Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Decision making”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Status Update on TRAC: A DOE-EM Tool for Tracking Groundwater Cleanup and Progress Toward Site Closure - 20245

The U.S. Department of Energy (DOE) Office of Environmental Management (EM) uses a customized, web-based mapping tool called TRAC (Tracking Restoration and Closure) to communicate information on plume sizes, remedial approaches, regulatory drivers, exit strategies, and long-term stewardship requirements at all sites within the DOE-EM complex. The web-based GIS story maps provide robust geospatial visualization of plumes at DOE sites using an intuitive interface that allows users to explore the plume maps, explanatory text, photographs, and video. This collection of story maps not only communicates information for each individual site, but also summarizes pertinent metrics on cleanup and remaining contaminants across all EM sites. This paper describes a new design within TRAC for communicating metrics on plume status, regulatory cleanup progress, and technology implementation. A principal benefit of TRAC is the ability to view individual pieces of data at a time, permitting targeted questions to be addressed, such as the status of regulatory decisions, site cleanup priorities, and site closure needs for each site within the DOE-EM complex. TRAC manages communication and supports decision-making through knowledge access, data and information transparency and traceability, and inclusive participation. It serves as a common resource that provides consistent information for DOE managers, site personnel, regulators and stakeholders. Because long-term stewardship of legacy waste sites requires ongoing coordination and communication among DOE, regulators, and stakeholders, TRAC can also be used to help transition EM sites to the Office of Legacy Management at site closure. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

Prognostics and Health Management in Nuclear Power Plants: An Updated Method-Centric Review With Special Focus on Data-Driven Methods

In a carbon-constrained world, future uses of nuclear power technologies can contribute to climate change mitigation as the installed electricity generating capacity and range of applications could be much greater and more diverse than with the current plants. To preserve the nuclear industry competitiveness in the global energy market, prognostics and health management (PHM) of plant assets is expected to be important for supporting and sustaining improvements in the economics associated with operating nuclear power plants (NPPs) while maintaining their high availability. Of interest are long-term operation of the legacy fleet to 80 years through subsequent license renewals and economic operation of new builds of either light water reactors or advanced reactor designs. Recent advances in data-driven analysis methods—largely represented by those in artificial intelligence and machine learning—have enhanced applications ranging from robust anomaly detection to automated control and autonomous operation of complex systems. The NPP equipment PHM is one area where the application of these algorithmic advances can significantly improve the ability to perform asset management. This paper provides an updated method-centric review of the full PHM suite in NPPs focusing on data-driven methods and advances since the last major survey article was published in 2015. The main approaches and the state of practice are described, including those for the tasks of data acquisition, condition monitoring, diagnostics, prognostics, and planning and decision-making. Research advances in non-nuclear power applications are also included to assess findings that may be applicable to the nuclear industry, along with the opportunities and challenges when adapting these developments to NPPs. Finally, this paper identifies key research needs in regard to data availability and quality, verification and validation, and uncertainty quantification.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Autonomous alloy composition optimization using molecular dynamics guided by a large language model

Here, we present an autonomous materials discovery framework that couples a large language model (LLM) with molecular dynamics (MD) simulations to optimize Fe–Cr–Mn alloy compositions for tensile strength. Starting from six distinct compositions, the LLM operated as an intelligent agent, iteratively proposing changes based on prior simulation results and constraints. Over 50 iterations per case, the LLM adaptively explored the composition space, identifying high-strength regions, not easily accessible by conventional methods. The highest strength, 18.7 GPa, was achieved with Fe 71 Cr 25 Mn 4 composition, identified from a Fe 75 Cr 20 Mn 5 starting point. The LLM autonomously adjusted its strategy in real time, demonstrating closed-loop decision-making using commodity hardware. This approach showcases the potential of LLMs as scientific co-pilots, capable of accelerating materials discovery and generalizable to other domains like biology and drug design.

