Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “operator regression”

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 181 records · Page 10

Comparison of Predictive Modeling Methods of Aircraft Landing Speed

Expected increases in air traffic demand have stimulated the development of air traffic control tools intended to assist the air traffic controller in accurately and precisely spacing aircraft landing at congested airports. Such tools will require an accurate landing-speed prediction to increase throughput while decreasing necessary controller interventions for avoiding separation violations. There are many practical challenges to developing an accurate landing-speed model that has acceptable prediction errors. This paper discusses the development of a near-term implementation, using readily available information, to estimate/model final approach speed from the top of the descent phase of flight to the landing runway. As a first approach, all variables found to contribute directly to the landing-speed prediction model are used to build a multi-regression technique of the response surface equation (RSE). Data obtained from operations of a major airlines for a passenger transport aircraft type to the Dallas/Fort Worth International Airport are used to predict the landing speed. The approach was promising because it decreased the standard deviation of the landing-speed error prediction by at least 18% from the standard deviation of the baseline error, depending on the gust condition at the airport. However, when the number of variables is reduced to the most likely obtainable at other major airports, the RSE model shows little improvement over the existing methods. Consequently, a neural network that relies on a nonlinear regression technique is utilized as an alternative modeling approach. For the reduced number of variables cases, the standard deviation of the neural network models errors represent over 5% reduction compared to the RSE model errors, and at least 10% reduction over the baseline predicted landing-speed error standard deviation. Overall, the constructed models predict the landing-speed more accurately and precisely than the current state-of-the-art.

Diallo, Ousmane H.↗

Impacts of climate change on subannual hydropower generation: a multi-model assessment of the United States federal hydropower plant

Abstract Hydropower is a low-carbon emission renewable energy source that provides competitive and flexible electricity generation and is essential to the evolving power grid in the context of decarbonization. Assessing hydropower availability in a changing climate is technically challenging because there is a lack of consensus in the modeling representation of key dynamics across scales and processes. Focusing on 132 US federal hydropower plants, in this study we evaluate the compounded impact of climate and reservoir-hydropower models’ structural uncertainties on monthly hydropower projections. In particular, instead of relying on one single regression-based hydropower model, we introduce another conceptual reservoir operations-hydropower model in the assessment framework. This multi-model assessment approach allows us to partition uncertainties associated with both climate and hydropower models for better clarity. Results suggest that while at least 70% of the uncertainties at the annual scale and 50% at the seasonal scale can be attributed to the choice of climate models, up to 50% of seasonal variability can be attributed to the choice of hydropower models, particularly in regions over the western US where the reservoir storage is substantial. The analysis identifies regions where multi-model assessments are needed and presents a novel approach to partition uncertainties in hydropower projections. Another outcome includes an updated evaluation of Coupled Model Intercomparison Project Phase 5 (CMIP5)-based federal hydropower projection, at the monthly scale and with a larger ensemble, which can provide a baseline for understanding future assessments based on CMIP6 and beyond.

54 ENVIRONMENTAL SCIENCES↗

SU-D-204-03: Comparison of Patient Positioning Methods Through Modeling of Acute Rectal Toxicity in Intensity Modulated Radiation Therapy for Prostate Cancer. Does Quality of Data Matter More Than the Quantity?

Purpose: To determine if differences in patient positioning methods have an impact on the incidence and modeling of grade >=2 acute rectal toxicity in prostate cancer patients who were treated with Intensity Modulated Radiation Therapy (IMRT). Methods: We compared two databases of patients treated with radiation therapy for prostate cancer: a database of 79 patients who were treated with 7 field IMRT and daily image guided positioning based on implanted gold markers (IGRTdb), and a database of 302 patients who were treated with 5 field IMRT and daily positioning using a trans-abdominal ultrasound system (USdb). Complete planning dosimetry was available for IGRTdb patients while limited planning dosimetry, recorded at the time of planning, was available for USdb patients. We fit Lyman-Kutcher-Burman (LKB) model to IGRTdb only, and Univariate Logistic Regression (ULR) NTCP model to both databases. We perform Receiver Operating Characteristics analysis to determine the predictive power of NTCP models. Results: The incidence of grade >= 2 acute rectal toxicity in IGRTdb was 20%, while the incidence in USdb was 54%. Fits of both LKB and ULR models yielded predictive NTCP models for IGRTdb patients with Area Under the Curve (AUC) in the 0.63 – 0.67 range. Extrapolation of the ULR model from IGRTdb to planning dosimetry in USdb predicts that the incidence of acute rectal toxicity in USdb should not exceed 40%. Fits of the ULR model to the USdb do not yield predictive NTCP models and their AUC is consistent with AUC = 0.5. Conclusion: Accuracy of a patient positioning system affects clinically observed toxicity rates and the quality of NTCP models that can be derived from toxicity data. Poor correlation between planned and clinically delivered dosimetry may lead to erroneous or poorly performing NTCP models, even if the number of patients in a database is large.

