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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Soft Actor Critic Based Volt-VAR Co-optimization in Active Distribution Grids

Modern distribution networks are undergoing several technical challenges, such as voltage fluctuations, because of high penetration of distributed energy resources (DERs). This paper proposes a deep reinforcement learning (DRL)-based Volt VAR co-optimization technique for reducing voltage fluctuations as well as power loss under high penetration of DERs. In addition, the proposed approach minimizes the operational cost of the grid. A stochastic policy optimization based soft actor critic (SAC) agent is proposed to configure the optimal set-points of the reactive power outputs of the inverters. The performance of the proposed model is verified on the modified IEEE 34- and 123-bus systems and compared with a base case scenario with no reactive supply by inverters, and a local droop control approach. The results demonstrate that the proposed framework outperforms the conventional droop control method in improving the voltage profile, minimizing the network power loss, and reducing grid operational cost.

—Distribution grids, deep reinforcement learning, ↗
NASA NTRS1982

Telecommunications and data acquisition systems support for the Viking 1975 mission to Mars, volume 5

The support provided by the Deep Space Network to the Viking Project from 1 June 1978 to 30 April 1980 is described. The project was supported by the worldwide network of Deep Space Stations with 26- and 64-meter-diameter antennas, together with a ground communications system, for the transmission of commands, telemetry, radio metric data, and operational instructions between the stations and the network operation control center in Pasadena, California. Assistance was substantially less than in the previous phases of the Viking Project in order to provide adequate support to the Pioneer and Voyager Projects.

Larkin, W. E.↗
NASA NTRS1976

Viking mission support

On April 26, 1976, the network operations control center was declared available for planetary operations in support of the Viking project. This final capability in the network configuration for Viking had been delayed since February with hardware and software problems both in the control center and at the Deep Space stations. The effect of these problems, particularly insofar as they affected production of intermediate data records, the resolution of the problems, and the current status of the network operations control center in the Viking environment, are given in this article. Also discussed are the operational verification tests performed to check out the new capabilities and associated procedures. The Viking project tests supported by the DSN and finally the DSN support of Viking cruise operations, along with some statistics on performance, are included.

Mudgway, D. J.↗
DOE OSTI2022

A Deep Reinforcement Learning-based Reserve Optimization in Active Distribution Systems for Tertiary Frequency Regulation

Federal Energy Regulatory Commission (FERC)Orders 841 and 2222 have recommended that distributed energy resources (DERs) should participate in energy and reserve markets; therefore, a mechanism needs to be developed to facilitate DERs’ participation at the distribution level. Although the available reserve from a single distribution system may not be sufficient for tertiary frequency regulation, stacked and coordinated contributions from several distribution systems can enable them participate in tertiary frequency regulation at scale. This paper proposes a deep reinforcement learning (DRL)-based approach for optimization of requested aggregated reserves by system operators among the clusters of DERs. The co-optimization of cost of reserve, distribution network loss, and voltage regulation of the feeders are considered while optimizing the reserves among participating DERs. The proposed framework adopts deep deterministic policy gradient (DDPG), which is an algorithm based on an actor-critic method. The effectiveness of the proposed method for allocating reserves among DERs is demonstrated through case studies on a modified IEEE 34-node distribution system.

deep reinforcement learning, distributed energy re↗
NASA NTRS1992

Environmental projects. Volume 15: Environmental assessment: Proposed 1-megawatt radar transmitter at the Mars site

The Goldstone Deep Space Communications Complex (GDSCC), located in the Mojave Desert about 64.5 km (40 mi) north of Barstow, California. and about 258 km (160 mi) northeast of Pasadena, California, is part of the National Aeronautics and Space Administration's (NASA's) Deep Space Network (DSN), one of the world's larger and more sensitive scientific telecommunications and radio navigation networks. The Goldstone Complex is managed, technically directed, and operated for NASA by the Jet Propulsion Laboratory (JPL) of the California Institute of Technology in Pasadena, California. Activities at the GDSCC support the operation of six parabolic dish antennas located at five separate sites called Deep Space Stations (DSS's). Four sites, named Echo, Mars, Uranus, and Apollo, are operational for space missions, while the remaining Venus Site is devoted to research and development activities. The Mars Site at the GDSCC contains two antennas: the Uranus antenna (DSS 15, 34 m) and the Mars antenna (DSS 14, 70 m). This present volume deals solely with the DSS-14 Mars antenna. The Mars antenna not only can act as a sensitive receiver to detect signals from spacecraft, but it also can be used in radar astronomy as a powerful transmitter to send out signals to probe the solar system. At present, the Mars antenna operates as a continuous-wave microwave system at a frequency of 8.51 GHz at a power level of 0.5 MW. JPL has plans to upgrade the Mars antenna to a power level of 1 MW. Because of the anticipated increase in the ambient levels of radio frequency radiation (RFR), JPL retained Battelle Pacific Northwest Laboratories (BPNL), Richland, Washington, to conduct an environmental assessment with respect to this increased RFR. This present volume is a JPL-expanded version of the BPNL report titled Environmental Assessment of the Goldstone Solar System Radar, which was submitted to JPL in Nov. 1991. This BPNL report concluded that the operation of the upgraded Mars antenna at the GDSCC, with its increased potential electromagnetic radiation hazards and interferences, would have no significantly adverse biological, physical, or socioeconomic effects on the environment. Thus, a Finding of No Significant Impact (FONSI) is appropriate in accordance with local, State, Federal, and NASA environmental rules and regulations.

