Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “system performance”

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 19 records

Performance and Energy Usage of Workloads on KNL and Haswell Architectures. In: High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation

Manycore architectures are an energy-efficient step towards exascale computing within a constrained power budget. The Intel Knights Landing (KNL) manycore chip is a specific example of this and has seen early adoption by a number of HPC facilities. It is therefore important to understand the performance and energy usage characteristics of KNL. In this paper, we evaluate the performance and energy efficiency of KNL in contrast to the Xeon (Haswell) architecture for applications representative of the workload of users at NERSC. We consider the optimal MPI/OpenMP configuration of each application and use the results to characterize KNL in contrast to Haswell. As well as traditional DDR memory, KNL contains MCDRAM and we also evaluate its efficacy. Our results show that, averaged over our benchmarks, KNL is 1.84 × more energy efficient than Haswell and has 1.27 × greater performance.

Benchmarking↗

Total System Performance Ratio—A Systems Based Approach for Evaluating HVAC System Efficiency

The prescriptive path is the most widely used approach for commercial code compliance in the United States. Though easy to implement, prescriptive approaches do not typically discriminate between minimally compliant, high-performing and poorly performing HVAC system configurations. Hence, to meet aggressive energy and carbon reduction goals, it is clear that energy codes will need to transition from prescriptive to performance-based approaches, a transition that is riddled with several challenges. This paper discusses a new HVAC system-based performance approach (HVAC System Performance) which provides a simpler solution to HVAV system evaluation compared to whole building performance, while keeping tradeoffs limited to specific building systems. The Total System Performance Ratio (TSPR) is a metric for evaluation of overall system efficiency instead of individual component efficiency, a solution which could also eventually facilitate the transition to a 100% performance-based code structure. TSPR is a ratio that compares the annual heating and cooling load of a building to the annual energy consumed by the building’s HVAC system. A calculation software tool has been developed for determining a building’s TSPR. Already incorporated into the 2018 Washington State Energy Code, this approach is also being evaluated by ASHRAE Standard 90.l Project Committee and has the potential to provide a comprehensive performance-based approach for HVAC system evaluation and analysis.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A side‐by‐side comparison of CPV module and system performance

Abstract A side‐by‐side comparison is made between concentrator photovoltaic module and system direct current aperture efficiency data with a focus on quantifying system performance losses. The individual losses measured/calculated, when combined, are in good agreement with the total loss seen between the module and the system. Results indicate that for the given test period, the largest individual loss of 3.7% relative is due to the baseline performance difference between the individual module and the average for the 200 modules in the system. A basic empirical model is derived based on module spectral performance data and the tabulated losses between the module and the system. The model predicts instantaneous system direct current aperture efficiency with a root mean square error of 2.3% relative. Copyright © 2016 John Wiley & Sons, Ltd.

Muller, Matthew↗

Automatic and Transparent Resource Contention Mitigation for Improving Large-Scale Parallel File System Performance

Proportional to the scale increases in HPC systems, many scientific applications are becoming increasingly data intensive, and parallel I/O has become one of the dominant factors impacting the large-scale HPC application performance. On a typical large-scale HPC system, we have observed that the lack of a global workload coordination coupled with the shared nature of storage systems cause load imbalance and resource contention over the end-to-end I/O paths resulting in severe performance degradation. I/O load imbalance on HPC systems is generally a self-inflicted wound and mostly occurs between the I/O paths and resources consumed by each individual job. In this paper, we introduce TAPP-IO, a dynamic, shared load balancing framework for mitigating resource contention. TAPP-IO extends our previous work and solves two major limitations: First, it transparently intercepts file creation calls during runtime to balance the workload over all available storage targets. The usage of TAPP-IO requires no application source code modifications and is independent from any I/O middleware. The framework can be applied to almost any HPC platform and is suitable for systems that lack a centralized file system resource manager. Second, the framework proposes a new placement strategy to support not only file-per-process I/O, but also single shared file I/O. This opens the door to a new class of scientific applications that can leverage the placement library for improved performance. We demonstrate the effectiveness of our integration on the Titan system at the Oak Ridge National Laboratory. Our experiments with a synthetic benchmark and real-world HPC workload show that, even in a noisy production environment, TAPP-IO can improve large-scale application performance significantly.