Autonomy↗
DOE OSTI2023

Explainable Artificial Intelligence Technology for Predictive Maintenance

The domestic nuclear power plant fleet has relied on labor-intensive and time-consuming preventive maintenance programs, thus driving up operation and maintenance costs to achieve high-capacity factors. Artificial intelligence and machine learning can help simplify complex problems, such as diagnosing equipment degradation, to enable more effective decision-making. Benefits will be felt not only within existing analog and digital instrumentation and control, but also work processes, the integration of people with technology, and most importantly, the business case. Together, these hold promise to make nuclear power more efficient and reduce costs associated with operation and maintenance. While the artificial intelligence and machine learning technologies hold significant promise in the nuclear industry, there are challenges or barriers to their adoption. This report outlines the those different machine learning adoption barriers (categorized as historical, technical, economic, regulatory, and user) that the industry must overcome to realize the full benefits of artificial intelligence and machine learning capabilities for long-term economic sustainability. This report also provides solutions for some of these barriers by focusing on improving the explainability of machine learning to encourage trust from the end-user. Trust and explainability are essential to machine learning adoption. This report focuses on research-developed solutions to some of these barriers while analyzing a non-safety-related system, namely the circulating water system. This system frequently experiences waterbox fouling which our models preemptively diagnoses then explains to the operator how those conclusions were reached. This report presents and discusses the inherent trade-off between machine learning performance (in terms of accuracy) and explainability, where highly accurate machine learning methods (such as deep-learning) are the least explainable, and the most explainable methods (such as decision trees) are the least accurate. In addition, explainability of artificial intelligence techniques in terms of transparency and post-hoc metrics are discussed. This report outlines the importance of data novelty and value of new information in evaluating both the explainability and trustworthiness. Novelty detection helps to establish consistency or inconsistency of the new data with respect to the training data. On the other hand, value of information could be a part of the user-centric visualization recommendation system that request additional information to be collected, thereby strengthening the machine learning outcomes. During this project, a copyrighted user-centric visualization that aligns with a human-in-the-loop approach was developed. The user-centric visualization presents different levels of information and can be tailored as per user credentials to gain user confidence. One of the salient features of the user-centric visualization is it presents machine learning methods with explainability metrics. A simplified version of the user-centric visualization was presented to 32 users with varying levels of machine learning expertise. Feedback was solicited to test the hypothesis that the app contained sufficient explainability and that the users would trust the algorithm. Overall, the app was positively received, and the hypothesis was supported. This report discusses the trust-but-verify framework – a potential approach to build user trust artificial intelligence. The framework discusses trust from the human level to artificial intelligence level. The fundamental premise of the trust but verify framework is derived from an observation of nuclear safety culture (i.e., nuclear power plant personnel do not rely on a singular source of data to make a decision). This also ties back to the user-centric visualization that presents different levels of information to achieve both explainability and trustworthiness of artificial intelligence. Even so, the adoption of artificial intelligence and machine learning in the nuclear industry faces additional barriers, namely regulatory and stakeholder readiness. To overcome these challenges, new solutions must gain regulatory approval and cater to stakeholder needs. The Nuclear Regulatory Committee has a 5-year strategic plan which prepares them for reviewing artificial intelligence technologies in licensee submissions. Early and frequent engagement with the regulator is encouraged. Additionally, artificial intelligence solutions should incorporate human-in-the-loop considerations and offer explainability. Stakeholders must prepare by hiring or training staff to adapt to advancing technology in everyday plant tasks.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Panel Session 80: Interagency Community of Practice in Risk and Performance Assessment

