Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Operator Networks”

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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
NASA NTRS1996

Sequence-of-Events-Driven Automation of the Deep Space Network

In February 1995, sequence-of-events (SOE)-driven automation technology was demonstrated for a Voyager telemetry downlink track at DSS 13. This demonstration entailed automated generation of an operations procedure (in the form of a temporal dependency network) from project SOE information using artificial intelligence planning technology and automated execution of the temporal dependency network using the link monitor and control operator assistant system. This article describes the overall approach to SOE-driven automation that was demonstrated, identifies gaps in SOE definitions and project profiles that hamper automation, and provides detailed measurements of the knowledge engineering effort required for automation.

Hill, R., Jr.↗
NASA NTRS2014

Networked Operations of Hybrid Radio Optical Communications Satellites

In order to address the increasing communications needs of modern equipment in space, and to address the increasing number of objects in space, NASA is demonstrating the potential capability of optical communications for both deep space and near-Earth applications. The Integrated Radio Optical Communications (iROC) is a hybrid communications system that capitalizes on the best of both the optical and RF domains while using each technology to compensate for the other's shortcomings. Specifically, the data rates of the optical links can be higher than their RF counterparts, whereas the RF links have greater link availability. The focus of this paper is twofold: to consider the operations of one or more iROC nodes from a networking point of view, and to suggest specific areas of research to further the field. We consider the utility of Disruption Tolerant Networking (DTN) and the Virtual Mission Operation Center (VMOC) model.

Delay Tolerant Networking↗
NASA NTRS1987

Design considerations for the beamwaveguide retrofit of a ground antenna station

A primary requirement of the NASA Deep Space Network (DSN) is to provide for optimal reception of very low signal levels. This requirement necessitates optimizing the antenna gain to the total system operating noise level quotient. Low overall system noise levels of 16 to 20 K are achieved by using cryogenically cooled preamplifiers closely coupled with an appropriately balanced antenna gain/spillover design. Additionally, high-power transmitters (up to 400 kW CW) are required for spacecraft emergency command and planetary radar experiments. The frequency bands allocated for deep space telemetry are narrow bands near 2.1 and 2.3 GHz (Ka-band), 7.1 and 8.4 GHz (X-band), and 32 and 34.5 GHz (Ka-band). In addition, planned operations for the Search for Extraterrestrial Intelligence (SETI) program require continuous low-noise receive coverage over the 1 to 10 GHz band. To summarize, DSN antennas must operate efficiently with low receive noise and high-power uplink over the 1 to 35 GHz band.

Veruttipong, T.↗
DOE OSTI2021

Encoding Frequency Constraints in Preventive Unit Commitment Using Deep Learning With Region-of-Interest Active Sampling

With the increasing penetration of renewable energy, frequency response and its security are of significant concerns for reliable power system operations. Frequency-constrained unit commitment (FCUC) is proposed to address this challenge. Despite existing efforts in modeling frequency characteristics in unit commitment (UC), current strategies can only handle oversimplified low-order frequency response models and do not consider wide-range operating conditions. This paper presents a generic data-driven framework for FCUC under high renewable penetration. Here, deep neural networks (DNNs) are trained to predict the frequency response using real data or high-fidelity simulation data. Next, the DNN is reformulated as a set of mixed-integer linear constraints to be incorporated into the ordinary UC formulation. In the data generation phase, all possible power injections are considered, and a region-of-interest active sampling is proposed to include power injection samples with frequency nadirs closer to the UFLC threshold, which enhances the accuracy of frequency constraints in FCUC. The proposed FCUC is investigated on the IEEE 39-bus system. Then, a full-order dynamic model simulation using PSS/E verifies the effectiveness of FCUC in frequency-secure generator commitments.

42 ENGINEERING↗
DOE OSTI2021

Evaluating Automated Face Identity-Masking Methods with Human Perception and a Deep Convolutional Neural Network

Face de-identification (or “masking”) algorithms have been developed in response to the prevalent use of video recordings in public places. Here, we evaluated the success of face identity masking for human perceivers and a deep convolutional neural network (DCNN). Eight de-identification algorithms were applied to videos of drivers’ faces, while they actively operated a motor vehicle. These masks were pre-selected to be applicable to low-quality video and to maintain coarse information about facial actions. Humans studied high-resolution images to learn driver identities and were tested on their recognition of active drivers in low-resolution videos. Faces in the videos were either unmasked or were masked by one of the eight algorithms. When participants were tested immediately after learning (Experiment 1), all masks reduced identification, with six of eight masks reducing identification to extremely poor performance. In a second experiment, two of the most effective masks were tested after a delay of 7 or 28 days. The delay did not further reduce identification of the masked faces. In all masked conditions, participants maintained stringent decision criteria, with low confidence in recognition, further indicating the effectiveness of the masks. Next, the DCNN performed an identity-matching task between high-resolution images and masked videos—a task analogous to that done by humans. The pattern of accuracy for the DCNN mirrored some, but not all, aspects of human performance, highlighting the need to test the effectiveness of identity masking for both humans and machines. The DCNN was also tested on its ability to match identity between masked and unmasked versions of the same video, based only on the face. DCNN performance for the eight masks offers insight into the nature of the information in faces that is coded in these networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Methods for R&D Portfolio Analysis and Evaluation (Workshop Report)

