Experiences developing large-scale synthetic U.S.-style distribution test systems
Not Available
Palmintier, Bryan (ORCID:0000000214520715)↗
SEARCH · Search NASA
Results for “Learning systems”
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.
Quantum computing based hybrid deep learning for fault diagnosis in electrical power systems
Quantum computing (QC) and deep learning have shown promise of supporting transformative advances and have recently gained popularity in a wide range of areas. Here, this paper proposes a hybrid QC-based deep learning framework for fault diagnosis of electrical power systems that combine the feature extraction capabilities of conditional restricted Boltzmann machine with an efficient classification of deep networks. Computational challenges stemming from the complexities of such deep learning models are overcome by QC-based training methodologies that effectively leverage the complementary strengths of quantum assisted learning and classical training techniques. The proposed hybrid QC-based deep learning framework is tested on a simulated electrical power system with 30 buses and wide variations of substation and transmission line faults, to demonstrate the framework’s applicability, efficiency, and generalization capabilities. High computational efficiency is enjoyed by the proposed hybrid approach in terms of computational effort required and quality of diagnosis performance over classical training methods. In addition, superior and reliable fault diagnosis performance with faster response time is achieved over state-of-the-art pattern recognition methods based on artificial neural networks (ANN) and decision trees (DT).
42 ENGINEERING↗
Cleared for Launch - Lessons Learned from the OSIRIS-REx System Requirements Verification Program
Requirements verification of a large flight system is a challenge. It is especially challenging for engineers taking on their first role in space systems engineering. This paper describes our approach to verification of the Origins, Spectral Interpretation, Resource Identification, Security-Regolith Explorer (OSIRIS-REx) system requirements. It also captures lessons learned along the way from developing systems engineers embroiled in this process. We begin with an overview of the mission and science objectives as well as the project requirements verification program strategy. A description of the requirements flow down is presented including our implementation for managing the thousands of program and element level requirements and associated verification data. We discuss both successes and methods to improve the managing of this data across multiple organizational interfaces. Our approach to verifying system requirements at multiple levels of assembly is presented using examples from our work at instrument, spacecraft, and ground segment levels. We include a discussion of system end-to-end testing limitations and their impacts to the verification program. Finally, we describe lessons learned that are applicable to all emerging space systems engineers using our unique perspectives across multiple organizations of a large NASA program.
Requirements Verification↗
Controlling optical-cavity locking using reinforcement learning
Abstract This study applies an effective methodology based on Reinforcement Learning to a control system. Using the Pound–Drever–Hall locking scheme, we match the wavelength of a controlled laser to the length of a Fabry-Pérot cavity such that the cavity length is an exact integer multiple of the laser wavelength. Typically, long-term drift of the cavity length and laser wavelength exceeds the dynamic range of this control if only the laser’s piezoelectric transducer is actuated, so the same error signal also controls the temperature of the laser crystal. In this work, we instead implement this feedback control grounded on Q-Learning. Our system learns in real-time, eschewing reliance on historical data, and exhibits adaptability to system variations post-training. This adaptive quality ensures continuous updates to the learning agent. This innovative approach maintains lock for eight days on average.
47 OTHER INSTRUMENTATION↗
Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning
The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.
Ruixuan Han↗
Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning
The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.
Ruixuan Han↗
Lessons Learned for Improving Spacecraft Ground Operations
NASA policy requires each Program or Project to develop a plan for how they will address Lessons Learned. Projects have the flexibility to determine how best to promote and implement lessons learned. A large project might budget for a lessons learned position to coordinate elicitation, documentation and archival of the project lessons. The lessons learned process crosses all NASA Centers and includes the contactor community. o The Office of The Chief Engineer at NASA Headquarters in Washington D.C., is the overall process owner, and field locations manage the local implementation. One tool used to transfer knowledge between program and projects is the Lessons Learned Information System (LLIS). Most lessons come from NASA in partnership with support contractors. A search for lessons that might impact a new design is often performed by a contractor team member. Knowledge is not found with only one person, one project team, or one organization. Sometimes, another project team, or person, knows something that can help your project or your task. Knowledge sharing is an everyday activity at the Kennedy Space Center through storytelling, Kennedy Engineering Academy presentations and through searching the Lessons Learned Information system. o Project teams search the lessons repository to ensure the best possible results are delivered. o The ideas from the past are not always directly applicable but usually spark new ideas and innovations. Teams have a great responsibility to collect and disseminate these lessons so that they are shared with future generations of space systems designers. o Leaders should set a goal for themselves to host a set numbers of lesson learned events each year and do more to promote multiple methods of lessons learned activities. o High performing employees are expected to share their lessons, however formal knowledge sharing presentation are not the norm for many employees.
