network (CAN)] in a masterless fashion so that the failure of one or more CCs will not impact the remaining functional CCs. Each micro-controller-based CC digitizes the cell voltage (V(sub cell)), two cell temperatures, and the voltage across the switch (V); the latter variable is used in conjunction with V(sub cell) to estimate the bypass current for a given bypass resistor. Furthermore, CC1 digitizes the battery current (I1) and battery voltage (V(sub batt) and CC5 digitizes a second battery current (I2). As a result, redundant readings are taken for temperature, battery current, and battery voltage through the summation of the individual cell voltages given that each CC knows the voltage of the other cells. For the purpose of cell balancing, each CC periodically and independently transmits its cell voltage and stores the received cell voltage of the other cells in an array. The position in the array depends on the identifier (ID) of the transmitting CC. After eight cell voltage receptions, the array is checked to see if one or more cells did not transmit. If one or more transmissions are missing, the missing cell(s) is (are) eliminated from cell-balancing calculations. The cell-balancing algorithm is based on the error between the cell s voltage and the other cells and is categorized into four zones of operation. The algorithm is executed every second and, if cell balancing is activated, the error variable is set to a negative low value. The largest error between the cell and the other cells is found and the zone of operation determined. If the error is zero or negative, then the cell is at the lowest voltage and no balancing action is needed. If the error is less than a predetermined negative value, a Cell Bad Flag is set. If the error is positive, then cell balancing is needed, but a hysteretic zone is added to prevent the bypass circuit from triggering repeatedly near zero error. This approach keeps the cells within a predetermined voltage range.

Button, Robert↗

Mars, the Moon, and the Ends of the Earth: Autonomy for Small Reactor Power Systems

In recent years, the National Aeronautics and Space Administration (NASA) has been considering deep space missions that utilize a small-reactor power system (SRPS) to provide energy for propulsion and spacecraft power. Additionally, application of SRPS modules as a planetary power source is being investigated to enable a continuous human presence for nonpolar lunar sites and on Mars. A SRPS can supply high-sustained power for space and surface applications that is both reliable and mass efficient. The use of small nuclear reactors for deep space or planetary missions presents some unique challenges regarding the operations and control of the power system. Current-generation terrestrial nuclear reactors employ varying degrees of human control and decision-making for operations and benefit from periodic human interaction for maintenance. In contrast, the control system of a SRPS employed for deep space missions must be able to accommodate unattended operations due to communications delays and periods of planetary occlusion while adapting to evolving or degraded conditions with no opportunity for repair or refurbishment. While surface power systems for planetary outposts face less extreme delays and periods of isolation and may benefit from limited maintenance capabilities, considerations such as human safety, resource limitations and usage priorities, and economics favor minimizing direct, continuous human interaction with the SRPS for online, dedicated power system management. Thus, a SRPS control system for space or planetary missions must provide capabilities for operational autonomy. For terrestrial reactors, large-scale power plants remain the preferred near-term option for nuclear power generation. However, the desire to reduce reliance on carbon-emitting power sources in developing countries may lead to increased consideration of SRPS modules for local power generation in remote regions that are characterized by emerging, less established infrastructures. Additionally, many Generation IV (Gen IV) reactor concepts have goals for optimizing investment recovery and economic efficiency that promote significant reductions in plant operations and maintenance staff over current-generation nuclear power plants. To accomplish these Gen IV goals and also address the SRPS remote-siting challenges, higher levels of automation, fault tolerance, and advanced diagnostic capabilities are needed to provide nearly autonomous operations with anticipatory maintenance. Essentially, the SRPS control system for several anticipated terrestrial applications can benefit from the kind of operational autonomy that is necessary for deep space and planetary SRPS-enabled missions. Investigation of the state of the technology for autonomous control confirmed that control systems with varying levels of autonomy have been employed in robotic, transportation, spacecraft, and manufacturing applications. As an example, NASA has pursued autonomy for spacecraft and surface exploration vehicles (e.g., rovers) to reduce mission costs, increase efficiency for communications between ground control and the vehicle, and enable independent operation of the vehicle during times of communications blackout. However, autonomous control has not been implemented for an operating terrestrial nuclear power plant nor has there been any experience beyond automating simple control loops for space reactors. Current automated control technologies for nuclear power plants are reasonably mature, and fully automated control of normal SRPS operations is clearly feasible. However, the space-based and remote terrestrial applications of SRPS modules require autonomous capabilities that can accommodate nonoptimum operations when degradation, failure, and other off-normal events challenge the performance of the reactor while immediate human intervention is not possible. The independent action provided by autonomous control, which is distinct from the more limited self action of automated control, can satisfy these conditions. Key characteristics that distinguish autonomous control include: (1) intelligence to confirm system performance and detect degraded or failed conditions, (2) optimization to minimize stress on SRPS components and efficiently react to operational events without compromising system integrity, (3) robustness to accommodate uncertainties and changing conditions, and (4) flexibility and adaptability to accommodate failures through reconfiguration among available control system elements or adjustment of control system strategies, algorithms, or parameters.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Coping with silent and fail-stop errors at scale by combining replication and checkpointing