The Workshop on Methods for R&D Portfolio Analysis and Evaluation convened on 17–18 July 2019 at the National Renewable Energy Laboratory in Golden, Colorado, and examined strengths and weaknesses of the various methodologies applicable to R&D portfolio modeling, analysis, and decision support, given pragmatic constraints such as data availability, uncertainties in estimating the impact of R&D spending, and practical operational overheads. Participants employed their deep expertise in approaches such as stochastic optimization, real options, Monte-Carlo analysis, Bayesian networks, decision theory, complex systems analysis, deep uncertainty, and technology-evolution modeling to critique the initial example models developed by the project’s core team and to conduct thought experiments grounded in real-life technology models, progress data, expert elicitation, and portfolio information. This engagement of participants’ methodological expertise with the practical requirements of real-life portfolio decision support yielded ideas for improved approaches, alternative methodological hypotheses, and hybridization of methodologies that are well-grounded theoretically, computationally sound, and realistically executable given data availability and other practical constraints.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Methods for R&D Portfolio Analysis and Evaluation (Workshop Report)

The Workshop on Methods for R&D Portfolio Analysis and Evaluation convened on 17-18 July 2019 at the National Renewable Energy Laboratory in Golden, Colorado, and examined strengths and weaknesses of the various methodologies applicable to R&D portfolio modeling, analysis, and decision support, given pragmatic constraints such as data availability, uncertainties in estimating the impact of R&D spending, and practical operational overheads. Participants employed their deep expertise in approaches such as stochastic optimization, real options, Monte-Carlo analysis, Bayesian networks, decision theory, complex systems analysis, deep uncertainty, and technology-evolution modeling to critique the initial example models developed by the project’s core team and to conduct thought experiments grounded in real-life technology models, progress data, expert elicitation, and portfolio information. This engagement of participants’ methodological expertise with the practical requirements of real-life portfolio decision support yielded ideas for improved approaches, alternative methodological hypotheses, and hybridization of methodologies that are well-grounded theoretically, computationally sound, and realistically executable given data availability and other practical constraints.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Machine Learning Solutions for a Stable Grid Recovery

Grid operating security studies are typically employed to establish operating boundaries, ensuring secure and stable operation for a range of operation under NERC guidelines. However, if these boundaries are severely violated, existing system security margins will be largely unknown, as would be a secure incremental dispatch path to higher security margins while continuing to serve load. As an alternative to the use of complex optimizations over dynamic conditions, this work employs the use of machine learning to identify a sequence of secure state transitions which place the grid in a higher degree of operating security with greater static and dynamic stability margins. Several reinforcement learning solution methods were developed using deep learning neural networks, including Deep Q-learning, Mu-Zero, and the continuous algorithms Proximal Reinforcement Learning, and Advantage Actor Critic Learning. The work is demonstrated on a power grid with three control dimensions but can be scaled in size and dimensionality, which is the subject of ongoing research.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1975

Implementation of the 64-meter-diameter Antennas at the Deep Space Stations in Australia and Spain

The management and construction aspects of the Overseas 64-m Antenna Project in which two 64-m antennas were constructed at the Tidbinbilla Deep Space Communications Complex in Australia, and at the Madrid Deep Space Communications Complex in Spain are described. With the completion of these antennas the Deep Space Network is equipped with three 64-m antennas spaced around the world to maintain continuous coverage of spacecraft operations. These antennas provide approximately a 7-db gain over the capabilities of the existing 26-m antenna nets. The report outlines the project organization and management, resource utilization, fabrication, quality assurance, and construction methods by which the project was successfully completed. Major problems and their solutions are described as well as recommendations for future projects.

Bartos, K. P.↗
NASA NTRS1978

The deep space network

Deep Space Network progress in flight support, tracking and data acquisition research and technology, network engineering, hardware and software implementation, and operations are reported.

Source record↗
NASA NTRS1983

The Telecommunications and Data Acquisition Report

Developments in programs in telecommunication and data acquisition in space communications, radio navigation, radio science, and ground based radio astronomy are reported. Activities of the deep space network (DSN) and its associated ground communication facility (GCF) in planning, supporting research and technology, implementation, and in operations are outlined. The publication of reports on the application of radio interferometry at microwave frequencies for geodynamic measurements are presented. Implementation and operation for searching the microwave spectrum is reported.

