SEARCH · Search NASA
Results for “system scaling”
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.
Rolex: Resilience-oriented language extensions for extreme-scale systems
Future exascale high-performance computing (HPC) systems will be constructed from VLSI devices that will be less reliable than those used today, and faults will become the norm, not the exception. This will pose significant problems for system designers and programmers, who for half-a-century have enjoyed an execution model that assumed correct behavior by the underlying computing system. The mean time to failure (MTTF) of the system scales inversely to the number of components in the system and therefore faults and resultant system level failures will increase, as systems scale in terms of the number of processor cores and memory modules used. However every error detected need not cause catastrophic failure. Many HPC applications are inherently fault resilient. Yet it is the application programmers who have this knowledge but lack mechanisms to convey it to the system. In this paper, we present new Resilience Oriented Language Extensions (Rolex) which facilitate the incorporation of fault resilience as an intrinsic property of the application code. We describe the syntax and semantics of the language extensions as well as the implementation of the supporting compiler infrastructure and runtime system. Furthermore, our experiments show that an approach that leverages the programmer's insight to reason about the context and significance of faults to the application outcome significantly improves the probability that an application runs to a successful conclusion.
Thermal runaway propagation models: from module scale to system scale.
Abstract not provided.
Sentiment Analysis based Error Detection for Large-Scale Systems
Today's large-scale systems such as High Performance Computing (HPC) Systems are designed/utilized towards exascale computing, inevitably decreasing its reliability due to the increasing design complexity. HPC systems conduct extensive logging of their execution behaviour. In this paper, we leverage the inherent meaning behind the log messages and propose a novel sentiment analysis-based approach for the error detection in large-scale systems, by automatically mining the sentiments in the log messages. Our contributions are four-fold. (1) We develop a machine learning (ML) based approach to automatically build a sentiment lexicon, based on the system log message templates. (2) Using the sentiment lexicon, we develop an algorithm to detect system errors. (3) We develop an algorithm to identify the nodes and components with erroneous behaviors, based on sentiment polarity scores. (4) We evaluate our solution vs. other state-of-the-art machine/deep learning algorithms based on three representative supercomputers' system logs. Experiments show that our error detection algorithm can identify error messages with an average MCC score and f -score of 91% and 96% respectively, while state of the art ML/deep learning model (LSTM) obtains only 67% and 84%. To the best of our knowledge, this is the first work leveraging the sentiments embedded in log entries of large-scale systems for system health analysis.
Dynamical System Scaling of a Thermocline Thermal Storage System in the Thermal Energy Distribution System (TEDS) Facility
The purpose of this study was to develop a process to convert input signals from one facility into another by reflecting geometric and environmental settings. The Dynamic Energy Transport and Integration Laboratory (DETAIL) is one facility in development that aims to emulate the daily interactions among power production industry systems and be capable of receiving real-time data from those systems as inputs. To convert signals and ensure that the temporal sequences and magnitudes reflect the laboratory settings, the ability to scale and project data is essential. To demonstrate this ability, Dynamical System Scaling (a methodology that enables systems to scale and project or extrapolate datasets to desired environments while conserving the observed transient behavior based on first principles) was applied to DETAIL’s thermocline thermal storage system in the Thermal Energy Distribution System. The thermocline system was successfully scaled and a test case was conducted to generate a doubly accelerated energy charge and discharge in reference to past experimental data from the facility. The accelerated data were determined as able to conserve the amount of energy stored and the associated test boundary conditions were charge line maximum temperature, charge line velocity, and thermocline maximum temperature at 354 °C, 0.458 m/s, and 418 °C, respectively. The research results represented a case that required signals to be accelerated without altering the stored energy.
Application of Dynamical System Scaling to Bubble Dynamics
Dynamical System Scaling (DSS) provides a useful method for analyzing, categorizing and scaling time-dependent processes. A key feature of DSS is the temporal displacement rate, D, which relates the natural process time to the reference clock time. Because of its property of being invariant under a two-parameter affine transformation, it provides an underlying basis for process scaling. Application of DSS to bubble dynamics serves to elucidate the physical significance of the temporal displacement rate and its role in scaling a variety of bubble dynamics processes. This paper shows that the temporal displacement rate consists of the sum of dimensionless groups that govern the bubble dynamics. Preserving the temporal displacement rate for a prototype and a scaled model results in similitude of the time-dependent normalized bubble size, growth rates and interfacial accelerations for different fluid conditions. For vapor bubble growth in a superheated liquid, it is shown that inertial controlled bubble growth occurs when D=0 and thermally controlled bubble growth occurs when D=1 .