This panel focused on the status of the Inter-agency Performance and Risk Assessment Community of Practice (P and RA COP). Representatives from the P and RA COP and subject matter experts discussed lessons learned and provided feedback on building the P and RA COP to support risk-informed environmental decision making. Panelists with presentations: Understanding Mechanisms to Manage Uncertainty and Risk in Waste Containment Systems (Craig Benson, University of Virginia - CRESP (USA) Scaling for Performance Assessments (Paul Black, Katie Catlett, Doug Anderson, Paul Duffy, Tom Stockton, Sam Van Sickle, John Carson); Interagency Community of Practice in Rick and Performance Assessment (Horst Monken Fernandes); Institutional Controls as a Risk Management Tool (David Esh); Superfund: Explanation of Screening and PRG's for Risk and Dose Assessment (Stuart Walker)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Blending Behavioral Science and Physics-Based Models Inform Equitable Decarbonization Pathways in the US Housing Stock: Preprint

A just energy transition is an imperative of the Biden-Harris Administration, emphasizing the equitable distribution of benefits through energy-efficient and decarbonizing household technologies. Understanding the factors that increase a household's willingness to adopt these technologies helps policymakers implement more targeted and effective approaches. Our research addresses this by blending 550,000 housing stock types and energy simulation data with a nationally representative survey on residential technology adoption and decision-making (n=10,000). We identify energy equity gaps across tenure and income, highlighting disparities in energy burdens and insecurity. Findings show that households with prior modification experience are more willing to renovate, suggesting that small-scale retrofit programs could foster greater willingness. Energy secure but burdened homeowners are least willing to modify, highlighting the need to consider energy bill perceptions in policy design. Nearly half of US households that are energy burdened also face energy insecurity, with a significant gap in assistance for low-income households. We emphasize the need to understand household perceptions to improve policy. This research underscores the importance of understanding household behaviors to improve policy effectiveness, offering actionable insights for policymakers to promote equitable housing upgrades and advance a decarbonized future.

behavioral science↗
DOE OSTI2020

Maximising the investment returns of a grid‐connected battery considering degradation cost

Energy storage systems (ESSs) are being deployed widely due to numerous benefits including operational flexibility, high ramping capability, and decreasing costs. This study investigates the economic benefits provided by battery ESSs when they are deployed for market‐related applications, considering the battery degradation cost. A comprehensive investment planning framework is presented, which estimates the maximum revenue that the ESS can generate over its lifetime and provides the necessary tools to investors for aiding the decision making process regarding an ESS project. The applications chosen for this study are energy arbitrage and frequency regulation. Lithium‐ion batteries are considered due to their wide popularity arising from high efficiency, high energy density, and declining costs. A new degradation cost model based on energy throughput and cycle count is developed for Lithium‐ion batteries participating in electricity markets. The lifetime revenue of ESS is calculated considering battery degradation and a cost–benefit analysis is performed to provide investors with an estimate of the net present value, return on investment and payback period. The effect of considering the degradation cost on the estimated revenue is also studied. The proposed approach is demonstrated on the IEEE Reliability Test System and historical data from PJM Interconnection.

25 ENERGY STORAGE↗
DOE OSTI2023

Scalable Bayesian optimization with randomized prior networks

Several fundamental problems in science and engineering consist of global optimization tasks involving unknown high-dimensional (black-box) functions that map a set of controllable variables to the outcomes of an expensive experiment. Bayesian Optimization (BO) techniques are known to be effective in tackling global optimization problems using a relatively small number objective function evaluations, but their performance suffers when dealing with high-dimensional outputs. To overcome the major challenge of dimensionality, here we propose a deep learning framework for BO and sequential decision making based on bootstrapped ensembles of neural architectures with randomized priors. Using appropriate architecture choices, we show that the proposed framework can approximate functional relationships between design variables and quantities of interest, even in cases where the latter take values in high-dimensional vector spaces or even infinite-dimensional function spaces. In the context of BO, we augmented the proposed probabilistic surrogates with re-parameterized Monte Carlo approximations of multiple-point (parallel) acquisition functions, as well as methodological extensions for accommodating black-box constraints and multi-fidelity information sources. We test the proposed framework against state-of-the-art methods for BO and demonstrate superior performance across several challenging tasks with high-dimensional outputs, including a constrained multi-fidelity optimization task involving shape optimization of rotor blades in turbo-machinery.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Optimal carbon storage reservoir management through deep reinforcement learning

