Multifidelity data fusion in convolutional encoder/decoder assembly networks for computational fluid dynamics.
Abstract not provided.
SEARCH · Engineering Papers
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.
Abstract not provided.
Technologies for increasing the bandwidth of partitioned hierarchical networks is disclosed. If each partition of network groups of a computer network are isolated, then the connections between the network groups of different partitions may go unused. However, careful selection of the network connections between partitions of different network groups may allow for a pseudo-direct connection between two network groups of the same partition using a single non-blocking switch in a network group of a different partition. Such a configuration can increase the effective bandwidth available within a partition without affecting the bandwidth available in another partition.
Abstract not provided.
The Department of Energy, Office of Science operates world-leading facilities for experimental, observational, and computational science. DOE supercomputing facilities will reach performance at the scale of ExaFLOPs in the coming years, enabling new vistas of scale and precision for large scale simulations and data analysis. Experimental scientific facilities are undergoing similar upgrades that will lead to higher data rates and correspondingly larger computational demands, and will increase the need for near-real-time processing and resilient support for more complex workflows. A transformation of science is underway, with workloads at supercomputing facilities increasingly driven by this explosion of data from instruments and experimental facilities, as well as the accelerating use of Artificial Intelligence (AI) as a tool for scientific discovery. A seamless integration of computing, networking, instruments, and experimental facilities is required to support these emerging workloads and open up a new frontier of U.S. leadership in scientific discovery. We propose to accomplish this by providing frictionless access to the ASCR supercomputing facilities. We describe our vision of combining the power of ASCR supercomputers and networking infrastructure into an integrated scalable fabric, available to end user scientists via interfaces that aim to automate and simplify access to high performance computing systems. This will enable unprecedented computational science capabilities for experimental and observational facilities, and will create new opportunities to combine large simulations and modeling with experimental facility data analysis. This blueprint for creating an integrated network of computational and experimental facilities will provide an enriched discovery environment and open doors for new scientific communities to access the DOE’s world-leading computing and networking capabilities.
Computer and communication network attacks are commonly orchestrated through Wireless Access Points (WAPs). This paper summarizes proof-of-concept research activity aimed at developing a physical layer Radio Frequency (RF) air monitoring capability to limit unauthorizedWAP access and mprove network security. This is done using Differential Evolution (DE) to optimize the performance of a Learning from Signals (LFS) classifier implemented with RF Distinct Native Attribute (RF-DNA) fingerprints. Performance of the resultant DE-optimized LFS classifier is demonstrated using 802.11a WiFi devices under the most challenging conditions of intra-manufacturer classification, i.e., using emissions of like-model devices that only differ in serial number. Using identical classifier input features, performance of the DE-optimized LFS classifier is assessed relative to a Multiple Discriminant Analysis / Maximum Likelihood (MDA/ML) classifier that has been used for previous demonstrations. The comparative assessment is made using both Time Domain (TD) and Spectral Domain (SD) fingerprint features. For all combinations of classifier type, feature type, and signal-to-noise ratio considered, results show that the DEoptimized LFS classifier with TD features is uperior and provides up to 20% improvement in classification accuracy with proper selection of DE parameters.
Accessing and managing large amounts of data is a great challenge in collaborative computing environments where resources and users are geographically distributed. Recent advances in network technology led to next-generation high-performance networks, allowing high-bandwidth connectivity. Efficient use of the network infrastructure is necessary in order to address the increasing data and compute requirements of large-scale applications. We discuss several open problems, evaluate emerging trends, and articulate our perspectives in network-aware data management.
Software-defined networking (SDN) is an emerging technology of efficiently controlling and managing computer networks, such as in data centres, wide-area networks, as well as in ubiquitous communication. In this study, the authors explore the idea of embedding the SDN components, represented by SDN controller and virtual switch, in end-hosts to improve network performance. In particular, the authors consider load balancing across multiple network interfaces on end-hosts with different link capacity scenarios. The authors have explored and implemented different SDN-based load-balancing approaches based on OpenFlow software switches, and have demonstrated the feasibility and the potential of this approach. The proposed system has been evaluated with MultiPath transmission control protocol (MPTCP). Furthermore, the proposed results demonstrated the potential of applying the SDN concepts on multi-homed devices resulting in an increase in achieved throughput of 55% compared to the legacy single network approach and 10% compared to the MPTCP.
Opportunistic managed access to local in-network compute resources can improve the performance of distributed applications and reduce the dependence on shared network resources. Instead of backhauling application data to a centralized cloud data center for processing, networked services may be adaptively and continuously dispersed into shared compute resources that are closer to the source of need. While this approach has several benefits, support for mission-aware access to computation is often an afterthought, and is implemented as a brittle extension over traditional load-balancer solutions.In this work, we investigate the design of two priority-aware resource allocation strategies and two load-balancing dispatching strategies as first class citizens in an open-source dispersed computing middleware. We present a control theoretic analysis of these load-balancing primitives to identify weaknesses and strengths in our design, and recommend future directions. In parallel, we prototype two priority-aware allocation algorithms to validate our priority predictions. In initial experiments our prototype shows substantial gains in processing prioritized load. Finally, we make our source-code and experimental configurations open source.
Mota is a library that provides several heuristics for mapping tasks to compute ranks (processes) on a networked computer cluster or supercomputer. It was originally designed for task placement of adaptive mesh refinement codes (AMR). It is multi-objective in the sense that it simultaneously balances (potentially multiple types of) computational load on each rank as well as the communication traffic between the boxes. The heuristics used for mapping include algorithms such as greedy list assignment and space-filling curves, as well as algorithms from graph analysis such as adjacency matrix bandwidth reduction, recursive bisection, and greedy graph placement.