60 APPLIED LIFE SCIENCES↗

SU-F-R-24: Identifying Prognostic Imaging Biomarkers in Early Stage Lung Cancer Using Radiomics

Purpose: Patients diagnosed with early stage lung cancer have favorable outcomes when treated with surgery or stereotactic radiotherapy. However, a significant proportion (∼20%) of patients will develop metastatic disease and eventually die of the disease. The purpose of this work is to identify quantitative imaging biomarkers from CT for predicting overall survival in early stage lung cancer. Methods: In this institutional review board-approved HIPPA-compliant retrospective study, we retrospectively analyzed the diagnostic CT scans of 110 patients with early stage lung cancer. Data from 70 patients were used for training/discovery purposes, while those of remaining 40 patients were used for independent validation. We extracted 191 radiomic features, including statistical, histogram, morphological, and texture features. Cox proportional hazard regression model, coupled with the least absolute shrinkage and selection operator (LASSO), was used to predict overall survival based on the radiomic features. Results: The optimal prognostic model included three image features from the Law’s feature and wavelet texture. In the discovery cohort, this model achieved a concordance index or CI=0.67, and it separated the low-risk from high-risk groups in predicting overall survival (hazard ratio=2.72, log-rank p=0.007). In the independent validation cohort, this radiomic signature achieved a CI=0.62, and significantly stratified the low-risk and high-risk groups in terms of overall survival (hazard ratio=2.20, log-rank p=0.042). Conclusion: We identified CT imaging characteristics associated with overall survival in early stage lung cancer. If prospectively validated, this could potentially help identify high-risk patients who might benefit from adjuvant systemic therapy.

60 APPLIED LIFE SCIENCES↗

Contribution of Vegetation to the Microbial Composition of Nearby Outdoor Air

Given that epiphytic microbes are often found in large population sizes on plants, we tested the hypothesis that plants are quantitatively important local sources of airborne microorganisms. The abundance of microbial communities, determined by quantifying bacterial 16S RNA genes and the fungal internal transcribed spacer (ITS) region, in air collected directly above vegetation was 2- to 10-fold higher than that in air collected simultaneously in an adjacent nonvegetated area 50 m upwind. Nonmetric multidimensional scaling revealed that the composition of airborne bacteria in upwind air samples grouped separately from that of downwind air samples, while communities on plants and downwind air could not be distinguished. In contrast, fungal taxa in air samples were more similar to each other than to the fungal epiphytes. A source-tracking algorithm revealed that up to 50% of airborne bacteria in downwind air samples were presumably of local plant origin. The difference in the proportional abundances of a given operational taxonomic unit (OTU) between downwind and upwind air when regressed against the proportional representation of this OTU on the plant yielded a positive slope for both bacteria and fungi, indicating that those taxa that were most abundant on plants proportionally contributed more to downwind air. Epiphytic fungi were less of a determinant of the microbiological distinctiveness of downwind air and upwind air than epiphytic bacteria. Emigration of epiphytic bacteria and, to a lesser extent, fungi, from plants can thus influence the microbial composition of nearby air, a finding that has important implications for surrounding ecosystems, including the built environment into which outdoor air can penetrate.

