Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Performance optimization”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

Parallel performance optimizations on unstructured mesh-based simulations

This paper addresses two key parallelization challenges the unstructured mesh-based ocean modeling code, MPAS-Ocean, which uses a mesh based on Voronoi tessellations: (1) load imbalance across processes, and (2) unstructured data access patterns, that inhibit intra- and inter-node performance. Our work analyzes the load imbalance due to naive partitioning of the mesh, and develops methods to generate mesh partitioning with better load balance and reduced communication. Furthermore, we present methods that minimize both inter- and intranode data movement and maximize data reuse. Our techniques include predictive ordering of data elements for higher cache efficiency, as well as communication reduction approaches. We present detailed performance data when running on thousands of cores using the Cray XC30 supercomputer and show that our optimization strategies can exceed the original performance by over 2×. Additionally, many of these solutions can be broadly applied to a wide variety of unstructured grid-based computations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A digital twin platform for building performance monitoring and optimization: Performance simulation and case studies

Advancements in sensor technology, data analytics, affordable compute, and communication infrastructure have paved the way for Digital Twin technology in optimizing building operations and controls. This study presents the development of an open and interoperable web-based Digital Twin platform for integrating diverse data streams and facilitating effective user interactions. The platform utilizes modern technologies for the web framework and time-series data management, ensuring scalability and responsiveness. The backend supports seamless integration of diverse data sources and emulators, incorporating data from building sensors and meters, external weather Application Programming Interfaces, and advanced EnergyPlus simulation models of the building and its energy systems including the Distributed Energy Resources that are formulated in Functional Mockup Units. A simulation case study was conducted with FlexLab, a test facility on Lawrence Berkeley National Laboratory campus. The case study includes normal operations, Distributed Energy Resource integration, and power outage scenarios, to illustrate the Digital Twin’s ability to provide critical insights into energy performance and thermal resilience. The results demonstrated the platform’s potential as a decision-support tool for optimizing building energy performance and enhancing resilience against extreme weather events. Future work will focus on deploying the Digital Twin platform to a real building for field validation, extending its capabilities to cover more scenarios such as bidirectional Electric Vehicle interactions, and enhancing user engagement.

EnergyPlus↗
DOE OSTI2020

AI-Science for Performance Optimization and Diagnosis of Science Instrument Federations

Next generation of science workflows are expected to be executed over complex federations composed of supercomputers, science instruments, storage systems and networks, with new additions of the edge and cloud systems and services. The sheer complexity of these multi-domain federations makes it hard to manage them and optimize their performance, as small impedance mismatches (that can dynamically develop between systems) could drastically degrade the entire federation performance. Recent proliferation of Software Defined Everything (SDX) technologies combined with containerization frameworks provide custom instruments that can monitor and collect critical measurements at various levels to support diagnoses and performance optimization; but their data too enormous for human operators and analysts to process and generate decisions. Machine Learning (ML) methods that extract critical parameters, relationships and trends from the data offer general solutions. Artificial Intelligence (AI) and ML methods must be custom-developed for these problems based on solid, rigorous foundations, since black-box approaches are often ineffective and unsound.We propose to develop comprehensive AI-Science for the performance of science federations to (i) monitor and control storage, networks, experiments, and computing systems across multiple domains via softwarization layers, at speeds and scales orders of magnitude superior to current practice, (ii) optimally realize and orchestrate complex workflows with high performance by using dynamic state and performance estimation methods, and (iii) aggregate measurements across sites and time to develop infrastructure-level profiles, optimizations and diagnoses using AI-Science based on foundational principles from ML, game theory, and information fusion areas.

