Search NASA⌕ Search

SEARCH · Search NASA

Results for “Q learning”

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 91 records · Page 5

Buyers Collusion in Incentivized Forwarding Networks: A Multi-Agent Reinforcement Learning Study

We present the issue of monetarily incentivized forwarding in a multi-hop mesh network architecture from an economic perspective. It is anticipated that credit-incentivized forwarding and relaying will be a simple method of exchanging transmission power and spectrum for connectivity. However, gateways and forwarding nodes, like any other free market, may create an oligopolistic market for the users they serve. In this study, a coalition scheme between buyers aims to address price control by gateways or nodes closer to gateways. In a Stackelberg competition game, buyer agents (users) and sellers (gateways) make decisions using reinforcement learning (RL), with decentralized Deep Q-Networks to buy and sell forwarding resources. We allow communication links between the buyers with a limited messaging space, without defining a collusion mechanism. The idea is to demonstrate that through messaging, and RL tacit collusion can emerge between agents in a decentralized setup. The multi-agent reinforcement learning (MARL) system is presented and analyzed from a machine-learning perspective. Moreover, MARL dynamics are discussed via mean field analysis to better understand divergence causes and make implementation recommendations for such systems. Finally, the simulation results show the results of coordination among the users.

42 ENGINEERING↗

Development of Real-Time Quantitative Safety Evaluation Method for Nuclear Power Plants

Human operators involved with large process control systems such as nuclear power plants (NPPs) perform significant roles in the operation of systems. In this reason, deficiencies in human factors such as poor HSI (Human System Interface) design, procedure, and training, are significant contributing factors to NPPs incidents and accidents. In this regard, many kinds of studies including human reliability analysis (HRA), operation support system, automation, have been conducted in order to reduce human errors. Among these fields of studies, automation has its own specialty since it mainly focuses on eliminating the human error-inducing tasks to reduce human error, while other topics are primarily focusing on reducing human error by aiding human operators during operation. It is commonly believed that replacing human operators to the automated system would guarantee greater efficiency, lower workloads, and fewer human errors. However, these beliefs are not always true in large and complex systems such as NPP, since excessive automation can generate new roles for human operators, change human operators' activities in unexpected ways, and inducing 'out-of-the-loop' (OOTL) problem. Especially, although human error probability drastically increases during abnormal situations in NPP due to overload of information, high workload, and short time available for diagnosis, automation is not actively adopted since conventional machine learning techniques are neither capable nor reliable to handle overwhelmingly complex abnormal situations in NPP. Recently, newly developed 'deep learning' techniques have been actively applied to many fields, and some of these studies proved that the artificial intelligences (AI) based on deep learning techniques show better performance than that of human being. In 2015, deep Q-network (DQN) which is one of the deep learning techniques was developed and applied to train AI that automatically plays various Atari 2800 games, and this AI surpassed the human-level playing in many kind of games. Also in 2016, 'AlphaGo', which was developed by 'Google Deepmind' based on deep learning technique to play the game of Go, was defeated Se-dol Lee who is the World Go champion with score of 4:1. In the point of view that the game of Go is considered as one of the challenging area in machine learning field, it is verified that these new machine learning techniques can perform well, even better than the human being in high-complexity tasks. Previously, most of AI applications in nuclear field were focusing on supporting human operators' tasks such as diagnosis and decision making by rapid classification and prediction, based on fixed training data sets. However, it is expected that AI can be applied to solve more complicated problems (i.e. automation during abnormal states in NPP) by adopting advanced machine learning methodologies. In order to apply the automation system in NPP, firstly it is needed to evaluate the status of the plant quantitatively in real-time, since the information about which state is better (i.e. safe) or worse (i.e. unsafe) is essential for training properly working automation AI. Currently, there are several methodologies for NPP safety evaluation such as probabilistic safety assessment (PSA), safety performance indicator (SPI). However, existing methodologies are not feasible for development of automated system since they are not capable for the cases which are not included in the underlying model, not able to consider delicate changes in the NPP, and hard to evaluate in real-time. Therefore, development of new NPP safety evaluation methodology which can cover previously mentioned requirements is needed to conduct the study on NPP automation further. In this study, the concept of early warning score (EWS) in medical field was adopted to develop the methodology which can evaluate the safety level of the NPP quantitatively and in real-time. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