Bell, Michael↗
Artificial Intelligence/Machine Learning Data Management Software System for NSRCs: Phase I Final Technical Report
Explore the source record for details and available documents.
77 NANOSCIENCE AND NANOTECHNOLOGY↗
Online Anomaly Detection Using Machine Learning and HPC for Power System Synchrophasor Measurements
This paper presents an online early anomaly detection framework for phasor measurement units (PMUs) to monitor the power system dynamics and help prevent blackouts using machine learning approaches. Dynamical machine learning solutions including state space model and Kalman filter are conducted in this study to learn the nonlinear and nonstationary PMU measurements and accurately predict system behaviors in real-time. The anomalies can be detected within seconds by comparing the predicted system behaviors with the real system observations. The method proposed in this framework trains PMU data with a given time window (e.g., 5 seconds) using a dynamic nonlinear model, and then predicts system behaviors during the following time window. High prediction accuracy is achieved by applying the dynamic nonlinear model to the real-world PMU measurements – the anomalies detected are successfully validated given the recorded real-world events. High-performance-computing (HPC) techniques are utilized to further reduce computational time to provide real time power system situational awareness.
Ren, Huiying↗
AEOLUS: Advances in Experimental Design, Optimal Control, and Learning for Uncertain Complex Systems
Sustained advances in the mathematics of modeling and simulation have resulted in the capability today for routine simulation of a number of large scale complex DOE-relevant systems. As remarkable as this capability for solving the so-called forward problem is, it is typically only the first step-an inner loop within an outer loop that explores the simulation model's parameter space and decision space to characterize uncertainty in the model's predictions, learn unknown model parameters from data, design the most informative experiments, determine optimal control strategies, and create optimal designs. Broadly, what unifies all of these outer loop problems is that they are, in one form or another, optimization problems over parameter/control/design space that are constrained by complex uncertain models. To fully realize the power of scientific simulation as a basis for scientific discovery, technological innovation, and rational decision-making, it is imperative to move beyond simulation to tackle the outer loop of optimization for learning from data, experimental design, and control with complex uncertain models. When the models under consideration are large-scale and complex, and when the optimization variable and uncertain parameter spaces are high (or infinite) dimensional, this constitutes a grand challenge of the highest order, and is intractable with conventional methods. To overcome these challenges, the AEOLUS Center was established to develop a unified mathematical, computational, and statistical framework for (1) Learning predictive models from complex data via Bayesian inference and optimization, and (2) Optimizing experiments, processes, and designs using the resulting uncertain models. These problems are intractable with conventional methods, for several reasons: (1) The simulation problems that govern the inner loops of the optimization problems are expensive to execute (due to severe nonlinearity, heterogeneity, multiphysics/multiscale coupling); (2) The optimization variable and uncertain parameter spaces are high dimensional, often stemming from discretizations of infinite dimensional fields such as initial conditions, sources, or material properties. We argue that the key to overcoming these challenges is to develop new mathematical, computational, and statistical methods that exploit the structure of the Bayesian inference and optimization problems mediated by their underlying complex uncertain models. This structure includes the regularity, sparsity, geometry, low intrinsic dimensionality, and multifidelity nature of the maps from uncertain parameter/optimization variable spaces to the specific objectives targeted: Bayesian inference, optimal experimental design, and optimal control design. Black box methods developed as generic tools are incapable of exploiting this structure. To be successful, we must create, integrate, and cross-fertilize ideas across multiple areas of applied math--including approximation theory, Bayesian inference, data science, experimental design, information theory, machine learning, model reduction, optimal control theory, parallel algorithms, PDE-constrained optimization, randomized algorithms, stochastic optimization, and uncertainty quantification--all while exploiting the structure of the problems at hand. With this goal in mind, we have marshaled a team of leading authorities in these areas. While the methods we develop will be broadly applicable across a wide spectrum of DOE problems in which experiments inform models and the systems those models describe must be optimized under uncertainty, we have chosen a specific area, advanced manufacturing and materials, to drive our work. AMM is characterized by complex models across multiple scales, and is a rich source of challenging problems in inference, experimental design, and optimal control, requiring multifaceted and integrated advances in applied mathematics. As such, AMM serves as an excellent vehicle to motivate and demonstrate the advances in applied mathematics developed by our center.