SharP Hash: A High-Performing Distributed Hash for Extreme-Scale Systems
A high-performing distributed hash is critical for achieving performance in many applications and system software using extreme-scale systems. It is also a central part of many Big-Data frameworks including Memcached, file systems, and job schedulers. However, there is a lack of high-performing distributed hash implementations. In this work, we propose, design, and implement, SharP Hash, a high-performing, RDMA-based distributed hash for extreme-scale systems. SharP Hash's high performance is obtained through the use of high-performing networks and one-sided semantics. We perform an evaluation of SharP Hash and demonstrate its performance characteristics with a synthetic micro-benchmark and implementation of a Key Value (KV) store, Memcached.
Emulation Framework for Distributed Large-Scale Systems Integration
Recent trends in systems engineering include integration of very large-scale systems, which entails significant challenges when they are geographically dispersed. In these scenarios, intelligent integration of distributed large-scale systems requires significant coordination among hardware elements as well as all software components. The approach of integrated systems (both computing platform and experimental equipment) for end-to-end orchestration is called federation. Virtual frameworks can aid in the testing, assessment, and implementation of a functional system of interconnected resources. We present an emulation framework that replicates the software environments of multi-site federations of computing systems and instruments. Our emulation framework allows systems engineers to reduce developmentcost and avoid disruptions to production infrastructure. Our framework was effectively used to develop and test software modules for various tasks including container orchestration and instrument access. For performance assessment, however, the emulated framework is severely limited in providing accurate network and IO measurements at 10 Gbps and higher data rates. The data transfer performance profiles estimated using these emulated measurements are usually inaccurate for high bandwidth and high latency connections, since emulation does not accurately reflect the critical network transport dynamics.We utilize measurements from a physical testbed with hardware network emulators to obtain data transfer profiles that closely match the expected profiles for the emulated federations. We show the effectiveness of our approach by an illustrative example of integrated (federated) multi-site ultra large-scale systems that are connected via high speed wide area networks.
Machine Learning-Based Model Predictive Control of Two-Time-Scale Systems
In this study, we present a general form of nonlinear two-time-scale systems, where singular perturbation analysis is used to separate the dynamics of the slow and fast subsystems. Machine learning techniques are utilized to approximate the dynamics of both subsystems. Specifically, a recurrent neural network (RNN) and a feedforward neural network (FNN) are used to predict the slow and fast state vectors, respectively. Moreover, we investigate the generalization error bounds for these machine learning models approximating the dynamics of two-time-scale systems. Next, under the assumption that the fast states are asymptotically stable, our focus shifts toward designing a Lyapunov-based model predictive control (LMPC) scheme that exclusively employs the RNN to predict the dynamics of the slow states. Additionally, we derive sufficient conditions to guarantee the closed-loop stability of the system under the sample-and-hold implementation of the controller. A nonlinear chemical process example is used to demonstrate the theory. In particular, two RNN models are constructed: one to model the full two-time-scale system and the other to predict solely the slow state vector. Both models are integrated within the LMPC scheme, and we compare their closed-loop performance while assessing the computational time required to execute the LMPC optimization problem.
Supporting Co-Design of Extreme-Scale Systems with In Situ Visual Analysis of Event-Driven Simulations (Final Report)
Extreme-scale systems for compute- and data-centric science are pushing the boundaries of system architectures in order to achieve ambitious goals in terms of computing capability, resilience, and power efficiency. Future systems necessitate emerging designs that incorporate new technologies, system organizations, and computer science techniques, and these changes are not yet well understood. Discrete-event-driven simulation of computing system architectures and subsystems has emerged as a productive and cost-effective means to evaluating potential designs, along with capabilities for executing these simulations of extreme-scale systems. However, techniques for analyzing the behavior of these simulations have not kept pace with our ability to perform the simulations, preventing us from extracting the most value from this promising approach. The objective of this project is to support the codesign of extreme-scale system architectures for compute and data-centric science through research and development of novel methods for analysis and visualization of large-scale event-driven simulations.