SU-F-I-12: Region-Specific Dictionary Learning for Low-Dose X-Ray CT Reconstruction

Purpose: Dictionary learning based method has attracted more and more attentions in low-dose CT due to the superior performance on suppressing noise and preserving structural details. Considering the structures and noise vary from region to region in one imaging object, we propose a region-specific dictionary learning method to improve the low-dose CT reconstruction. Methods: A set of normal-dose images was used for dictionary learning. Segmentations were performed on these images, so that the training patch sets corresponding to different regions can be extracted out. After that, region-specific dictionaries were learned from these training sets. For the low-dose CT reconstruction, a conventional reconstruction, such as filtered back-projection (FBP), was performed firstly, and then segmentation was followed to segment the image into different regions. Sparsity constraints of each region based on its dictionary were used as regularization terms. The regularization parameters were selected adaptively according to different regions. A low-dose human thorax dataset was used to evaluate the proposed method. The single dictionary based method was performed for comparison. Results: Since the lung region is very different from the other part of thorax, two dictionaries corresponding to lung region and the rest part of thorax respectively were learned to better express the structural details and avoid artifacts. With only one dictionary some artifact appeared in the body region caused by the spot atoms corresponding to the structures in the lung region. And also some structure in the lung regions cannot be recovered well by only one dictionary. The quantitative indices of the result by the proposed method were also improved a little compared to the single dictionary based method. Conclusion: Region-specific dictionary can make the dictionary more adaptive to different region characteristics, which is much desirable for enhancing the performance of dictionary learning based method.

60 APPLIED LIFE SCIENCES↗

DeepGrid: Robust Deep Reinforcement Learning-based Contingency Management

Increasing uncertainty raised by the integration of renewable energy resources requires an enormous number of simulations to be carried out for the security assessment of the power grid. However, it is challenging to assess the steady-state and dynamic security indices for different system contingency events by doing an exhaustive analysis in real-time due to the computational and communication constraints. One promising solution is using data-driven techniques along with the system models to train an intelligent contingency management framework to better handle the contingencies in real-time. Nevertheless, implementing a data-driven technique to obtain the best remedial actions necessitates to account for the effect of the measurement noise on the performance of the contingency management. To tackle these challenges, we leverage a robust deep reinforcement learning (DRL) algorithm called Double Deep Q-Network (DDQN) to design a recommender system capable of prescribing optimal control actions with the help of the real-time digital simulator (RTDS). The use of RTDS system in combination with the advanced DRL algorithm allows to explore a wide variety of system contingencies in order to derive better remedial actions. The performance of the proposed algorithm is evaluated in IEEE 9-bus system under different loading conditions, and different network configurations in presence of noisy measurements.

Ghasemkhani, Amir↗

Integrated Routing and Traffic Signal Control for CAVs via Reinforcement Learning Approach

Incorporating Connected and Automated Vehicles (CAVs) into urban traffic networks presents opportunities and challenges for traffic management systems. This paper aims to develop an integrated routing and traffic signal control system designed explicitly for CAVs, utilizing a Reinforcement Learning (RL) approach. The objective is to enhance traffic flow and improve overall transportation efficiency in the controlled areas. We propose an innovative framework that employs the Deep Reinforcement Learning (DRL) algorithm, especially the Deep Q-network (DQN), to dynamically adjust the number of vehicles in the routes and the duration of traffic signals. Our simulation results demonstrate that a DQN agent successfully optimizes the number of vehicles in the routes and traffic signal timings of traffic signal controllers, eventually reducing total travel time. The study illustrates the potential usage of RL-based systems in managing routing and traffic signals for CAVs, offering a promising opportunity for future urban traffic management strategies.