Rao, Nageswara↗
DOE OSTI2026

Near-Optimal Performance of Stochastic Model Predictive Control

Here, this article presents a regret analysis for stochastic model predictive control (SMPC) in linear systems with quadratic performance index and additive and multiplicative uncertainties. Under a finite support assumption, the problem can be cast as a finite-dimensional quadratic program, but the problem becomes quickly intractable as the problem size grows exponentially in the horizon length. SMPC aims to compute approximate solutions by solving a sequence of problems with truncated prediction horizons and committing the solution in a receding-horizon fashion. Although this approach is widely used in practice, its performance relative to the optimal solution is not well understood. This article reports for the first time a rigorous near-optimal performance guarantee of SMPC: under stabilizability and detectability conditions, the regret of SMPC is exponentially small in the prediction horizon length, allowing SMPC to achieve near-optimal performance at a substantially reduced computational expense.

93E20, 93B45↗
DOE OSTI2025

Performance Optimization of the IOTA Duoplasmatron Proton Source

We present results from online optimization studies of a duoplasmatron ion source designed to produce 50~keV protons for acceleration to 2.5~MeV and subsequent injection into the Integrable Optics Test Accelerator (IOTA) at Fermilab. Using a Bayesian exploration technique, we developed multi-parameter models of the source s proton current and employed these models to optimize its performance. Depending on the spectrometer configuration used to isolate the proton beam and the chosen optimization objective, we identified three candidate operating points, achieving normalized 50~\% emittances between 0.57 and 1.3~\textmu m and a maximum proton current of $14.5 \pm 0.6$~mA.

Banerjee, Nilanjan [Fermilab] (ORCID:0000000344660↗
DOE OSTI2019

Hierarchical Roofline analysis for GPUs: Accelerating performance optimization for the NERSC‐9 Perlmutter system

Summary The Roofline performance model provides an intuitive and insightful approach to identifying performance bottlenecks and guiding performance optimization. In preparation for the next‐generation supercomputer Perlmutter at NERSC, this paper presents a methodology to construct a hierarchical Roofline on NVIDIA GPUs and extends it to support reduced precision and Tensor Cores. The hierarchical Roofline incorporates L1, L2, device memory, and system memory bandwidths into one single figure, and it offers more profound insights into performance analysis than the traditional DRAM‐only Roofline. We use our Roofline methodology to analyze three proxy applications: GPP from BerkeleyGW, HPGMG from AMReX, and conv2d from TensorFlow. In doing so, we demonstrate the ability of our methodology to readily understand various aspects of performance and performance bottlenecks on NVIDIA GPUs and motivate code optimizations.

Yang, Charlene↗
DOE OSTI2017

Performance Optimization of Alternative Lower Global Warming Potential Refrigerants in Mini-Split Room Air Conditioners

Oak Ridge National laboratory (ORNL) recently conducted extensive laboratory, drop-in investigations for lower Global Warming Potential (GWP) refrigerants to replace R-22 and R-410A. ORNL studied propane, DR-3, ARM-20B, N-20B and R-444B as lower GWP refrigerant replacement for R-22 in a mini-split room air conditioner (RAC) originally designed for R-22; and, R-32, DR-55, ARM-71A, and L41-2, in a mini-split RAC designed for R-410A. We obtained laboratory testing results with very good energy balance and nominal measurement uncertainty. Drop-in studies are not enough to judge the overall performance of the alternative refrigerants since their thermodynamic and transport properties might favor different heat exchanger configurations, e.g. cross-flow, counter flow, etc. This study compares optimized performances of individual refrigerants using a physics-based system model tools. The DOE/ORNL Heat Pump Design Model (HPDM) was used to model the mini-split RACs by inputting detailed heat exchangers geometries, compressor displacement and efficiencies as well as other relevant system components. The RAC models were calibrated against the lab data for each individual refrigerant. The calibrated models were then used to conduct a design optimization for the cooling performance by varying the compressor displacement to match the required capacity, and changing the number of circuits, refrigerant flow direction, tube diameters, air flow rates in the condenser and evaporator at 100% and 50% cooling capacities. This paper compares the optimized performance results for all alternative refrigerants and highlights best candidates for R-22 and R-410A replacement.