Model-based optimization plays a central role in energy system design and management. The complexity and high-dimensionality of many process-level models, especially those used for geosystem energy exploration and utilization, often lead to formidable computational costs when the dimension of decision space is also large. This work adopts elements of recently advanced deep learning techniques to solve a sequential decision-making problem in applied geosystem management. Specifically, a deep reinforcement learning framework was formed for optimal multiperiod planning, in which a deep Q-learning network (DQN) agent was trained to maximize rewards by learning from high-dimensional inputs and from exploitation of its past experiences. To expedite computation, deep multitask learning was used to approximate high-dimensional, multistate transition functions. Both DQN and deep multitask learning are pattern based. As a demonstration, the framework was applied to optimal carbon sequestration reservoir planning using two different types of management strategies: monitoring only and brine extraction. Both strategies are designed to mitigate potential risks due to pressure buildup. Results show that the DQN agent can identify the optimal policies to maximize the reward for given risk and cost constraints. Finally, experiments also show that knowledge the agent gained from interacting with one environment is largely preserved when deploying the same agent in other similar environments.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Lowering the computational barrier: Partially Bayesian neural networks for transparency in medical imaging AI

Deep Neural Networks (DNNs) can provide clinicians with fast and accurate predictions that are highly valuable for high-stakes medical decision-making, such as in brain tumor segmentation and treatment planning. However, these models largely lack transparency about the uncertainty in their predictions, potentially giving clinicians a false sense of reliability that may lead to grave consequences in patient care. Growing calls for Transparent and Responsible AI have promoted Uncertainty Quantification (UQ) to capture and communicate uncertainty in a systematic and principled manner. However, traditional Bayesian UQ methods remain prohibitively costly for large, million-dimensional tumor segmentation DNNs such as the U-Net. In this work, we discuss a computationally-efficient UQ approach via the partially Bayesian neural networks (pBNN). In pBNN, only a single layer, strategically selected based on gradient-based sensitivity analysis, is targeted for Bayesian inference. We illustrate the effectiveness of pBNN in capturing the full uncertainty for a 7.8-million parameter U-Net. We also demonstrate how practitioners and model developers can use the pBNN's predictions to better understand the model's capabilities and behavior.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Measuring Climate and Water Risk across the Bulk Power System

As climate impacts increase and power systems transition to renewables, planners and operators need insights into climate risks to power generation and infrastructure to ensure reliable decision-making in the short and long-term. We present a standardized, consistent mechanism for utilities and system operators to evaluate the climate- and water-related risks of their current and future grid assets. Using a risk-based approach on the combined outcomes of high-fidelity climate drivers together with water and power system models, we examine the temperature and water availability impacts within the contiguous United States to power system assets at the water basin level in three different time periods and report resulting outcomes on lost capacity across different expansion scenarios and climate models. The results indicate that air temperature has the highest effect on derating. Changes in streamflow do not have a large impact on generation capacity at the national level. Electric sector buildout scenarios each have a unique regional risk profile, depending on the technology mix and total capacity, although risks from high temperatures are significant for both traditional and renewable energy generation. Stakeholders can use this approach to monitor effects of generation capacity losses and potential impacts as climate, generation mix, and infrastructure change.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Seasonal grassland productivity forecast for the U.S. Great Plains using Grass–Cast