54 ENVIRONMENTAL SCIENCES↗

An Artificial Intelligence-Assisted Method for Dementia Detection Using Images from the Clock Drawing Test

Background: Widespread dementia detection could increase clinical trial candidates and enable appropriate interventions. Since the Clock Drawing Test (CDT) can be potentially used for diagnosing dementia-related disorders, it can be leveraged to develop a computer-aided screening tool. Objective: To evaluate if a machine learning model that uses images from the CDT can predict mild cognitive impairment or dementia. Methods: Images of an analog clock drawn by 3,263 cognitively intact and 160 impaired subjects were collected during in-person dementia evaluations by the Framingham Heart Study. We processed the CDT images, participant’s age, and education level using a deep learning algorithm to predict dementia status. Results: When only the CDT images were used, the deep learning model predicted dementia status with an area under the receiver operating characteristic curve (AUC) of 81.3% ± 4.3%. A composite logistic regression model using age, level of education, and the predictions from the CDT-only model, yielded an average AUC and average F1 score of 91.9% ±1.1% and 94.6% ±0.4%, respectively. Conclusion: Our modeling framework establishes a proof-of-principle that deep learning can be applied on images derived from the CDT to predict dementia status. When fully validated, this approach can offer a cost-effective and easily deployable mechanism for detecting cognitive impairment.

Neurosciences & Neurology↗

Hybrid Model Based Approaches for Systems Health Management and Prognostics

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Hybrid Modeling↗

Systems Health Management and Prognostics Approaches for Electric Aircrafts

As more and more electric vehicles emerge in our daily operation progressively, a very critical challenge lies in the prediction of remaining driving flying time/distance for the flying vehicles. This information is important, particularly in the case of auto vehicles, because such vehicles can become self-aware, autonomously compute its own capabilities, and identify how to best plan and successfully complete vehicular missions safely. In case of electric aircrafts, computing the remaining flying time is also safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. A systematic prediction framework is implemented to identify all possible sources of uncertainty, quantify each of them individually, and mathematically estimate their combined effect on the system-level quantity of interest, in this case, the remaining flying time/distance of the unmanned aircraft. Note - This presentation contains all previously published information.

Systems Health Managent↗

Hybrid Approaches to Systems Health Management and Prognostics

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Systems Health Management↗

Hybrid Model Based Approaches for Systems Health Management and Prognostics

This is a previously approved and published presentation. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Present achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. In principle, data-driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data-driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety-critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Prognostics↗

Health Monitoring and Prognostics for Electric Aircrafts

As more and more electric vehicles emerge in our daily operation progressively, a very critical challenge lies in the prediction of remaining driving flying time/distance for the flying vehicles. This information is important, particularly in the case of auto vehicles, because such vehicles can become self-aware, autonomously compute its own capabilities, and identify how to best plan and successfully complete vehicular missions safely. In case of electric aircrafts, computing the remaining flying time is also safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. A systematic prediction framework is implemented to identify all possible sources of uncertainty, quantify each of them individually, and mathematically estimate their combined effect on the system-level quantity of interest, in this case, the remaining flying time/distance of the unmanned aircraft. Note - This presentation contains all previously approved and published information.

Systems Health Managent↗

Novel method for accurately estimating membrane transport properties and mass transfer coefficients in reverse osmosis

Here, we present a simple and robust method to simultaneously characterize the water and salt permeability (A, B) of reverse osmosis (RO) membranes and mass transfer coefficient (k) in membrane modules. The proposed methodology comprises a set of RO experiments performed at different operating pressures or stages. The measured water and salt fluxes in each stage are simultaneously fitted to the RO transport equations by performing a non-linear regression, using A, B, and k as regression parameters. We first perform a systematic accuracy analysis of the proposed method across the full operational range of RO. The assessment shows that the method accuracy is substantially higher than current methods and increases with number of experimental stages and driving forces. This assessment is used to inform the design of an experimental protocol that minimizes errors in estimated A, B, and k. We then evaluate two commercial RO membranes following the new protocol. For both membranes, A and B parameters decrease by 17% and 15% from the dilute solution to seawater concentrations, whereas the k parameter remains constant. Our study demonstrates that the proposed method, informed by data-driven experimental designs, provides a new approach for accurately characterizing transport phenomenon in membrane processes with feeds of less than 100 g/L total dissolved solids.

36 MATERIALS SCIENCE↗

Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach that enables effective net-load monitoring capabilities at high-frequency with minimal additional equipment and cost. The proposed machine learning based solution provides accurate multiclass state predictions while operating at a faster timescale (able to provide a prediction for each 60- Hz ac cycle used in US power grid) without relying on event-detection techniques. We also introduce an innovative hybrid classification-regression method that allows for the prediction of not only load on/off states but also individual load operating power levels. A test bed with eight residential appliances is used for validating the NILM approach. Results show that the overall method has high accuracy, good scaling and generalization properties.

feature extraction↗

Operational Weight Estimations of Commercial Jet Transport Aircraft

In evaluating current or proposed commercial transport airplanes, there has not been available a ready means to determine weights so as to compare airplanes within this particular class. This paper describes the development of and presents such comparative tools. The major design characteristics of current American jet transport airplanes were collected, and these data were correlated by means of regression analysis to develop weight relationships for these airplanes as functions of their operational requirements. The characteristics for 23 airplanes were assembled and examined in terms of the effects of the number of people carried, the cargo load, and the operating range. These airplane characteristics were correlated for the airplanes as one of three subclasses, namely the small, twin-engine jet transport, the conventional three- and four-engine jets, and the new wide-body jets.

