Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “graph analytics”

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 OSTI2024

Portable Parallel Algorithms and Frameworks for Exascale Graph Analytics

Graphs (or networks) are a tool used to model the interactions among various entities. Efficiently processing large graphs has recently attracted significant attention due to the applications of graphs in various domains, such as biology, chemistry, and cyber-security. Analyzing the structure and properties of these graphs is an important component of many scientific computing pipelines. With the explosion in the volume of data, graphs have become very large and can contain hundreds of billions of vertices and trillions of edges. Therefore, it is crucial to develop high-performance methods to enable graph analysis to be done quickly and energy-efficiently. Furthermore, these solutions should be highly parallel in order to take advantage of modern parallel machines. However, designing efficient solutions is not enough. With the wide variety of computing environments available, each with different programmability and performance characteristics, it is necessary to develop solutions that are portable in terms of both performance (i.e., provide theoretical guarantees) and programmability (i.e., provide high level abstractions).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Exploring the Landscape of Distributed Graph Clustering on Leadership Supercomputers

The rapid growth of large-scale datasets in fields like biology and social networks has driven the need for advanced graph analytics techniques. Community detection, a fundamental task in graph analytics, identifies closely connected groups of nodes within a network, providing valuable insights across various disciplines. This study focuses on two classic community detection methods, the Louvain algorithm and Markov Clustering (MCL), and evaluates the performance of two prominent distributed community detection algorithms: HiPDPL-GPU, our prior implementation, and HipMCL. We conduct experiments on GPU-accelerated heterogeneous HPC systems, Summit and Frontier, to assess their performance under varying conditions. Our objective is to identify the strengths and weaknesses of these algorithms in terms of scalability, and quality of solutions. We evaluate these algorithms on a diverse set of 70+ networks spanning 13 domains, with sizes ranging up to 4.2 billion edges. Our results demonstrate that HiPDPL-GPU consistently outperforms HipMCL, especially for large-scale networks. HiPDPL-GPU achieves significantly faster runtimes (47x to 1439x), higher modularity scores, and improved scalability. These findings highlight HiPDPL-GPU as a promising solution for efficient and effective large-scale graph analytics in diverse application domains, and provide insights into the feasibility of using MCL-based approaches for certain application domains.

Community detection, graph algorithms↗
DOE OSTI2025

A Privacy First Path Analysis using Clickstream Data

In the modern digital economy, data-driven decision making is crucial for effectively meeting the ever-evolving demands of consumer engagement and satisfaction. Clickstream data has become invaluable for understanding customer behavior, yet concerns over privacy and security persist, especially with some internet service providers profiting from its sale. This article introduces an innovative methodology that blends experiential learning with advanced cryptographic techniques, including differential privacy and graph analytics. The core objective of this methodology is to estimate Customer Lifetime Value (CLV) by analyzing clickstream data, achieving an average prediction accuracy of 92.4% in user engagement levels while ensuring user anonymity through Recency, Frequency, and Monetary (RFM) analysis. Our study introduces the concept of a “data depositor” and a privacy manager, employing the composition theorem to merge non-adaptive queries effectively. Privacy budgets (? = 1.0, d = 10-5), sensitivity-specific techniques, and data partitioning were applied. Randomization and noise addition protect data integrity, with special handling for categorical values. This approach, differing from prior studies, offers a 12.6% improvement in privacy-preserving targeting accuracy while maintaining strict confidentiality, presenting a novel path forward in data-driven decision-making.

Frequency and Monetary (RFM) analysis↗
DOE OSTI2025

GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism

Graph neural networks (GNNs), an emerging class of machine learning models for graphs, have gained popularity for their superior performance in various graph analytical tasks. Mini-batch training is commonly used to train GNNs on large graphs, and data parallelism is the standard approach to scale mini-batch training across multiple GPUs. Data parallel approaches contain redundant work as subgraphs sampled by different GPUs contain significant overlap. To address this issue, we introduce a hybrid parallel mini-batch training paradigm called Split parallelism. Split parallelism avoids redundant work by splitting the sampling, loading, and training of each mini-batch across multiple GPUs. Split parallelism, however, introduces communication overheads that can be more than the savings from removing redundant work. We further present a lightweight partitioning algorithm that probabilistically minimizes these overheads. We implement spllit parllelism in GSplit and show that it outperforms state-of-the-art mini-batch training systems like DGL, Quiver, and P3.