Source record↗
DOE OSTI2025

Temporally-consistent koopman autoencoders for forecasting dynamical systems

Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the dimension reduction capabilities of autoencoders, and the spectral properties of the Koopman operator to learn a reduced-order feature space with simpler, linear dynamics. However, the effectiveness of KAEs is hindered by limited and noisy training datasets, leading to poor generalizability. To address this, we introduce the Temporally-Consistent Koopman Autoencoder (tcKAE), designed to generate accurate long-term predictions even with limited and noisy training data. This is achieved through a consistency regularization term that enforces prediction coherence across different time steps, thus enhancing the robustness and generalizability of tcKAE over existing models. We provide analytical justification for this approach based on Koopman spectral theory and empirically demonstrate tcKAE’s superior performance over state-of-the-art KAE models across a variety of test cases, including simple pendulum oscillations, kinetic plasma, and fluid flow data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1992

Optimizing the G/T ratio of the DSS-13 34-meter beam-waveguide antenna

Calculations using Physical Optics computer software were done to optimize the gain-to-noise-temperature (G/T) ratio of Deep Space Station (DSS)-13, the Deep Space Network's (DSN's) 34-m beam-waveguide antenna, at X-band for operation with the ultra-low-noise amplifier maser system. A better G/T value was obtained by using a 24.2-dB far-field-gain smooth-wall dual-mode horn than by using the standard X-band 22.5-dB-gain corrugated horn.

Esquivel, M. S.↗
NASA NTRS1993

Clementine: An inexpensive mission to the Moon and Geographos

The Clementine Mission, a joint project of the Strategic Defense Initiative Organization (SDIO) and NASA, has been planned primarily to test and demonstrate a suite of lightweight sensors and other lightweight spacecraft components under extended exposure to the space environment. Although the primary objective of the mission is to space-qualify sensors for Department of Defense applications, it was recognized in 1990 that such a mission might also be designed to acquire scientific observations of the Moon and of Apollo asteroid (1620) Geographos. This possibility was explored jointly by SDIO and NASA, including representatives from NASA's Discovery Program Science Working Group, in early 1991. Besides the direct return of scientific information, one of the benefits envisioned from a joint venture was the development of lightweight components for possible future use in NASA's Discovery-class spacecraft. In Jan. 1992, SDIO informed NASA of its intent to fly a 'Deep Space Program Science Experiment,' now popularly called Clementine; NASA then formed an advisory science working group to assist in the early development of the mission. The Clementine spacecraft is being assembled at the Naval Research Laboratory, which is also in charge of the overall mission design and mission operations. Support for mission design is being provided by GSFC and by JPL. NASA's Deep Space Network will be utilized in tracking and communicating with the spacecraft. Following a recommendation of the COMPLEX committee of the Space Science Board, NASA will issue an NRA and appoint a formal science team in early 1993. Clementine is a 3-axis stabilized, 200 kg (dry weight) spacecraft that will be launched on a refurbished Titan-2G. One of the goals has been to build two spacecraft, including the sensors, for $100M. Total time elapsed from the decision to proceed to the launch will be two years.

Shoemaker, Eugene M.↗
NASA NTRS1995

Digital signal processing in the radio science stability analyzer

The Telecommunications Division has built a stability analyzer for testing Deep Space Network installations during flight radio science experiments. The low-frequency part of the analyzer operates by digitizing wave signals with bandwidths between 80 Hz and 45 kHz. Processed outputs include spectra of signal, phase, amplitude, and differential phase; time series of the same quantities; and Allan deviation of phase and differential phase. This article documents the digital signal-processing methods programmed into the analyzer.

Greenhall, C. A.↗
NASA NTRS1995

Automated Consultation for the Diagnosis of Interplanetary Telecommunications

SHARP (Spacecraft Health Automated Reasoning Program) is a knowledge-based system for the diagnosis of problems in NASA's Deep Space Network (DSN) telecommunications system. This system provides the means of communication between a spacecraft and operations personnel at Jet Propulsion Laboratory. SHARP analyzes problems that occur in both the on-board spacecraft telecom subsystem, and the DSN.