Anderson, Joseph L.↗

Hydroacoustic Evaluation of Juvenile Salmonid Passage and Distribution at Detroit Dam, 2011

Pacific Northwest National Laboratory evaluated juvenile salmonid passage and distribution at Detroit Dam (DET) on the North Santiam River, Oregon for the U.S. Army Corps of Engineers (USACE) to provide data to support decisions on long-term measures to enhance downstream passage at DET and others dams in USACE’s Willamette Valley Project. This study was conducted in response to regulatory requirements necessitated by the listing of Upper Willamette River Spring Chinook salmon (Oncorhynchus tshawytscha) and Upper Willamette River steelhead (O. mykiss) as threatened under the Endangered Species Act. The goal of the study was to provide information of juvenile salmonid passage and distribution at DET from February 2011 through February 2012. The results of the hydroacoustic study provide new and, in some cases, first-ever data on passage estimates, run timing, distributions, and relationships between fish passage and environmental variables at the dam. This information will inform management decisions on the design and development of surface passage and collection devices to help restore Chinook salmon populations in the North Santiam River watershed above DET. During the entire study period, an estimated total of 182,526 smolt-size fish (±4,660 fish, 95% CI) passed through turbine penstock intakes. Run timing peaked in winter and early spring months. Passage rates were highest during late fall, winter and early spring months and low during summer. Horizontal distribution for hours when both turbine units were operated simultaneously indicated Unit 2 passed almost twice as much fish as Unit 1. Diel distribution for smolt-size fish during the study period was fairly uniform, indicating fish were passing the turbines at all times of the day. A total of 5,083 smolt-size fish (± 312 fish, 95% CI) were estimated passed via the spillway when it was open between June 23 and September 27, 2011. Daily passage was low at the spillway during the June-August period, and increased somewhat in September 2011. When the spillway was operated simultaneously with the turbines, spillway efficiency (efficiency is estimated as spillway passage divided by total project passage) was 0.72 and effectiveness (fish:flow ratio—proportion fish passage at a route (e.g., spillway) divided by proportion water through that route out of the total project) was 2.69. That is, when the spillway was open, 72% of the fish passing the dam used the spillway and 28% passed into the turbine penstocks. Diel distribution for smolt-size fish at the spillway shows a distinct peak in passage between mid-morning and mid-afternoon and low passage at night. We estimated that 23,339 smolt-size fish (± 572 fish, 95% CI) passed via the Regulating Outlet (RO) when it was open from October 29 through November 12, 2011, January 2-6, and January 20 through February 3, 2012. During the October–November period, RO passage peaked at 1,086 fish on November 5, with a second peak on November 7 (1,075 fish). When the RO was operated simultaneously with the turbines, RO efficiency was 0.33 and effectiveness was 0.89. In multiple regression analyses, a relatively parsimonious model was selected that predicted the observed fish passage data well. The best model included forebay temperature at depth, forebay elevation, total discharge, hours of daylight, and the operation period. The vertical distribution of fish in the forebay near the face of the dam where the transducers sampled showed fish were generally distributed throughout the water column during all four operational periods. During the refill and full pool periods, vertical distribution was bi-modal with surface-layer and mid-water modes. Patterns for day and night distributions were variable. Fish were distributed above and below the thermocline when it was present (full pool and drawdown periods).