Neuwirth, Sarah↗

Flexspander: augmenting expander networks in high-performance systems with optical bandwidth steering

Communication efficiency is one of the deciding factors in determining many of today’s high-performance computing (HPC) applications. Traditionally, HPC systems have been on static network topologies, making them inflexible to the variety of skewed traffic demands that may arise due to the spatial locality inherent in many applications. To handle traffic locality, researchers have proposed integrating optical circuit switches (OCSs) into the network architecture, which reconfigures the network topology to alter and dynamically adapt to the predicted traffic. In this paper, we present a novel reconfigurable network topology called Flexspander. Beyond offering a flexible interconnect, Flexspander also offers full flexibility in terms of construction and can be built with any arbitrary combination of commercial electrical packet switches and OCSs. We evaluate Flexspander performance through extensive simulations with multiple network traces, and our results show improved performance for Flexspander over currently proposed static and reconfigurable topologies in terms of the flow completion time.

Teh, Min Yee↗

TSPR: The Total System Performance Ratio as a Metric for HVAC System Efficiency

North American energy codes do not typically discriminate between high-performing and poorly-performing HVAC system types, thereby perpetuating the installation of systems with high energy consumption and carbon emissions. The problem is compounded in the US by federal preemption rules, prohibiting state and local energy codes from mandating more efficient equipment than is defined in federal standards. The lack of a total system efficiency metric for HVAC effectively blocks an eventual transition to a performance-based code structure. To surmount this problem, the City of Seattle and Pacific Northwest National Laboratory have developed the Total System Performance Ratio (TSPR) as a proposed amendment to the 2018 Washington State Energy Code. The TSPR is a ratio that compares the annual space heating and cooling load of a building to the annual energy consumed by the building’s entire HVAC system. In the TSPR, target ratios for several building types are calculated in relation to those of the HVAC systems judged to be the most appropriate for each building type. Installation of the lowest-performing HVAC system types will be severely constrained, while exceptional design flexibility will still be provided. With financial support from an international nonprofit, a calculation software tool has been developed as a module of the US DOE Asset Score tool, using simplified building energy modeling. Taken together with whole-system evaluation options for lighting and building envelope systems, a whole-system HVAC performance evaluation would create a path for a transition away from prescriptive-based and towards performance-based codes.

Total System Performance Ratio, Performanced Based↗

Improving Process Heating System Performance v3

Improving Process Heating System Performance: A Sourcebook for Industry is a development of the U.S. Department of Energy (DOE) Advanced Manufacturing Office (AMO) and the Industrial Heating Equipment Association (IHEA). The AMO and IHEA undertook this project as part of an series of sourcebook publications developed by AMO on energy-consuming industrial systems, and opportunities to improve performance. Other topics in this series include compressed air systems, pumping systems, fan systems, steam systems, and motors and drives

U.S. DOE, IHEA, Lawrence Berkeley National Laborat↗

Simulation, Characterization, and Optimization of Metabolic Models with the High Performance Systems Biology Toolkit

The High Performance Systems Biology Toolkit (HiPer SBTK) is a collection of simulation and optimization components for metabolic modeling and the means to assemble these components into large parallel processing hierarchies suiting a particular simulation and optimization need. The components come in a variety of different categories: model translation, model simulation, parameter sampling, sensitivity analysis, parameter estimation, and optimization. They can be configured at runtime into hierarchically parallel arrangements to perform nested combinations of simulation characterization tasks with excellent parallel scaling to thousands of processors. We describe the observations that led to the system, the components, and how one can arrange them. We show nearly 90% efficient scaling to over 13,000 processors, and we demonstrate three complex yet typical examples that have run on {approx}1000 processors and accomplished billions of stiff ordinary differential equation simulations. This work opens the door for the systems biology metabolic modeling community to take effective advantage of large scale high performance computing resources for the first time.