97 MATHEMATICS AND COMPUTING↗
Algorithms for Learning Preferences for Sets of Objects
A method is being developed that provides for an artificial-intelligence system to learn a user's preferences for sets of objects and to thereafter automatically select subsets of objects according to those preferences. The method was originally intended to enable automated selection, from among large sets of images acquired by instruments aboard spacecraft, of image subsets considered to be scientifically valuable enough to justify use of limited communication resources for transmission to Earth. The method is also applicable to other sets of objects: examples of sets of objects considered in the development of the method include food menus, radio-station music playlists, and assortments of colored blocks for creating mosaics. The method does not require the user to perform the often-difficult task of quantitatively specifying preferences; instead, the user provides examples of preferred sets of objects. This method goes beyond related prior artificial-intelligence methods for learning which individual items are preferred by the user: this method supports a concept of setbased preferences, which include not only preferences for individual items but also preferences regarding types and degrees of diversity of items in a set. Consideration of diversity in this method involves recognition that members of a set may interact with each other in the sense that when considered together, they may be regarded as being complementary, redundant, or incompatible to various degrees. The effects of such interactions are loosely summarized in the term portfolio effect. The learning method relies on a preference representation language, denoted DD-PREF, to express set-based preferences. In DD-PREF, a preference is represented by a tuple that includes quality (depth) functions to estimate how desired a specific value is, weights for each feature preference, the desired diversity of feature values, and the relative importance of diversity versus depth. The system applies statistical concepts to estimate quantitative measures of the user s preferences from training examples (preferred subsets) specified by the user. Once preferences have been learned, the system uses those preferences to select preferred subsets from new sets. The method was found to be viable when tested in computational experiments on menus, music playlists, and rover images. Contemplated future development efforts include further tests on more diverse sets and development of a sub-method for (a) estimating the parameter that represents the relative importance of diversity versus depth, and (b) incorporating background knowledge about the nature of quality functions, which are special functions that specify depth preferences for features.
Wagstaff, Kiri L.↗
An Advanced Machine Learning and Artificial Intelligence System for Demonstrating Radiation Regulatory Compliance in DOE Accelerator Facilities
In this Phase II proposal, Applied Research LLC (ARLLC), Thomas Jefferson National Accelerator Facility (Jefferson Lab), and Old Dominion University (ODU) propose the combination of domain knowledge (beam characteristics, fixed structural shielding, earthen burden (the soil and foliage added to the dome of the experimental halls as additional shielding), etc.), machine learning (ML) and/or artificial intelligence (AI) to correlate a variety of multi-modal onsite signals and the radiation fields seen in accessible areas of the accelerator site and the site boundary. The ML/AI will consider the complex influence of environmental parameters affecting the radon contribution of the measurements, focusing on actual data obtained from Jefferson Lab. In Phase I, the coded beam and location data were fed into a deep learning model to predict doses at several designated locations in Jefferson Lab’s facility. Moreover, a dense radiation map was generated using only a sparse collection of the samples in a facility. In Phase II, we will develop a software prototype containing a radiation prediction algorithm, dense radiation map algorithms, and background noise prediction algorithms, with actual data used to evaluate the prototype. This work will provide a framework for evaluation of radiation measurement results around the site based on learned responses. In addition, the proposed approach allows more granular mapping of radiation levels. Better understanding and communication of these levels is related to the overall approach in keeping doses to personnel ALARA.