Hydroacoustics↗

Development of a User Interface for a Regression Analysis Software Tool

An easy-to -use user interface was implemented in a highly automated regression analysis tool. The user interface was developed from the start to run on computers that use the Windows, Macintosh, Linux, or UNIX operating system. Many user interface features were specifically designed such that a novice or inexperienced user can apply the regression analysis tool with confidence. Therefore, the user interface s design minimizes interactive input from the user. In addition, reasonable default combinations are assigned to those analysis settings that influence the outcome of the regression analysis. These default combinations will lead to a successful regression analysis result for most experimental data sets. The user interface comes in two versions. The text user interface version is used for the ongoing development of the regression analysis tool. The official release of the regression analysis tool, on the other hand, has a graphical user interface that is more efficient to use. This graphical user interface displays all input file names, output file names, and analysis settings for a specific software application mode on a single screen which makes it easier to generate reliable analysis results and to perform input parameter studies. An object-oriented approach was used for the development of the graphical user interface. This choice keeps future software maintenance costs to a reasonable limit. Examples of both the text user interface and graphical user interface are discussed in order to illustrate the user interface s overall design approach.

Ulbrich, Norbert Manfred↗

Future SDN-HPON Control Plane Architecture and Protocol for On-Demand Terabit End-to-End Extreme-Scale Science Applications

The UC Davis team conducted architecture, algorithm and experimental studies for next generation ultra-high-bandwidth optical networks in support of extreme-scale science applications. In particular, over the course of this 3-year project, the UC Davis team achieved the following main accomplishments: Designed a network architecture for automated multi-domain service provisioning: Designed information exchange schemes between autonomous systems (domains) Designed application programming interfaces to orchestrate resource reservation in data centers, high performance computation facilities, and communication networks belonging to different autonomous systems Experimentally assessed the multi-domain network architecture in a distributed field trial set-up connecting premises in three continents Designed a broker-based orchestrated multi-domain optical networking framework supporting observe-analyze-act cycle based cognitive inter-domain service provisioning: Designed an inter-domain operation mechanism, e.g., topology abstraction, for the broker plane and domain managers to collaboratively accomplish inter-domain service provisioning while respecting the autonomy of each administrative domain Designed an alien wavelength monitoring scheme and an artificial neural network based optical signal-to-noise ratio estimator for quality-of-transmission aware inter-domain service provisioning Developed a deep neural network based multi-domain traffic predictor and a cognitive routing and spectrum assignment algorithm to realize knowledge-based autonomous traffic engineering in multi-domain networks Implemented an optical signal-to-noise ratio estimator and traffic predictor with Google’s Tensor flow and assessed their performance using experimental and synthetic data Demonstrated the benefits of the proposed cognitive schemes with experiments ona two-domain elastic optical network testbed and evaluations on a six-domain simulation framework Built a two-domain software-defined networking control plane testbed using the ONOS platform and demonstrated the workflow of broker and domain manager cooperation, including hierarchical performance monitoring, topology abstraction and cognitive resource allocation. Designed self-learning cognitive service provisioning schemes using advanced machine learning technologies: Designed a self-taught anomaly detection framework for optical networks, including an unsupervised data clustering module for pattern recognition, a supervised data regression and classification module for online anomaly detection, and the system operation principle Experimentally validated the effectiveness of the self-taught anomaly detection framework with various failure/anomaly scenarios. Designed a self-learning autonomic routing, modulation and spectrum assignment (RMSA) provisioning framework for elastic optical networks with deep reinforcement learning. Designed effective modeling and training mechanisms for the self-learning RMSA framework Conducted extensive numerical simulations with various traffic patterns and topologies to verify the advantage of the self-learning RMSA framework.

42 ENGINEERING↗

Non-intrusive nonlinear model reduction via machine learning approximations to low-dimensional operators

Abstract Although projection-based reduced-order models (ROMs) for parameterized nonlinear dynamical systems have demonstrated exciting results across a range of applications, their broad adoption has been limited by their intrusivity: implementing such a reduced-order model typically requires significant modifications to the underlying simulation code. To address this, we propose a method that enables traditionally intrusive reduced-order models to be accurately approximated in a non-intrusive manner. Specifically, the approach approximates the low-dimensional operators associated with projection-based reduced-order models (ROMs) using modern machine-learning regression techniques. The only requirement of the simulation code is the ability to export the velocity given the state and parameters; this functionality is used to train the approximated low-dimensional operators. In addition to enabling nonintrusivity, we demonstrate that the approach also leads to very low computational complexity, achieving up to $$10^3{\times }$$ 10 3 × in run time. We demonstrate the effectiveness of the proposed technique on two types of PDEs. The domain of applications include both parabolic and hyperbolic PDEs, regardless of the dimension of full-order models (FOMs).

42 ENGINEERING↗