GWP↗
DOE OSTI2018

Systematic Layout Planning of a Radiology Reporting Area to Optimize Radiologists’ Performance

Optimizing radiologists’ performance is a major priority for managers of health services/systems, since the radiologists’ reporting activity imposes a severe constraint on radiology productivity. Despite that, methods to optimize radiologists’ reporting workplace layout are scarce in the literature. This study was performed in the Radiology Division (RD) of an 850-bed University-based general hospital. The analysis of the reporting workplace layout was carried out using the systematic layout planning (SLP) method, in association with cluster analysis as a complementary tool in early stages of SLP. Radiologists, architects, and hospital managers were the stakeholders consulted for the completion of different stages of the layout planning process. A step-by-step description of the proposed methodology to plan an RD reporting layout is presented. Clusters of radiologists were defined using types of exams reported and their frequency of occurrence as clustering variables. Sectors with high degree of interaction were placed in proximity in the new RD layout, with separation of noisy and quiet areas. Four reporting cells were positioned in the quiet area, grouping radiologists by subspecialty, as follows: cluster 1-abdomen; cluster 2-musculoskeletal; cluster 3-neurological, vascular and head & neck; cluster 4-thoracic and cardiac. The creation of reporting cells has the potential to limit unplanned interruptions and enhance the exchange of knowledge and information within cells, joining radiologists with the same expertise. That should lead to improvements in productivity, allowing managers to more easily monitor radiologists’ performance.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2017

Topology-Aware Performance Optimization and Modeling of Adaptive Mesh Refinement Codes for Exascale

Here, we introduce a topology-aware performance optimization and modeling workflow for AMR simulation that includes two new modeling tools, ProgrAMR and Mota Mapper, which interface with the BoxLib AMR framework and the SSTmacro network simulator. ProgrAMR allows us to generate and model the execution of task dependency graphs from high-level specifications of AMR-based applications, which we demonstrate by analyzing two example AMR-based multigrid solvers with varying degrees of asynchrony. Mota Mapper generates multiobjective, network topology-aware box mappings, which we apply to optimize the data layout for the example multigrid solvers. While the sensitivity of these solvers to layout and execution strategy appears to be modest for balanced scenarios, the impact of better mapping algorithms can be significant when performance is highly constrained by network hop latency. Furthermore, we show that network latency in the multigrid bottom solve is the main contributing factor preventing good scaling on exascale-class machines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

MUPPET: An automated OpenMP mutation testing framework for performance optimization

MUPPET is a tool for OpenMP programs that identifies program modifications, called mutations, aimed at improving program performance. Existing performance optimization techniques, including profiling-based and auto-tuning techniques, fail to indicate program modifications at the source level thus preventing their portability across compilers. MUPPET aims to help HPC developers reason about performance defects and missed opportunities to improve performance at the source code level.

Parasyris, Konstantinos↗
DOE OSTI2019

Performing optimized collective operations in an irregular subcommunicator of compute nodes in a parallel computer

In a parallel computer, performing optimized collective operations in an irregular subcommunicator of compute nodes may be carried out by: identifying, within the irregular subcommunicator, regular neighborhoods of compute nodes; selecting, for each neighborhood from the compute nodes of the neighborhood, a local root node; assigning each local root node to a node of a neighborhood-wide tree topology; mapping, for each neighborhood, the compute nodes of the neighborhood to a local tree topology having, at its root, the local root node of the neighborhood; and performing a one way, rooted collective operation within the subcommunicator including: performing, in one phase, the collective operation within each neighborhood; and performing, in another phase, the collective operation amongst the local root nodes.

Davis, Kristan D.↗
DOE OSTI2021

Performing optimized collective operations in a irregular subcommunicator of compute nodes in a parallel computer

In a parallel computer, performing optimized collective operations in an irregular subcommunicator of compute nodes may be carried out by: identifying, within the irregular subcommunicator, regular neighborhoods of compute nodes; selecting, for each neighborhood from the compute nodes of the neighborhood, a local root node; assigning each local root node to a node of a neighborhood-wide tree topology; mapping, for each neighborhood, the compute nodes of the neighborhood to a local tree topology having, at its root, the local root node of the neighborhood; and performing a one way, rooted collective operation within the subcommunicator including: performing, in one phase, the collective operation within each neighborhood; and performing, in another phase, the collective operation amongst the local root nodes.