A final report is made of a three-year effort to develop a new forecasting paradigm for computer network performance. This effort was made in co-ordination with Fermi Lab's construction of e-Weather Center.
A framework is provided for modeling the activity surrounding user credentials and/or machine level activity on a computer network using computer event logs by viewing the logs attributed to each user as a multivariate data stream. The methodology performs well in detecting compromised user credentials at a very low false positive rate. Such a methodology may detect both users of compromised credentials by external actors and otherwise authorized users who have begun engaging in malicious activity.
Scientists from many domains desire to address problems within the next decade that, by all estimates, require computer systems that can achieve sustained exaflop computing rates (i.e., 1 x 10{sup 18} floating point operations per second) with real-world applications. Simply scaling existing designs is insufficient: analysis of current technological trends suggests that only a few architectural components are on track to reach the performance levels needed for exascale computing. The network connecting computer system nodes presents a particularly difficult challenge because of the prevalence of a wide variety of communication patterns and collective communication operations in algorithms used in scientific applications and their tendency to be the most significant limit to application scalability. Researchers at Oak Ridge National Laboratory and elsewhere are actively working to overcome these network-related scalability barriers using advanced hardware and software design, alternative network topologies, and performance prediction using modeling and simulation.
Several scenarios exist in the modern interconnected world which call for an efficient network interdiction algorithm. Applications are varied, including various monitoring and load shedding applications on large smart energy grids, computer network security, preventing the spread of Internet worms and malware, policing international smuggling networks, and controlling the spread of diseases. In this paper we consider some natural network optimization questions related to the budget constrained interdiction problem over general graphs, specifically focusing on the sensor/switch placement problem for large-scale energy grids. Many of these questions turn out to be computationally hard to tackle. We present a particular form of the interdiction question which is practically relevant and which we show as computationally tractable. A polynomial-time algorithm will be presented for solving this problem.
Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings.
As electric power systems undergo a transformative upgrade with the integration of advanced technologies to enable the smarter electric grid, professionals who work in the area require a new understanding of the evolving complexity of the grid. Cyber Infrastructure for the Smart Electric Grid delivers a comprehensive overview of the fundamental principles of smart grid operation and control, smart grid technologies, including sensors, communication networks, computation, data management, and cyber security, and the interdependencies between the component technologies on which a smart grid's security depends. The book offers readers the opportunity to critically analyze the smart grid infrastructure needed to sense, communicate, compute, and control in a secure way.
As any mechanical system ages, broken or outdated parts must be replaced; nuclear power plants (NPPs) are no different. The average age of a NPP in the United States' aging fleet of commercial reactors is 35 years, with many of these plants operating under extensions of their original licenses. These plants, originally designed in the 1960's and 1970's, are controlled by analog instrumentation and control (I and C) systems, and have since been upgraded (to varying degrees) to hybrid analog-digital systems. As these NPPs are upgraded to continue operating and to meet more stringent safety requirements imposed by the Nuclear Regulatory Commission (NRC), the implementation of digital systems to monitor and run the power plant introduces new vulnerabilities that must be addressed. The main objectives of a vulnerability assessment (VA) are to identify, quantify, and prioritize all of the susceptibilities inherent in a system. This allows for all weaknesses to be analyzed, and for the most serious concerns to be addressed first. Traditional VA methodologies deal with the analysis of physical systems associated with the NPP; with the introduction of digital control systems and computer networks, these methodologies must be expanded to include these fundamentally different systems and vulnerability concerns. Digital systems have been used in NPPs since the 1980's, but only for non-safety control systems; attacks on these systems were not deemed consequential, and no dedicated VA methodology was required. However, 'all new NPPs are being designed with integrated digital instrumentation and control systems as the backbone of protection, controls, alarms, and display and monitoring'. This gives rise to new vulnerabilities such as disrupted data displays, the suppression of critical alarms, or unauthorized access to secure systems from connected networks. The NRC released formal cybersecurity regulations in March 2009 (10 CFR 73.54), as well as a guide for the program in January 2010 (RG 5.71). However, the regulations and guide provide limited insight on how to identify these vulnerabilities; the focus is on remediating them once found. Hence, there is a need for a comprehensive, systematic methodology to conduct a VA on digital computer and communications and network systems. In this paper, we review traditional VA methodologies and discuss relevant cases. Then we discuss challenges to vulnerabilities within the context of modernization of the fleet and what needs to be done to address this issue.
n the pass-the-hash attack, hackers repeatedly steal password hashes and move through a computer network with the goal of reaching a computer with high level administrative privileges. In this paper we apply graph coarsening in network graphs for the purpose of detecting hackers using this attack or assessing the risk level of the network's current state. We repeatedly take graph minors, which preserve the existence of paths in the graph, and take powers of the adjacency matrix to count the paths. This allows us to detect the existence of paths as well as find paths that have high risk of being used by adversaries.
There is a national cyber dilemma that threatens the very fabric of government, commercial and private use operations worldwide. Much is written about 'what' the problem is, and though the basis for this paper is an assessment of the problem space, we target the 'how' solution space of the wide-area national information infrastructure through the advancement of science, technology, evaluation and analysis with actionable results intended to produce a more secure national information infrastructure and a comprehensive national cyber defense capability. This cybersecurity High Performance Computing (HPC) analysis concepts, planning and roadmap activity was conducted as an assessment of cybersecurity analysis as a fertile area of research and investment for high value cybersecurity wide-area solutions. This report and a related SAND2010-4765 Assessment of Current Cybersecurity Practices in the Public Domain: Cyber Indications and Warnings Domain report are intended to provoke discussion throughout a broad audience about developing a cohesive HPC centric solution to wide-area cybersecurity problems.