Park, Jiho [New York University]↗

Learning and Tuning of Fuzzy Rules

In this chapter, we review some of the current techniques for learning and tuning fuzzy rules. For clarity, we refer to the process of generating rules from data as the learning problem and distinguish it from tuning an already existing set of fuzzy rules. For learning, we touch on unsupervised learning techniques such as fuzzy c-means, fuzzy decision tree systems, fuzzy genetic algorithms, and linear fuzzy rules generation methods. For tuning, we discuss Jang's ANFIS architecture, Berenji-Khedkar's GARIC architecture and its extensions in GARIC-Q. We show that the hybrid techniques capable of learning and tuning fuzzy rules, such as CART-ANFIS, RNN-FLCS, and GARIC-RB, are desirable in development of a number of future intelligent systems.

Berenji, Hamid R.↗

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

59 BASIC BIOLOGICAL SCIENCES↗

Search for heavy scalar resonances decaying to Lorentz-boosted Higgs and Higgs-like bosons in the $\mathrm{b}\overline{\mathrm{b}}4\mathrm{q}$ final state at $\sqrt{s}=13$ TeV

A search is performed for a heavy scalar resonance X decaying to a Higgs boson (H) and a Higgs-like scalar boson (Y) in the two bottom quark (H → $b\bar{b}$) and four quark (Y → VV → 4q) final state, where V denotes a W or Z boson. Masses of the X between 900 and 4000 GeV and the Y between 60 and 2800 GeV are considered. The search is performed in data collected by the CMS experiment at the CERN LHC from proton-proton collisions at 13 TeV center-of-mass energy, with a data set corresponding to a total integrated luminosity of 138 fb −1 . It targets the Lorentz-boosted regime, in which the products of the H → $b\bar{b}$ decay can be reconstructed as a single large-area jet, and those from the Y → VV → 4q decay as either one Y → 4q or two jets V → H → $q\bar{q}$. Jet identification and mass reconstruction exploit machine-learning tools, including a novel attention-based “particle transformer” for Y → 4q identification. No significant excess is observed in the data above the standard model background expectation. Upper limits on the product of production cross section and branching fraction as low as 0.2 fb are derived at 95% confidence level for various mass hypotheses. This is the first search at the LHC for scalar resonances in the all-hadronic H → $b\bar{b}$VV decay channel.

Beyond Standard Model↗

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↗

Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks

Next generation High Performance (HP) tokamaks risk damage from unmitigated disruptions at high current and power. Achieving reliable disruption prediction for a device's HP operation based on its Low Performance (LP) data is a key to its success. In this letter, through explorative data analysis and dedicated numerical experiments on multiple existing tokamaks, we demonstrate how the operational regimes of tokamaks can affect the power of a trained disruption predictor. First, our results suggest data-driven disruption predictors trained on abundant LP discharges work poorly on the HP regime of the same tokamak, which is a consequence of the distinct distributions of the tightly correlated signals related to disruptions in these two regimes. Second, we find that matching operational parameters among tokamaks strongly improves cross-machine accuracy which implies our model learns from the underlying scalings of dimensionless physics parameters like q 95 , β p and confirms the importance of these parameters in disruption physics and cross machine domain matching from the data-driven perspective. Finally, our results show in the absence of HP data from the target devices, the best predictivity of the HP regime for the target machine can be achieved by combining LP data from the target with HP data from other machines. Furthermore, these results provide a possible disruption predictor development strategy for next generation tokamaks, such as ITER and SPARC, and highlight the importance of developing baseline scenario discharges of future tokamaks on existing machines to collect more relevant disruptive data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Constructing a new predictive scaling formula for ITER's divertor heat-load width informed by a simulation-anchored machine learning