SHARP spacecraft health automated reasoning progra↗
NASA NTRS1998

NASA's Deep Space Telecommunications Roadmap

This paper will present this roadmap, describe how it will support an increasing mission set while also providing significantly increased science data return, summarize the current state of key Ka-band and optical communications technologies, and identify critical path items in terms of technology developments, demonstrations, and mission users.

roadmap↗
NASA NTRS2014

Preparing for Crew-Control of Surface Robots from Orbit

Since 2010, the European Space Agency (ESA) and the National Aeronautics and Space Administration (NASA) have been developing robots that can be remotely operated on planetary surfaces by astronauts in orbiting spacecraft. A primary objective of this work has been to test telerobotic technologies that are needed for future deep-space human exploration missions. Specifically, ESA's Multi-Purpose End-To-End Robotic Operations Network (METERON) project and NASA's Human Exploration Telerobotics (HET) project are complementary initiatives that aim to validate communications, operations and robotic systems through a range of ground and flight experiments with humans and robots in the loop. Several experiments have already been successfully completed and others are now in preparation for flight.

telerobotics↗
NASA NTRSDate not supplied

Assumption Generation for the Verification of Learning-Enabled Autonomous Systems

Providing safety guarantees for autonomous systems is difficultas these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard to analyze due to their size (they can have thousands or millions of parameters), lack of formal specifications (DNNs are typically learnt from labeled data, in the absence of any formal or informal requirements), and sensitivity to small changes in the environment. We present an assume-guarantee style compositional approach for the formal verification of system-level safety properties of such autonomous systems. Our insight is that we can analyze the system in the absence of the DNN perception components by automatically synthesizing assumptions on the DNN behaviour that guarantee the satisfaction of the required safety properties. The synthesized assumptions are the weakest in the sense that they characterize the output sequences of all the possible DNNs that, plugged into the autonomous system, guarantee the required safety properties. The assumptions can be leveraged as run-time monitors over a deployed DNN to guarantee the safety of the overall system; they can also be mined to extract local specifications for use during training and testing of DNNs. We illustrate our approach on a case study taken from the autonomous airplanes domain that uses a complex DNN for perception

Autonomous systems↗
DOE OSTI2022

Solving Newton’s equations of motion with large timesteps using recurrent neural networks based operators

Classical molecular dynamics simulations are based on solving Newton’s equations of motion. Using a small timestep, numerical integrators such as Verlet generate trajectories of particles as solutions to Newton’s equations. We introduce operators derived using recurrent neural networks that accurately solve Newton’s equations utilizing sequences of past trajectory data, and produce energy-conserving dynamics of particles using timesteps up to 4000 times larger compared to the Verlet timestep. We demonstrate significant speedup in many example problems including 3D systems of up to 16 particles.

Newton’s equations↗
DOE OSTI2020

Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.

41 EE - Solar Energy Technologies Office (EE-4S)↗
NASA NTRSDate not supplied

Lunar Node 1 and Beyond

Lunar Node 1 (LN-1) is an S-band Navigation beacon for lunar applications that was recently designed and built at MSFC. As part of NASA's Commercial Lunar Payload Services initiative, this beacon will be delivered to the moon's surface on Intuitive Machine's NOVA-C lunar lander in November 2021. During this mission, LN-1’s goal will be to demonstrate navigation technologies that can support local surface and orbital operations around the moon, enabling autonomy which would decrease dependency on heavily utilized Earth based assets like the Deep Space Network. To do this, LN-1’s design leverages Cubesat components as well as the Multi-spacecraft Autonomous Positioning System (MAPS) algorithms, which enable the autonomous spacecraft positioning through communication-integrated navigation measurements. In addition to demonstrating the MAPS payload, the radio will also be used in standard tone-based non-coherent ranging and Doppler tracking to provide an alternate approaches and comparisons for navigation performance. LN-1 will represent a single node in a potential greater MAPS network of assets. While LN-1 awaits launch to demonstrate this initial use of one-way navigation, designs are already under way for proposed subsequent missions like LN-2 to enable expanded capability. The next steps in these missions seek to include a receive capability to allow two-way ranging support with other operational spacecraft in the lunar vicinity, and to provide some component upgrades related to the radio, power, and thermal systems that will improve the longevity of the payload in the harsh lunar environment. The LN-1 design details, status, and potential forward work with mission like LN-2 will be outlined in this presentation.

Evan John Anzalone↗
DOE OSTI2022

Deep Reinforcement Learning based Model-free On-line Dynamic Multi-Microgrid Formation to Enhance Resilience

Multi-microgrid formation (MMGF) is a promising solution for enhancing power system resilience. This paper proposes a new deep reinforcement learning (RL) based model-free on-line dynamic MMGF scheme. Additionally, the dynamic MMGF problem is formulated as a Markov decision process, and a complete deep RL framework is specially designed for the topologytransformable micro-grids. In order to reduce the large action space caused by flexible switch operations, a topology transformation method is proposed and an action-decoupling Q-value is applied. Then, a convolutional neural network (CNN) based multi-buffer double deep Q-network (CM-DDQN) is developed to further improve the learning ability of the original DQN method. The proposed deep RL method provides real-time computing to support the on-line dynamic MMGF scheme, and the scheme handles a long-term resilience enhancement problem using an adaptive on-line MMGF to defend changeable conditions. The effectiveness of the proposed method is validated using a 7-bus system and the IEEE 123-bus system. The results show strong learning ability, timely response for varying system conditions and convincing resilience enhancement.

24 POWER TRANSMISSION AND DISTRIBUTION↗