43 PARTICLE ACCELERATORS↗
A learning controller for nonrepetitive robotic operation
A practical learning control system is described which is applicable to complex robotic and telerobotic systems involving multiple feedback sensors and multiple command variables. In the controller, the learning algorithm is used to learn to reproduce the nonlinear relationship between the sensor outputs and the system command variables over particular regions of the system state space, rather than learning the actuator commands required to perform a specific task. The learned information is used to predict the command signals required to produce desired changes in the sensor outputs. The desired sensor output changes may result from automatic trajectory planning or may be derived from interactive input from a human operator. The learning controller requires no a priori knowledge of the relationships between the sensor outputs and the command variables. The algorithm is well suited for real time implementation, requiring only fixed point addition and logical operations. The results of learning experiments using a General Electric P-5 manipulator interfaced to a VAX-11/730 computer are presented. These experiments involved interactive operator control, via joysticks, of the position and orientation of an object in the field of view of a video camera mounted on the end of the robot arm.
Miller, W. T., III↗
A Tale of Two Chambers: Iterative Approaches and Lessons Learned from Life Support Systems Testing in Altitude Chambers
With a brand new fire set ablaze by a serendipitous convergence of events ranging from a science fiction novel and movie ("The Martian"), to ground-breaking recent discoveries of flowing water on its surface, the drive for the journey to Mars seems to be in a higher gear than ever before. We are developing new spacecraft and support systems to take humans to the Red Planet, while scientists on Earth continue using the International Space Station as a laboratory to evaluate the effects of long duration space flight on the human body. Written from the perspective of a facility test director rather than a researcher, and using past and current life support systems tests as examples, this paper seeks to provide an overview on how facility teams approach testing, the kind of information they need to ensure efficient collaborations and successful tests, and how, together with researchers and principal investigators, we can collectively apply what we learn to execute future tests.
Callini, Gianluca↗
Learning Behavior of Distribution System Discrete Control Devices for Cyber-Physical Security
Conventional cyber-security intrusion detection systems monitor network traffic for malicious activity and indications that an adversary has gained access to the system. The approach discussed here expands the idea of a traditional intrusion detection system within electrical power systems, specifically power distribution networks, by monitoring the physical behavior of the grid. This is achieved through the use of high-rate distribution Phasor Measurement Units (PMUs), alongside SCADA packets analysis, for the purpose of monitoring the behavior of discrete control devices. In this work we present a set of algorithms for passively learning the control logic of voltage regulators and switched capacitor banks. Upon detection of an abnormal operation, the operator is alerted and further action can be taken. Finally, the proposed learning algorithms are validated on both simulated data and on measured PMU data from a utility pilot deployment site.
29 ENERGY PLANNING, POLICY, AND ECONOMY↗
Computerized Interactive Harness Engineering
Computerized interactive harness engineering program inexpensive, interactive system for learning and using engineering approach to interconnection systems. Basically data-base system that stores information as files of individual connectors and handles wiring information in circuit groups stored as records.
Billitti, J. W.↗
PCACE-Personal-Computer-Aided Cabling Engineering
PCACE computer program developed to provide inexpensive, interactive system for learning and using engineering approach to interconnection systems. Basically database system that stores information as files of individual connectors and handles wiring information in circuit groups stored as records. Directly emulates typical manual engineering methods of handling data, thus making interface between user and program very natural. Apple version written in P-Code Pascal and IBM PC version of PCACE written in TURBO Pascal 3.0
Billitti, Joseph W.↗
An Efficient Checkpointing System for Large Machine Learning Model Training
As machine learning models increase in size and complexity rapidly, the cost of checkpointing in ML training became a bottleneck in storage and performance (time). For example, the latest GPT-4 model has massive parameters at the scale of 1.76 trillion. It is highly time and storage consuming to frequently writes the model to checkpoints with more than 1 trillion floating point values to storage. This work aims to understand and attempt to mitigate this problem. First, we characterize the checkpointing interface in a collection of representative large machine learning/language models with respect to storage consumption and performance overhead. Second, we propose the two optimizations: i) A periodic cleaning strategy that periodically cleans up outdated checkpoints to reduce the storage burden; ii) A data staging optimization that coordinates checkpoints between local and shared file systems for performance improvement.
machine learning, artificial intelligence↗