Understanding and predicting divertor heat-load width λq is a critically important problem for an easier and more robust operation of ITER with high fusion gain. Previous predictive simulation data for λ q using the extreme-scale edge gyrokinetic code XGC1 [S. Ku et al., Phys. Plasmas 25, 056107 (2018)] in the electrostatic limit under attached divertor plasma conditions in three major US tokamaks [C. S. Chang et al., Nucl. Fusion 57, 116023 (2017)] reproduced the Eich and Goldston attached-divertor formula results [formula #14 in T. Eich et al., Nucl. Fusion 53, 093031 (2013) and R. J. Goldston, Nucl. Fusion 52, 013009 (2012)] and furthermore predicted over six times wider λ q than the maximal Eich and Goldston formula predictions on a full-power (Q = 10) scenario ITER plasma. After adding data from further predictive simulations on a highest current JET and highest-current Alcator C-Mod, a machine learning program is used to identify a new scaling formula for λ q as a simple modification to the Eich formula #14, which reproduces the Eich scaling formula for the present tokamaks and which embraces the wide λ q XGC for the full-current Q = 10 ITER plasma. Additionally, the new formula is then successfully tested on three more ITER plasmas: two corresponding to long burning scenarios with Q = 5 and one at low plasma current to be explored in the initial phases of ITER operation. The new physics that gives rise to the wider λ q XGC is identified to be the weakly collisional, trapped-electron-mode turbulence across the magnetic separatrix, which is known to be an efficient transporter of the electron heat and mass. Electromagnetic turbulence and high-collisionality effects on the new formula are the next study topics for XGC1.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Measuring Q₀ in LCLS-II Cryomodules Using Helium Liquid Level

The nitrogen-doped cavities used in the Linac Coherent Light Source II (LCLS-II) cryomodules have shown an unprecedented high Q₀ in vertical and cryomodule testing compared with cavities prepared with standard methods. While demonstration of high Q₀ in the test stand has been achieved, maintaining that performance in the linac is critical to the success of LCLS-II and future accelerator projects. The LCLS-II cryomodules required a novel method of measuring Q₀, due to hardware incompatibilities with existing procedures. Initially developed at Jefferson Lab during cryomodule acceptance testing before being used in the tunnel at SLAC, we use helium liquid level data to estimate the heat generated by cavities. We first establish the relationship between the rate of helium evaporation from known heat loads using electric heaters, and then use that relationship to determine heat from an RF load. Here we present the full procedure along with the development process, lessons learned, and reproducibility while demonstrating for the first time that world record Q₀ can be maintained within the real accelerator environment.

43 PARTICLE ACCELERATORS↗

On the Utility (or Futility) of Using Stable Water Isotopes to Constrain the Bulk Properties of Tropical Convection

Atmospheric water-vapor isotopes have been proposed as a potentially powerful constraint on convection, which plays a critical role in Earth's present and future climate. It is shown here, however, that the mean tropical profile of HDO in the free troposphere does not usefully constrain the mean convective entrainment rate or precipitation efficiency. This is demonstrated using a single-column analytical model of atmospheric water isotopes. The model has three parameters: the entrainment rate, the precipitation efficiency, and the distance that evaporating condensates fall. At a given relative humidity, the possible range of HDO is small: its range is comparable to both the measurement uncertainty in the mean tropical profile and the structural uncertainty of a single-column model. Therefore, the mean tropical HDO profile is unlikely to add information about convective processes in a bulk-plume framework that cannot already be learned from relative humidity alone.

58 GEOSCIENCES↗

Machine learning BPS spectra and the gap conjecture

We explore statistical properties of Bogomol’nyi-Prasad-Sommerfield q-series for strongly coupled supersymmetric theories that correspond to a particular family of three-manifolds. We discover that gaps between exponents in the -series are statistically more significant at the beginning of the -series compared to gaps that appear in higher powers of. Our observations are obtained by calculating saliencies of -series features used as input data for principal component analysis, which is a standard example of an explainable machine learning technique that allows for a direct calculation and a better analysis of feature saliencies.