Every spring, ranchers in the drought-prone U.S. Great Plains face the same difficult challenge —trying to estimate how much forage will be available for livestock to graze during the upcoming summer grazing season. To reduce this uncertainty in predicting forage availability, we developed an innovative new grassland productivity forecast system, named Grass-Cast, to provide science-informed estimates of growing season above ground net primary production (ANPP). Grass-Cast uses over 30 yr of historical data including weather and the satellite-derived normalized vegetation difference index (NDVI)—combined with ecosystem modeling and seasonal precipitation forecasts—to predict if rangelands in individual counties are likely to produce below-normal, near-normal, or above-normal amounts of grass biomass (lbs/ac). Grass-Cast also provides a view of rangeland productivity in the broader region, to assist in larger scale decision-making—such as where forage resources for grazing might be more plentiful if a rancher’s own region is at risk of drought. Grass-Cast is updated approximately every two weeks from April through July. Each Grass-Cast forecast provides three scenarios of ANPP for the upcoming growing season based on different precipitation outlooks. Near real-time 8-d NDVI can be used to supplement Grass-Cast in predicting cumulative growing season NDVI and ANPP starting in mid-April for the Southern Great Plains and mid-May to early June for the Central and Northern Great Plains. Here, we present the scientific basis and methods for Grass-Cast along with the county-level production forecasts from 2017 and 2018 for ten states in the U.S. Great Plains. The correlation between early growing season forecasts and the end-of growing season ANPP estimate is >50% by late May or early June. In a retrospective evaluation, we compared Grass-Cast end-of-growing season ANPP results to an independent dataset and found that the two agreed 69% of the time over a 20-yr period. Although some predictive tools exist for forecasting upcoming growing season conditions, none predict actual productivity for the entire Great Plains. The Grass-Cast system could be adapted to predict grassland ANPP outside of the Great Plains or to predict perennial biofuel grass production.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A large-scale comparison of Artificial Intelligence and Data Mining (AI&DM) techniques in simulating reservoir releases over the Upper Colorado Region

In recent years, the Artificial Intelligence and Data Mining (AI&DM) models have become popular tools in assisting various aspects of reservoir operation. However, the practical uses are still rarely reported. Comparison experiment of many AI&DM models over a large number of reservoir cases is particularly valuable to help reservoir operators first examine the usefulness and transferability of different AI&DM models, and then identify the most stable and reliable AI&DM model in assist of various decision-making processes. In this study, a total of 12 AI&DM models with different parameterizations and simulation scenarios are comprehensively tested out and compared in simulating the controlled reservoir outflows of 33 reservoir cases over the Upper Colorado Region, United States. Results show that the Random Forecast and the Long-Short-Term-Memory model could consistently derive the best statistical performance than other models under the baseline simulation scenario. The employed AI&DM models could obtain satisfactory statistical interquartile ranges (25–75%) between [0.6–0.9], [0.3–0.8], and [0.2–0.8], for CORR, NSE, and KGE measurements, respectively, and [1.5–6.5], [–15 to 20], and [0.5–8.5] for the normalized RMSE, PBIAS and RSR measurements, respectively. Results also show Multi-Layer Perceptron model and Extreme Gradient Boosting Tree Algorithm produced more stable and superior performance than other models under more complex input scenarios. We also found that the performance of different AI&DM models are closely relevant to the reservoir elevations, sizes, and functionalities. Discussions were made about the sensitivity of AI&DM models’ parameterizations and the key advantages of AI&DM models over the rule-based reservoir models. We further identify that the main advantage of AI&DM models is the flexibility in designing input structures, whereas the rule-based simulation model is rather limited. Future studies were suggested regarding the best way reservoir operators and researchers could use, select, and apply different AI&DM models in simulating reservoir releases under different natural and modeling environments. Finally, this comparison study also serves as a reference and a piece of groundwork for further promoting the practical uses of AI&DM models in assisting reservoir operation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Automated Data Review of Analytical Laboratory Results at Los Alamos National Laboratory - 20299