Lim, Seung-Hwan [ORNL] (ORCID:0000000194616866)↗
DOE OSTI2026

Wattchmen: Watching the Wattchers – High Fidelity, Flexible GPU Energy Modeling

Modern GPU-rich HPC systems are increasingly becoming energy-constrained. Thus, understanding an application’s energy consumption becomes essential. Unfortunately, current GPU energy attribution techniques are either inaccurate, inflexible, or outdated. Therefore, we propose Wattchmen, a flexible methodology for measuring, attributing, and predicting GPU energy consumption. We construct a per-instruction energy model using a diverse set of microbenchmarks to systematically quantify the energy consumption of GPU instructions, enabling finer-grain prediction and energy consumption breakdowns for applications. Compared with the state-of-the-art systems like AccelWattch (32%) and Guser (25%), across 16 popular GPGPU, graph analytics, HPC, and ML workloads, Wattchmen reduces the mean absolute percent error (MAPE) to 14% on V100 GPUs. Furthermore, we show that Wattchmen provides similar MAPEs for water-cooled V100s (15%) and extends to later architectures, including air-cooled A100 (11%) and H100 (12%) GPUs. Finally, to further demonstrate Wattchmen ’s value, we apply it to applications such as Backprop and QMCPACK, where Wattchmen ’s insights enable energy reductions of up to 35%.

Tran, Brandon [University of Wisconsin, Madison] (↗
DOE OSTI2024

SPARTAN (Scalable Probabilistic Application Reconfigurable Tensor Autonomous Network)

The technical founder of Ludwig Computing Inc has been competitively selected for support by Cyclotron Road, a U.S. Department of Energy (DOE) Advanced Manufacturing Office (AMO) Lab-Embedded Entrepreneurship Program (LEEP) through an approved merit review process. Ludwig Computing Inc, supported by the U.S. Department of Energy's Advanced Manufacturing Office through the Cyclotron Road program, has investigated the advantages of probabilistic computing for real-world compute-intensive applications. This research adds to the understanding of alternative computing paradigms by exploring a unique hardware-software co-design that integrates quantum computing methods with nature-inspired problem-solving techniques. The project's focus on areas such as combinatorial optimization, graph analytics, and machine learning demonstrates the potential for significant advancements in computational efficiency and performance. By harnessing natural randomness to streamline large circuits into fewer devices, Ludwig's approach enables massive parallelism, potentially offering higher throughput, speed, and energy efficiency compared to conventional hardware solutions. This work benefits the public by paving the way for more efficient computing solutions that could address complex real-world problems while potentially reducing energy consumption in data-intensive industries.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

From Data to Discovery: AI's Transformative Role in Thin Film Research

The advancement of thin film technologies is pivotal for progress in numerous fields, including energy, electronics, and quantum computing. However, the traditional trial-and-error approach to materials discovery is inherently slow and inefficient. This presentation will showcase how artificial intelligence (AI) is transforming thin film research by enabling a data-driven paradigm shift. We will highlight our past successes in applying AI to understand radiation damage in thin film oxides, demonstrating how graph analytics can unravel complex material behavior. Additionally, we will provide insights into our current work at the National Renewable Energy Laboratory, where we are leading the charge in autonomous materials science. Backed by a $14M investment in our characterization facility, we are developing AI-guided workflows that seamlessly integrate experimentation and AI-guided decision-making. By harnessing the power of AI, we aim to accelerate the discovery and design of high-performance thin films, propelling innovation across a multitude of industries.

36 MATERIALS SCIENCE↗
NASA NTRS1983

Windmilling of the rotor of a turbojet engine with an axial-flow compressor under flight conditions

The concept of rotor windmilling is understood to mean rotation of the rotor caused solely by the energy of the air (not gas) streaming through the apertures between the blades (under conditions of power shut-off) under the action of dynamic pressure. The concept of windmilling is analyzed for an engine with an axial-flow compressor, showing that windmilling must be taken into account in such cases as in-flight reignition of the engine. A graph-analytic method for determining the range of windmilling is proposed.