Davis, Kristan Suzanne D.↗
DOE OSTI2019

Integrated Solutions for Optimized Performance (ISOP) Final Technical Report

The goal of this project was to demonstrate technical feasibility of an integrated approach for deep energy retrofits by packaging innovative technologies with smart communicating controls that represent the next generation of energy efficiency. The integrated solutions for optimized performance (ISOP) package integrates (i) advanced lighting and plug load controls; (ii) intelligent daylight harvesting through automated self-powered shades and window films; (iii) advanced HVAC controls sequences (ASHRAE Guideline (GDL) 36); and (iv) fault detection and diagnosis (FDD) and continuous commissioning (CCx) using advanced analytics. These technologies address energy use across multiple building end uses that represent more than 60% of the energy consumption in all commercial buildings. The project was structured to be implemented over three budget periods: Budget Period 1 scope included site selection, project design, site-specific customization of technology packages, procurement of technologies, initiation of installation of technologies, the development of a measurement and verification plan and collection of pre-retrofit data collection. The first year go/no-go decision was based on securing host sites representing 250,000 sq. ft. of occupied operational spaces, savings analysis, technology procurement and initiation of installation. Budget Period 2 planned to complete technology installations and initiate data collection of post-retrofit performance data. The second year go/no-go was to be the completion of technology installations and commissioning, metering and data collecting to support the requirements laid out in site specific M&V plans. Budget Period 3 planned to collect and analyze post-retrofit performance data and provide data and reporting to support energy efficiency rebate programs. After the team completed activities planned for Budget Period 1, the team reached a Go/No-Go Decision Point. At that point, TRC recommended that DOE discontinue the project without prejudice due to challenges with securing demonstration sites to meet the full 250,000 sf of occupied operational spaces and DOE concurred. In Budget Period 1, the TRC team developed criteria to recruit and evaluate potential demonstration host sites. TRC worked with Princeton University, the project demonstration partner, to identify buildings on their campus as potential candidates for the demonstration. Following the selection of demonstration sites, the TRC team customized energy technology packages according to the needs and characteristics of each site. TRC defined technology specifications, identified vendors, and conducted analysis to estimate energy and cost savings potential. The project team then developed schedules for technology procurement processes and scheduled for installation at all selected demonstration sites. The project team worked with Princeton University and DOE to develop an approach to verify energy savings achieved through measurement and verification (M&V) 2.0 methods. Princeton University initiated open bids to procure the necessary materials and installation contractors. Bid results came back higher than estimates due to a couple of factors – lack of familiarity of the bidders with the proposed technologies and lack of local trained installers to execute the installation of these new measures. Due to the higher bids, projects no longer met the internal cost-effectiveness criteria used by Princeton to proceed with procurement of the full suite of technologies as proposed in ISOP. Princeton had already procured parts of the ISOP package as part of a campus-wide initiative for FDD and lighting retrofits, but with the higher costs for other ISOP components, Princeton could no longer commit to the full ISOP package on the selected sites. Based on this, the team reached the Go/No-Go decision point, where they decided not to proceed with the project. Princeton is separately installing portions of the ISOP package where they individually meet Princeton’s payback criteria but on a different schedule than would have been needed for the DOE ISOP project. The team has learned several lessons from project progress in the first budget period. The team will utilize these lessons in future projects, as should any team which proceeds with a project around the ISOP technology. The first lesson is that more information about the proposed sites is required earlier in the process (perhaps even at the proposal stage) in order to have a successful demonstration. Technical details not evident earlier in the process (such as the TLED limitations for ALCS) can derail project execution. The second lesson is that pricing of emerging technologies is highly variable due to lack of familiarity of local installers and distributor with the proposed technologies as well as alternate bids using products they were more familiar with, but that cost more than the ones proposed by TRC. Finally, the last major lesson is that the host site’s internal project criteria is of critical importance. Based on these higher installed costs and lack of an informed installer base for the products proposed for this project, the project does not meet Princeton’s simple payback goals of five years.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