Posner, E. C.↗
NASA NTRS1988

The Telecommunications and Data Acquisition Report

In space communications, radio navigation, radio science, and ground based radio and radar astronomy, activities of the Deep Space Network and its associated Ground Communications Facility in planning, in supporting research and technology, in implementation, and in operations are reported. Also included is TDA funded activity at JPL on data and information systems and reimbursable DSN work performed for other space agencies through NASA.

Posner, E. C.↗
NASA NTRS1989

The Telecommunications and Data Acquisition Report

Archival reports on developments in programs managed by JPL's Office of Telecommunications and Data Acquisition (TDA) are presented. Activities of the Deep Space Network (DSN) and its associated Ground Communications Facility (GCF) related to DSN advanced systems, systems implementation, and DSN operations are addressed. In addition, recent developments in the NASA SETI (Search for Extraterrestrial Intelligence) sky survey are summarized.

Posner, E. C.↗
NASA NTRS1989

The Telecommunications and Data Acquisition Report

Developments in programs managed by JPL's Office of Telecommunications and Data Acquisition (TDA) are provided. Activities of the Deep Space Network and its associated Ground Communications Facility in planning, in supporting research and technology, in implementation, and in operations are reported in space communications, radio navigation, radio science, and ground-based radio and radar astronomy.

Posner, E. C.↗
NASA NTRS2020

Experimental Validation of Swarm Array Results Using Mars Cube One (Marco) A,B Downlink Signals

In this paper, we investigate the feasibility of calibrating an orbiting phased array composed of CubeSat class spacecraft together with a larger reference (or “chief”) spacecraft, comprising an overall Swarm Array. Considered as an analog to the Deep Space Network (DSN) Uplink Arraying problem [1], a spaceborne Swarm Array that can potentially deliver comparable or even greater operational performance than large monolithic spacecraft (such as increased data rates for telecommunications, or greater baselines for improved spatial resolution), thus increasing future mission capability but with significantly enhanced flexibility, evolvability and robustness.

Kahan, Daniel↗
NASA NTRS2020

Experimental Validation of Swarm Array Results Using Mars Cube One (MarCO) A,B Downlink Signals

In this paper, we investigate the feasibility of calibrating an orbiting phaased array composed of CubeSat class spacecraft together with a larger reference (or “chief”) spacecraft, comprising an overall Swarm Array. Considered as an analog to the Deep Space Network (DSN) Uplink Arraying problem [1], a spaceborne Swarm Array that can potentially deliver comparable or even greater operational performance than large monolithic spacecraft (such as increased datarates for telecommunications, or greater baselines for improved spatial resolution), thus increasing future mission capability but with significantly enhanced flexibility, evolvability and robustness.

Vilnrotter, Victor↗
DOE OSTI2023

Adaptive Deep Reinforcement Learning Algorithm for Distribution System Cyber Attack Defense With High Penetration of DERs

With grid modernization, smart inverters are increasingly used to execute advanced controls for distribution network reliability. However, this also increases the cyber-attack space. Here this paper focuses on the defense approaches to restore the system to normal operation circumstances in the presence of cyber-attacks. A unique deep reinforcement learning (DRL) method is developed to minimize voltage violations and reduce power losses for impacted feeders. The defense problem is reformulated as a Markov decision-making process to dynamically control DERs while minimizing load shedding. This is achieved via an improved soft actor-critic (SAC)-based DRL algorithm, which can govern DER set points and load-shedding scenarios in discrete and continuous modes via the auto-tune entropy and Gaussian policy features. Numerical comparison results on the modified IEEE 123-node system with other control approaches, such as Volt-VAR (VV), Volt-Watt (VW), and model predictive control (MPC) show that the proposed method can eliminate voltage violations and provide feasible control actions that perform complete mitigation of cyber-threats.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2012

Conceptual Design of a Communication-Based Deep Space Navigation Network

As the need grows for increased autonomy and position knowledge accuracy to support missions beyond Earth orbit, engineers must push and develop more advanced navigation sensors and systems that operate independent of Earth-based analysis and processing. Several spacecraft are approaching this problem using inter-spacecraft radiometric tracking and onboard autonomous optical navigation methods. This paper proposes an alternative implementation to aid in spacecraft position fixing. The proposed method Network-Based Navigation technique takes advantage of the communication data being sent between spacecraft and between spacecraft and ground control to embed navigation information. The navigation system uses these packets to provide navigation estimates to an onboard navigation filter to augment traditional ground-based radiometric tracking techniques. As opposed to using digital signal measurements to capture inherent information of the transmitted signal itself, this method relies on the embedded navigation packet headers to calculate a navigation estimate. This method is heavily dependent on clock accuracy and the initial results show the promising performance of a notional system.

Anzalone, Evan J.↗