Newport News Nuclear BWXT-Los Alamos, LLC (N3B) collects samples in support of the U.S. Department of Energy's (DOE) Office of Environmental Management (EM) Los Alamos Legacy Cleanup Contract (LLCC). N3B receives and reviews over 1.6 million sample data points annually in support of various ongoing environmental monitoring and remediation projects of the LLCC. N3B must demonstrate and document that reported external analytical laboratory data produced for the LLCC are of sufficient quality to fulfill their intended purpose and to support defensible decision making as described in EPA QA/G4 Guidance for the Data Quality Objectives Process 1994. In 2018, N3B assumed management of the LLCC along with the Environmental Information Management (EIM) database that contains all historical and current environmental data associated with the LLCC. The entire EIM database is shared between N3B, Triad National Security, LLC (Triad), and New Mexico Environment Department (NMED). These three parties jointly manage the database, its configuration, and changes / updates. All environmental data that are entered into EIM are updated and available, on a daily basis, in the linked public database Intellus New Mexico (Intellus). The quality and defensibility of the environmental data generated from sampling activities is a key component of an effective remediation process. Providing quality data is accomplished through a data assessment process that includes examination, verification, and validation. Examination is the assessment of completeness of the deliverables, identification of any reporting errors, and determining the usability of the data based on the laboratory's evaluation of its data as described in the case narrative received with the data. Verification consists of an evaluation of the Electronic Data Deliverables (EDD) data report to determine the extent to which the external analytical laboratories met method and contract-specific quality control and reporting requirements. Validation consists of determining the data quality and the extent to which the external analytical laboratories accurately and completely reported all sample and quality control results and satisfied all contract requirements. EIM contains an automatic Data Validation Module which performs automated data review (DVM ADR). DVM ADR is a tool to assist in the validation process. When DVM ADR is used in conjunction with manual examination of sample data packages, the combination of the two will meet and exceed the requirements of verification. N3B recognized an opportunity for process improvement, focusing on DVM ADR configuration and enhancements in EIM. Testing EIM's configuration provided proof of the DVM ADR's capabilities and flexibility to accurately perform routine data checks based on analytical methods and regulatory requirements. In addition, the DVM ADR module was improved through enhancements for all analytes, particularly upgrades for radiochemistry data. Extensive testing of the DVM ADR module occurred using EDDs from actual laboratory analyses on the EIM testing site. During this process, N3B manipulated EDD information to verify that the actual outcomes matched the expected outcomes. The results of this testing were shared with the database architects, and configuration improvements were identified to address these results. During this process, N3B identified that the radiochemical DVM ADR capabilities were underutilized, and so enhanced the DVM ADR functionality with respect to radioanalytical assessment. N3B environmental data uploads to Intellus on a daily basis from EIM, once the analytical data undergoes examination and verification. As such, it is important to have a high level of confidence in the quality and defensibility of the data. The process of manual examination, along with the DVM ADR, in conjunction with full validation of a percentage the data specified through the Data Quality Objectives greatly increases efficiency of data review and confidence level of the quality of the data, and gives the project managers, governmental offices, and the public expedited access to high-quality data. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

Here, the rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for system operators. The large-scale integration of distributed energy resources (DERs) and the rapid exchange of measurement data via communication networks present major opportunities for advancing grid operations but also introduce greater uncertainty, higher data dimensionality, more complex network and device models, and challenging control and optimization problems. Deep reinforcement learning (DRL) algorithms are promising in addressing these challenges. However, they have not been effectively adapted for power systems applications, requiring extensive customization for implementation and evaluation. This has resulted in reproducibility challenges and a steep learning curve for researchers new to applying DRL algorithms to the power systems domain. To bridge these gaps, this tutorial aims to serve as a valuable resource for researchers interested in exploring learning-based algorithms to operate active power distribution networks. Specifically, this work presents a generalized process for translating sequential decision-making problems in power distribution systems into Markov decision process (MDP) formulations, illustrated through concrete grid service examples. Additionally, we introduce a simple environment design strategy to develop and evaluate example DRL algorithms for distribution system applications, complete with an included code repository to guide users through environment construction.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Load Shedding for Voltage Regulation With Probabilistic Agent Compliance