59 BASIC BIOLOGICAL SCIENCES↗

Understanding Solar Photovoltaic System Performance: An Assessment of 75 Federal Photovoltaic Systems

This report presents a performance analysis of 75 photovoltaic systems based on PV system production data collected as part of a FEMP Federal PV Performance Assessment project combined with co-incident insolation, and ambient temperature to analyze how actual performance compares with a performance model. FEMP collaborated with 17 Federal agencies and sub-agencies to collect the information required to analyze the performance of each system. The systems represent a total capacity of 30,714 kW and range in size from 1 kW to 4,043 kW, with an average size of 410 kW, and were installed between 2011 and 2020. The data is analyzed for Key Performance Indicators, Availability, Performance Ratio and Energy Ratio by comparing the measured production data to model production data. The System Advisor Model (SAM) combines a description of the system (such as inverter capacity, de-rating for temperature, balance-of-system efficiency) with environmental parameters (coincident solar and temperature data) to calculate predicted performance. The performance metrics are calculated by lining up the measured production data with the model estimate on an hour-by-hour, day-by-day, or month-by-month basis (depending on the interval resolution of the production data). A report with system description, photo of the system, special assumptions made for the site, graph of measured production and model production, table of key performance indicators, and links to O&M resources that might improve performance was produced and delivered to site and agency staff with a short on-line briefing.

14 SOLAR ENERGY↗

The Numerical Computation of Clear-Sky Transmittance and Reflectance of Solar Radiation for the Modeling of PV System Performance

Modeling of photovoltaics (PV) system performance requires numerical computation of plane-of-array (POA) irradiances that are influenced by atmospheric absorption and scattering. Clear-sky transmittance and reflectance of diffuse irradiance are essential for the understanding of solar radiation related to multiple reflection between land surface and clouds. This study analytically solves the radiative transfer equation for clear-sky conditions and numerically computes the transmittance and reflectance of diffuse irradiance as functions of the optical thickness of the atmosphere. The computation will be implemented in all-sky radiative transfer models to improve their computational efficiency.

14 SOLAR ENERGY↗

Demonstrating Hybrid Heat Transport and Energy Conversion System Performance Characterization Using Intelligent Control Systems

The debate continues on the magnitude and validity of climate change caused by human activities. However, there is no debate about the need to make buildings, modes of transportation, factories, and homes as energy efficient as possible. Given that climate change could occur with the wasteful use of fossil fuel and the fact that fossil energy costs could and will swing wildly, it is imperative that every effort be made to utilize energy sources to their fullest. Hybrid energy systems (HES) are two or more separate energy producers used together to produce energy commodities. The HES this report focuses on is the use of nuclear reactor waste heat as a source of further energy utilization. Nuclear reactors use a fluid to cool the core and produce the steam needed for the production of electricity. Traditionally this steam, or coolant, is used to convert the energy then cooled elsewhere. The heat is released into the environment without being used further. By adding technologies to nuclear reactors to use the wasted heat, a system can be developed to make more than just electricity and allow for loading following capabilities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Improving Steam System Performance: A Sourcebook for Industry, Second Edition (Book) (Revised)

Improving Steam System Performance: A Sourcebook for Industry was developed for the U.S. Department of Energy's (DOE) Advanced Manufacturing Office (AMO), formerly the Industrial Technologies Program. AMO undertook this project as a series of sourcebook publications. Other topics in this series include: compressed air systems, pumping systems, fan systems, process heating and motor and drivesystems. For more information about program resources, see AMO in the Where to Find Help section of this publication.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