Borgon, J.↗
NASA NTRS2010

Understanding the Scalability of Bayesian Network Inference Using Clique Tree Growth Curves

One of the main approaches to performing computation in Bayesian networks (BNs) is clique tree clustering and propagation. The clique tree approach consists of propagation in a clique tree compiled from a Bayesian network, and while it was introduced in the 1980s, there is still a lack of understanding of how clique tree computation time depends on variations in BN size and structure. In this article, we improve this understanding by developing an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, specifically: (i) the ratio of the number of a BN s non-root nodes to the number of root nodes, and (ii) the expected number of moral edges in their moral graphs. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for the total size of each set. For the special case of bipartite BNs, there are two sets and two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, where random bipartite BNs generated using the BPART algorithm are studied, we systematically increase the out-degree of the root nodes in bipartite Bayesian networks, by increasing the number of leaf nodes. Surprisingly, root clique growth is well-approximated by Gompertz growth curves, an S-shaped family of curves that has previously been used to describe growth processes in biology, medicine, and neuroscience. We believe that this research improves the understanding of the scaling behavior of clique tree clustering for a certain class of Bayesian networks; presents an aid for trade-off studies of clique tree clustering using growth curves; and ultimately provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms.

Mengshoel, Ole J.↗
DOE OSTI2026

Ginzburg--Landau functionals in the large-graph limit

Ginzburg–Landau (GL) functionals on graphs, which are relaxations of graph-cut functionals on graphs, have yielded a variety of insights in image segmentation and graph clustering. In this paper, we study large-graph limits of GL functionals by taking a functional-analytic view of graphs as nonlocal kernels. For a graph Wn with n nodes, the corresponding graph GL functional GL W n ϵ is an energy for functions on Wn. We minimize GL functionals on sequences of growing graphs that converge to functions called graphons. For such sequences of graphs, we show that the graph GL functional Γ-converges to a continuous and nonlocal functional that we call the graphon GL functional. We investigate the sharp-interface limits of the graph GL and graphon GL functionals, and we relate these limits to a nonlocal total-variation (TV) functional. We express the limiting GL functional in terms of Young measures and thereby obtain a probabilistic interpretation of the minimization problem in the large-graph limit. Finally, to develop intuition about graphon GL functionals, we determine the GL minimizer for several example families of graphons.

Zhang, Edith↗
NASA NTRS2020

Dynamic IT Security Database and Analytics for Launch Control Systems Software

During the Summer 2020 session, I worked with intern Destani S. Van Arsdalen of EGS Software. Together, we co-created a tool to aid the dynamic investigation, updated over time,of the security compliance of LCS COTS and open source software. We originally planned touse spreadsheet software for management and analysis, but through this exploratoryproject, chose to use Python and JSON after receiving feedback on our project’s current anddesired capabilities at that time.At first, the project was solely designed to help on-board new COTS software, based on aquestionnaire that could be filled out for each software package. This, combined with usingthe spreadsheet application’s web-query capabilities to fetch information from the NVD,allowed presentation and analytics cells to automatically populate as elements of themanually-filled questionnaire changed. While this system was promising, we decided tochange technologies for a few reasons. In the spreadsheet, single cells could not hold complexdata like arrays and objects. The automatic population of cells and dynamic updates made itdifficult to manage and add new features. And finally, it had limited extensibility sinceadding new software required significant understanding of how both the spreadsheet wasconstructed, and the more obscure, proprietary scripting languages packaged with it.The pivot to a standard computer science database language of JSON, aided by thescripting capabilities of Python, greatly helped to improve the project’s functionality. First,and most importantly, the script’s import and analysis of database data is easilyreproducible. Additional data analysis can be modularly added without requiringmodification of the script and is capable of routine scheduling. The revised process can besplit into three parts. First, the conversion of LCS asset and software documentation into theJSON hierarchical database format. Second, the merging of this database with the NVD,forming a new data structure, using CPEs of the CVE object as a linking element betweenthem. And third, the automatically performed analytics and analysis of the combined data,in a modular and extensible format, to produce better informed business decisions. The outputted graphs, for example, are automatically generated by the Python script inconnection with the combined database. This allows updated graphs and any analytics to be re-rendered automatically following updates to the LCS’s initial asset documentation. Afinal report can then be programmatically and easily constructed from these sources to allow fully reproducible metrics for heavily evidenced risk management decisions.