With the increased observability and controllability of distribution systems, the share of behind-the-meter systems is trending upwards rapidly. As a consequence, the impact of human behaviors on system performance can no longer be ignored and should be reflected in the energy management system models. In this paper, we discuss the problem of distribution system voltage control by active power curtailment where the agent compliance of the load curtailment signal is probabilistic. We discuss the modeling of the optimal voltage control problem with probabilistic agent compliance as a chance-constrained optimization problem, its tractable safe approximation using convex restriction, and a scenario-based mixed-integer reformulation as well as the associated solution method based on augmented Lagrangian method. The numerical simulation on IEEE test system validates the effectiveness of the proposed approach in obtaining high-quality feasible load curtailment signal with low computational cost, which makes it a viable tool for real time decision making.

augmented Lagrangian method↗
DOE OSTI2023

Using Eye-Tracking to Quantify Reverse Engineering Expertise

Software reverse engineering (RE) requires analysts to closely read and make decisions about code. Little is known about what makes an analyst successful, making it difficult to train new analysts or design tools to augment existing ones. The goal of this project was to quantify the eye movement behaviors supporting RE and code comprehension more generally. We applied eye-tracking methods from the language comprehension literature to understand where analysts direct their attention over time when completing tasks (e.g., function identification, bug detection). Across three studies, we manipulated aspects of code hypothesized to impact comprehension (e.g., variable name meaningfulness, code complexity) and presentation methods (e.g., line-by-line, free viewing, gaze-contingent moving window) to understand effects on accuracy and gaze patterns. Results showed clear benefits of meaningful variable names, and effects of expertise on global and line-specific viewing patterns. Findings could inspire empirically-supported tool or analytic adaptations that help to reduce analyst workload.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

PV Generation and Load Forecasting for Adjuntas PR Community Microgrids

Existing frameworks to forecast time-series photovoltaic (PV) output power and consumer load for microgrid operations and controls assume a near-continuous availability of real-time input features from the field assets such as PV inverters, energy meters, and weather station. These incoming data points are used to periodically retrain models and update forecast snapshots over a moving horizon window, be it one hour-ahead, one-day ahead, or one-week ahead. However, such frameworks are not resilient to disruptions in data availability caused by losses in communications between the field sensors and data loggers. Hence, there is a need for programs that assume no availability of real-time microgrid asset data and still make reliable forecasts that can be used for decision-making. Such programs would be apt to function in extreme weather events such as hurricanes and would use lightweight recursive time-series models to independently forecast solar irradiance and ambient temperature, then compute PV power from those forecasts, as well as independently forecast consumer load. The codebase performs forecasting for the scenario of when the microgrid does not have a reliable access to forecasts or real-time observations of solar irradiance (I) and ambient temperature (AT) and load (Load) to be able to adequately forecast, in real-time, the PV power production or a business' load. In this case, using historical values of PV power and load, a univariate forecasting of generation and consumption are respectively made. The use-case in particular has two sub-scenarios: one, a normal 7-day ahead forecast where the unavailability of real-time data is assumed due to infrastructure issues such as loss of communication or sensor maintenance or service downtimes. Whereas a hurricane-caused unavailability of real-time data requires a second model trained specifically on historical hurricane days to be able to capture the extreme day behavior of generation in particular, and load if applicable. A gradient boosted regression tree comprises an ensemble of additive models that map between the input of historical values (be it irradiance, temperature, or load) and their corresponding output forecasts of a given horizon such that the individual learner predictions are summed up over the total number of such learners in the ensemble to produce an aggregate forecast. A weighting mechanism is applied to the training data in each iteration, where actual and forecast values are compared to penalize incorrect forecasts by increasing the weight and reducing it to reward correct forecasts. The code's benefits are that it: (a) accounts for a contingency where communication loss renders newly measured real-time data unavailable for model tuning and snapshot updates; (b) presents blind forecasting that recursively determines the next time-step value in a horizon using the forecast of the same attribute from a prior step; and (c) employs lightweight models that, once trained, can reliably generalize for different horizons, which make them suitable for enhancing the resilience of field microgrids prone to extreme events that encounter disruptions to data availability.

Sundararajan, Aditya [Oak Ridge National Laborator↗