This paper provides a model and an analytical study of replication as a technique to cope with silent errors, as well as a mixture of both silent and fail-stop errors on large-scale platforms. Compared with fail-stop errors that are immediately detected when they occur, silent errors require a detection mechanism. To detect silent errors, many application-specific techniques are available, either based on algorithms (e.g., ABFT), invariant preservation or data analytics, but replication remains the most transparent and least intrusive technique. We explore the right level (duplication, triplication or more) of replication for two frameworks: (i) when the platform is subject to only silent errors, and (ii) when the platform is subject to both silent and fail-stop errors. A higher level of replication is more expensive in terms of resource usage but enables to tolerate more errors and to even correct some errors, hence there is a trade-off to be found. Replication is combined with checkpointing and comes with two flavors: process replication and group replication. Process replication applies to message-passing applications with communicating processes. Each process is replicated, and the platform is composed of process pairs, or triplets. Group replication applies to black-box applications, whose parallel execution is replicated several times. The platform is partitioned into two halves (or three thirds). In both scenarios, results are compared before each checkpoint, which is taken only when both results (duplication) or two out of three results (triplication) coincide. Otherwise, one or more silent errors have been detected, and the application rolls back to the last checkpoint, as well as when fail-stop errors have struck. We provide a detailed analytical study for all of these scenarios, with formulas to decide, for each scenario, the optimal parameters as a function of the error rate, checkpoint cost, and platform size. We also report a set of extensive simulation results that nicely corroborates the analytical model.

Checkpointing↗

Update on Development of SiC Multi-Chip Power Modules

Progress has been made in a continuing effort to develop multi-chip power modules (SiC MCPMs). This effort at an earlier stage was reported in 'SiC Multi-Chip Power Modules as Power-System Building Blocks' (LEW-18008-1), NASA Tech Briefs, Vol. 31, No. 2 (February 2007), page 28. The following recapitulation of information from the cited prior article is prerequisite to a meaningful summary of the progress made since then: 1) SiC MCPMs are, more specifically, electronic power-supply modules containing multiple silicon carbide power integrated-circuit chips and silicon-on-insulator (SOI) control integrated-circuit chips. SiC MCPMs are being developed as building blocks of advanced expandable, reconfigurable, fault-tolerant power-supply systems. Exploiting the ability of SiC semiconductor devices to operate at temperatures, breakdown voltages, and current densities significantly greater than those of conventional Si devices, the designs of SiC MCPMs and of systems comprising multiple SiC MCPMs are expected to afford a greater degree of miniaturization through stacking of modules with reduced requirements for heat sinking; 2) The stacked SiC MCPMs in a given system can be electrically connected in series, parallel, or a series/parallel combination to increase the overall power-handling capability of the system. In addition to power connections, the modules have communication connections. The SOI controllers in the modules communicate with each other as nodes of a decentralized control network, in which no single controller exerts overall command of the system. Control functions effected via the network include synchronization of switching of power devices and rapid reconfiguration of power connections to enable the power system to continue to supply power to a load in the event of failure of one of the modules; and, 3) In addition to serving as building blocks of reliable power-supply systems, SiC MCPMs could be augmented with external control circuitry to make them perform additional power-handling functions as needed for specific applications. Because identical SiC MCPM building blocks could be utilized in such a variety of ways, the cost and difficulty of designing new, highly reliable power systems would be reduced considerably. This concludes the information from the cited prior article. The main activity since the previously reported stage of development was the design, fabrication, and testing a 120- VDC-to-28-VDC modular power-converter system composed of eight SiC MCPMs in a 4 (parallel)-by-2 (series) matrix configuration, with normally-off controllable power switches. The SiC MCPM power modules include closed-loop control subsystems and are capable of operating at high power density or high temperature. The system was tested under various configurations, load conditions, load-transient conditions, and failure-recovery conditions. Planned future work includes refinement of the demonstrated modular system concept and development of a new converter hardware topology that would enable sharing of currents without the need for communication among modules. Toward these ends, it is also planned to develop a new converter control algorithm that would provide for improved sharing of current and power under all conditions, and to implement advanced packaging concepts that would enable operation at higher power density.

Lostetter, Alexander↗