it↗
NASA NTRSDate not supplied

Airspace Research and Development Portfolio Assessment of Urban Air Mobility using Knowledge Graph Data Science

National Aeronautics and Space Administration (NASA) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of Urban Air Mobility (UAM) operations. The UAM vision is one in which advanced technologies and new operational procedures enable practical and cost-effective air transport as an integrated mode of movement of people and goods throughout metropolitan areas. To safely support UAM operations at scale in the National Airspace System (NAS), NASA’s Air Traffic Management-Exploration (ATM-X) project has been conducting research that evolves the UAM air traffic management system towards a highly automated and operationally flexible system of the future. The complexity of UAM airspace evolution to accommodate the increasing tempo of UAM operations over time is managed through the UAM airspace research roadmap, which is a system engineering approach to the R&D of complex system-of-systems, where system’s interdependencies make it nearly impossible to define requirements for individual elements of the system in isolation. These interdependencies form a knowledge graph (node-link network) with a highly complex structure far beyond the human user’s ability to extract insights for project management’s research portfolio assessment. This study applies advanced data analytics in knowledge graph to the UAM knowledge graph to facilitate the portfolio assessment.

ATM↗
NASA NTRSDate not supplied

Airspace Research and Development Portfolio Assessment of Urban Air Mobility using Knowledge Graph Data Science

National Aeronautics and Space Administration (NASA) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of Urban Air Mobility (UAM) operations. The UAM vision is one in which advanced technologies and new operational procedures enable practical and cost-effective air transport as an integrated mode of movement of people and goods throughout metropolitan areas. To safely support UAM operations at scale in the National Airspace System (NAS), NASA’s Air Traffic Management-Exploration (ATM-X) project has been conducting research that evolves the UAM air traffic management system towards a highly automated and operationally flexible system of the future. The complexity of UAM airspace evolution to accommodate the increasing tempo of UAM operations over time is managed through the UAM airspace research roadmap, which is a system engineering approach to the R&D of complex system-of-systems, where system’s interdependencies make it nearly impossible to define requirements for individual elements of the system in isolation. These interdependencies form a knowledge graph (node-link network) with a highly complex structure far beyond the human user’s ability to extract insights for project management’s research portfolio assessment. This study applies advanced data analytics in knowledge graph to the UAM knowledge graph to facilitate the portfolio assessment.

ATM↗
DOE OSTI2024

SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks

While Spiking Neural Networks (SNNs) show a lot of promise, it is difficult to optimize them because applying traditional gradient-based optimization techniques is difficult. Even though evolutionary algorithms (EAs) have been shown to promise to optimize SNNs, understanding the relationship between evolving the characteristics of SNNs and their performance to improve the optimization algorithm is challenging because of the complex characteristics and huge population size. We propose visual analytics with novel graph embedding for evolutionary SNNs to address the challenges. While existing graph embedding techniques have limitations in preserving the specific features of the nodes and edges, our approach maintains them. Also, we develop visual analytics for understanding the relationship between the network performance and the features of nodes and edges and exploring and analyzing the evolving SNNs to build insights into improving the EA.