97 MATHEMATICS AND COMPUTING↗

Resolving the dynamic correlated disorder in KTa 1- x Nb x O 3

Understanding the complex temporal and spatial correlations of ions in disordered perovskite oxides is critical to rationalize their functional properties. Here, in this study, we provide new insights into the longstanding controversy regarding the off-centering of transition metal ions in the archetypal ferroelectric alloy KTa 1-x Nb x O 3 (KTN). By mapping the full energy (E) and wavevector (Q) dependence of the dynamical structure factor S(Q, E) using neutron scattering, and rationalizing our observations with atomistic simulations leveraging machine learning, we fully resolve the static vs dynamic nature of diffuse scattering sheets, as well as their composition (x) and temperature dependence. Our first-principles simulations, extended with machine-learning molecular dynamics, reproduce both inelastic neutron spectra and diffuse features, and establish how dynamically-correlated transition metal off-centerings couple to phonons, unifying local and collective viewpoints. This study sheds new light into an exemplary ferroelectric systems and shows the importance of mapping the full S(Q, E) to reveal critical spatio-temporal correlations of atomic disorder from which functional properties emerge.

42 ENGINEERING↗

Radiochemistry and the Study of Fission

These are slides from a lecture given at UC Berkeley. Radiochemistry has been used to study fission since its discovery. Radiochemical methods are used to determine cumulative mass yields. These measurements have led to the two-mode fission hypothesis to model the neutron energy dependence of fission product yields. Fission product yields can be used for the nuclear forensics of nuclear explosions. The mass yield curve depends on both the fuel and the neutron spectrum of a device. Recent studies have shown that the nuclear structure of the compound nucleus can affect the mass yield distribution. The following topics are covered: In the beginning: the discovery of fission; forensics using fission products: what can be learned from fission products, definitions of R-values and Q-values, fission bases, K-factors and fission chambers, limitations; the neutron energy dependence of the mass yield distribution (the two mode fission hypothesis); the influence of nuclear structure on the mass yield distribution. In summary: Radiochemistry has been used to study fission since its discovery. Radiochemical measurement of fission product yields have provided the highest precision data for developing fission models and for nuclear forensics. The two-mode fission hypothesis provides a description of the neutron energy dependence of the mass yield curve. However, data is still rather sparse and more work is needed near second and third chance fission. Radiochemical measurements have provided evidence for the importance of nuclear states in the compound nucleus in predicting the mass yield curve in the resonance region.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

Physicochemical signatures of nanoparticle-dependent complement activation

Nanoparticles are potentially powerful therapeutic tools that have the capacity to target drug payloads and imaging agents. However, some nanoparticles can activate complement, a branch of the innate immune system, and cause adverse side-effects. Recently, we developed an in vitro hemolytic assay protocol for measuring the nanoparticle-dependent complement activity of serum samples and applied this protocol to several nanoparticle formulations that differed in size, surface charge, and surface chemistry; quantifying the nanoparticle-dependent complement activity using a metric called Residual Hemolytic Activity (RHA). In the present work, we have used a decision tree learning algorithm to derive the rules for estimating nanoparticle-dependent complement response based on the data generated from the hemolytic assay studies. Our results indicate that physicochemical properties of nanoparticles, namely, size, polydispersity index, zeta potential, and mole percentage of the active surface ligand of a nanoparticle, can serve as good descriptors for prediction of nanoparticle-dependent complement activation in the decision tree modeling framework. The robustness and predictability of the model can be improved by training the model with additional data points that are uniformly distributed in the RHA/physicochemical descriptor space and by incorporating instability effects on nanoparticle physicochemical properties into the model.

informatics↗