Ceramic Membrane Solar Desal: Pilot System Design and Full-Scale System Techno-Economic Analysis (CRADA Final Report)
This work is conducted in support of the American Made Challenges Solar Prize. The current scope addresses the Design portion of the overall prize competition. This team, led by the University of Connecticut, will design a solar powered, pilot scale, ceramic-based membrane distillation system that can operate on high salinity waters and propose that design for construction in the Test phase of the Prize competition.
A Co-Simulation Framework for Steady-State Analyses of Multiple Droop-based MTdc Grids in Continental-Scale Systems
The growing scale and complexity of planning continental hybrid ac and multi-terminal dc (MTdc) systems require scalable steady-state modeling and analysis approaches not currently available in commercial tools. This paper presents a comprehensive multi-fidelity model-conversion framework that enables the efficient transition of MTdc grid models from production cost modeling (PCM) and approximated ac power flow to detailed ac–MTdc power flow for large-scale planning studies. The core of this framework is a scalable co-simulation approach that, for the first time, enables power flow analysis in continental-scale ac–MTdc systems. It seamlessly couples commercial ac solvers with a detailed MTdc grid model that incorporates droop-based control and current-limiting strategies of multiple meshed MTdc grids. Leveraging this capability, an evaluation framework to systematically assess and compare different MTdc power redispatch strategies under ac and dc contingencies is introduced. The proposed framework and algorithm are evaluated using a combined Western and Eastern Interconnection system with 11 MTdc grids of various sizes, showing a coherent transition from PCM to detailed ac–MTdc power flow and improved system performance in voltage regulation and line overload mitigation following typical contingencies.
Using Rollback Avoidance to Mitigate Failures in Next-Generation Extreme-Scale Systems
High-performance computing (HPC) systems enable scientists to numerically model complex phenomena in many important physical systems. The next major milestone in the development of HPC systems is the construction of the rst supercomputer capable executing more than an exa op, 10 18 oating point operations per second. On systems of this scale, failures will occur much more frequently than on current systems. As a result, resilience is a key obstacle to building next-generation extremescale systems. Coordinated checkpointing is currently the most widely-used mechanism for handling failures on HPC systems. Although coordinated checkpointing remains e ective on current systems, increasing the scale of today's systems to build next-generation systems will increase the cost of fault tolerance as more and more time is taken away from the application to protect against or recover from failure. Rollback avoidance techniques seek to mitigate the cost of checkpoint/restart by allowing an application to continue its execution rather than rolling back to an earlier checkpoint when failures occur. These techniqes include failure prediction and preventive migration, replicated computation, fault-tolerant algorithms, and softwarebased memory fault correction. In this thesis, we examine how rollback avoidance techniques can be used to address failures on extreme-scale systems. Using a combination of analytic modeling and simulation, we evaluate the potential impact of rollback avoidance on these systems. We then present a novel rollback avoidance technique that exploits similarities in application memory. Finally, we examine the feasibility of using this technique to protect against memory faults in kernel memory.
SharP: Towards Programming Extreme-Scale Systems with Hierarchical Heterogeneous Memory
The pre-exascale systems are expected to have a significant amount of hierarchical and heterogeneous on-node memory, and this trend of system architecture in extreme-scale systems is expected to continue into the exascale era. Along with hierarchical-heterogeneous memory, the system typically has a high-performing network and a compute accelerator. This system architecture is not only effective for running traditional High Performance Computing (HPC) applications (Big-Compute), but also running data-intensive HPC applications and Big-Data applications. As a consequence, there is a growing desire to have a single system serve the needs of both Big-Compute and Big-Data applications. Though the system architecture supports the convergence of the Big-Compute and Big-Data, the programming models have yet to evolve to support either hierarchical-heterogeneous memory systems or the convergence. In this work, we propose and develop the programming abstraction called SHARed data-structure centric Programming abstraction (SharP) to address both of these goals, i.e., provide (1) a simple, usable, and portable abstraction for hierarchical-heterogeneous memory and (2) a unified programming abstraction for Big-Compute and Big-Data applications. To evaluate SharP, we implement a Stencil benchmark using SharP, port QMCPack, a petascale-capable application, and adapt Memcached ecosystem, a popular Big-Data framework, to use SharP, and quantify the performance and productivity advantages. Additionally, we demonstrate the simplicity of using SharP on different memories including DRAM, High-bandwidth Memory (HBM), and non-volatile random access memory (NVRAM).