Chae, Junghoon [ORNL] (ORCID:0000000206016746)↗
NASA NTRS2012

Calculation of Sensitivity Derivatives in an MDAO Framework

During gradient-based optimization of a system, it is necessary to generate the derivatives of each objective and constraint with respect to each design parameter. If the system is multidisciplinary, it may consist of a set of smaller "components" with some arbitrary data interconnection and process work ow. Analytical derivatives in these components can be used to improve the speed and accuracy of the derivative calculation over a purely numerical calculation; however, a multidisciplinary system may include both components for which derivatives are available and components for which they are not. Three methods to calculate the sensitivity of a mixed multidisciplinary system are presented: the finite difference method, where the derivatives are calculated numerically; the chain rule method, where the derivatives are successively cascaded along the system's network graph; and the analytic method, where the derivatives come from the solution of a linear system of equations. Some improvements to these methods, to accommodate mixed multidisciplinary systems, are also presented; in particular, a new method is introduced to allow existing derivatives to be used inside of finite difference. All three methods are implemented and demonstrated in the open-source MDAO framework OpenMDAO. It was found that there are advantages to each of them depending on the system being solved.

Moore, Kenneth T.↗
NASA NTRS2004

Automated Processing of ISIS Topside Ionograms into Electron Density Profiles

Modeling of the topside ionosphere has for the most part relied on just a few years of data from topside sounder satellites. The widely used Bent et al. (1972) model, for example, is based on only 50,000 Alouette 1 profiles. The International Reference Ionosphere (IRI) (Bilitza, 1990, 2001) uses an analytical description of the graphs and tables provided by Bent et al. (1972). The Alouette 1, 2 and ISIS 1, 2 topside sounder satellites of the sixties and seventies were ahead of their times in terms of the sheer volume of data obtained and in terms of the computer and software requirements for data analysis. As a result, only a small percentage of the collected topside ionograms was converted into electron density profiles. Recently, a NASA-funded data restoration project has undertaken and is continuing the process of digitizing the Alouette/ISIS ionograms from the analog 7-track tapes. Our project involves the automated processing of these digital ionograms into electron density profiles. The project accomplished a set of important goals that will have a major impact on understanding and modeling of the topside ionosphere: (1) The TOPside Ionogram Scaling and True height inversion (TOPIST) software was developed for the automated scaling and inversion of topside ionograms. (2) The TOPIST software was applied to the over 300,000 ISIS-2 topside ionograms that had been digitized in the fkamework of a separate AISRP project (PI: R.F. Benson). (3) The new TOPIST-produced database of global electron density profiles for the topside ionosphere were made publicly available through NASA s National Space Science Data Center (NSSDC) ftp archive at . (4) Earlier Alouette 1,2 and ISIS 1, 2 data sets of electron density profiles from manual scaling of selected sets of ionograms were converted fiom a highly-compressed binary format into a user-friendly ASCII format and made publicly available through nssdcftp.gsfc.nasa.gov. The new database for the topside ionosphere established as a result of this project, has stimulated a multitude of new studies directed towards a better description and prediction of the topside ionosphere. Marinov et al. (2004) developed a new model for the upper ion transition height (Oxygen to Hydrogen and Helium) and Bilitza (2004) deduced a correction term for the I N topside electron density model. Kutiev et al. (2005) used this data to develop a new model for the topside ionosphere scale height (TISH) as a function of month, local time, latitude, longitude and solar flux F10.7. Comparisons by Belehaki et al. (2005) show that TISH is in general agreement with scale heights deduced from ground ionosondes but the model predicts post-midnight and afternoon maxima whereas the ionosonde data show a noon maximum. Webb and Benson (2005) reported on their effort to deduce changes in the plasma temperature and ion composition from changes in the topside electron density profile as recorded by topside sounders. Limitations and possible improvements of the IRI topside model were discussed by Coisson et al. (2005) including also the possible use of the NeQuick model, Our project progressed in close collaboration and coordination with the GSFC team involved in the ISIS digitization effort. The digitization project was highly successful producing a large amount of digital topside ionograms. Several no-cost extensions of the TOPIST project were necessary to keep up with the pace and volume of the digitization effort.

Reinisch, bodo W.↗
NASA NTRS1985

Analysis of three-dimensional solidification interface shape

The determination of the shape of the solidification interface in a cooling melt by the thermal boundary conditions is investigated analytically, extending the analysis of Siegel (1982) and Siegel and Sosoka (1982) to the three-dimensional case. The solutions are generated by continuation into the solid region from conditions at the cooled wall, and some numerical results are presented in tables and graphs. These findings and the analytical approach employed are applicable to crystallization and metal-forming processes.

Siegel, R.↗