Comparing and contrasting In-Vial and full-scale systems for sparging volatile analytes
Here, in-vial sparging was demonstrated as an effective, practical alternative to a full-scale sparging system for supporting the analysis of volatile constituents. Using elemental mercury (Hg 0 ) and toluene as representative purgeable analytes, the mass removal for various sparge configurations was measured and a reduced order model was developed and validated. In the primary experiments, Hg 0 in the sparge gas was trapped on activated carbon or gold, thermally desorbed, and quantified using atomic absorption or atomic fluorescence spectroscopy. Toluene experiments using the same in-vial sparge apparatus and sparge parameters were performed to demonstrate the applicability of the reduced order model to a broad range of compounds. Toluene removal was tracked by measuring the remaining toluene in sparged aliquots using Ultraviolet-visible (UV–Vis) spectroscopy. For the sparging, flow rates varied from 25 to 75 mL/min for periods from 0 to 30 min. Sparge performance, mass removal as a function of time, and sparge gas volume were measured for both in-vial and full-scale systems. A model based on dimensionless Henry's Law coefficient, normalized sparge gas volume, and fractional extent of equilibrium matched the experimental data for both compounds and provides a practical tool for future applications. For the conditions tested in this study, the calibrated model indicated that the sparge gas in the in-vial system reached approximately 33% of its equilibrium value before exiting the water surface, while a full-scale system reached approximately 100%. The tests validated the quality, reproducibility, and predictability of sparging performance for both full scale and in-vial sparge systems. Related factors such as waste generation, worker risk, and labor were also assessed. Full scale sparge systems provide the advantage of lower detection levels due to larger sample volume, while the in-vial sparge systems provide advantages for most other factors; including automatability, reducing secondary wastes, lessening the need to clean and check the sparge apparatus, and lowering labor and costs. The data and associated reduced order model support continued development and deployment of in-vial sparge platforms as a practical option for analysis of purgeable analytes such as volatile organic compounds and volatile metals/organometallics.
IEEE 39 Bus System Scaled to 100 Matrix
A matrix for IEEE 39 bus system scaled to 100 times
Dynamic System Scaling Applied to Zr-4 Cladding under RIA Conditions
The research and development lifecycle for new fuel designs currently has an ideal 20-25 year timeline. Efforts are currrently underway to accelerate fuel design and development using high performance fuel modeling codes and reduced scale experiments with new instrumentation techniques. However current tools available require a full scale prototype to be designed and tested for fuel qualification. The thermal-hydraulics community has leveraged scaling methodologies to use reduced scale integral effect test facilities (Westinghouse AP600/1000, NuScale Power Module) in lieu of building full scale prototypes for reactor design certification. Dynamic System Scaling (DSS) is a recent development to scaling methodologies that enable the tracking and quantification of dynamic scaling distortions experienced throughout a transient. Recent TREAT experiments performed reactivity initiated accident (RIA) pulses on UO2 fuel rodlets in Zr-4 cladding and were accompanied by BISON predictions for the cladding temperature. DSS is applied to pyrometer data of outer cladding temperatures and two BISON predictions after peak cladding temperature has been reached. One BISON case uses a constant gap conductance value between the fuel and cladding and the other using a conventional gap conductance model. Results from the DSS analysis show that there is good agreement between both BISON predictions and the experimental data and that there is not a significant distortion seen between using either gap conductance model.
Integration of Dynamical System Scaling to RAVEN and Facility Application
As part of the design optimization and model validation effort within the hybrid energy systems program, the research to implement dynamical system scaling (DSS) code to RAVEN is funded under the Integrated Energy System program in collaboration with the Digital Reactor Technology & Development department. The DSS data processing algorithm has been coded within the RAVEN framework along with other metrics and postprocessing models. The implemented code was tested using a gravity-driven draining tank draining case modeled in RELAP5-3D and generated data was successfully postprocessed based on the scaling analyses defined by DSS. Postprocessed data concluded less agreement for the tank exit velocity and indicated that the modeled input deck for RELAP5-3D requires modification to enforce minimal pressure differential effects to the draining process.