Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “federated 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 181 records · Page 10

A Machine Learning Approach to Predict Aircraft Landing Times using Mediated Predictions from Existing Systems

We developed a novel approach for predicting the landing time of airborne flights in real-time operations. The first step predicts a landing time by using mediation rules to select from among physics-based predictions (relying on the expected flight trajectory) already available in real time in the Federal Aviation Administration System Wide Information Management system data feeds. The second step uses a machine learning model built upon the mediated predictions. The model is trained to predict the error in the mediated prediction, using features describing the current state of an airborne flight. These features are calculated in real time from a relatively small number of data elements that are readily available for airborne flights. Initial results based on five months of data at six large airports demonstrate that incorporating a machine learning model on top of the mediated physics-based prediction can lead to substantial additional improvements in prediction quality.

Machine learning↗

Federal Automotive Statistical Tool: FY 2018 Federal Fleet Data Call [Slides]

This presentation provides an overview of collecting federal motor vehicle fleet data at the individual vehicle level for the first time during the fall of 2017, lessons learned related how that data was validated, and changes made during the summer of 2018 based on those lessons in preparation for the now in-progress FY 2018 federal fleet reporting activity. This presentation will be given at the October 2018 FedFleet quarterly meeting (convened on-line on 2018-1024 by GSA's Office of Government-wide Policy). The Federal Automative Statistical Tool (FAST)is a Web-based information system managed by the US Department of Energy, the US General Services Administration, and the Energy Information Administration. FAST is used to collect information about the fleet of motor vehicles used and managed by the Federal government. FAST is developed and maintained by DOE's Idaho National Laboratory (INL).

99 GENERAL AND MISCELLANEOUS↗

Bootstrapping a Sustainable North American PEM Fuel Cell Industry: Could a Federal Acquisition Program Make a Difference?

The North American Proton Exchange Membrane (PEM) fuel cell industry may be at a critical juncture. A large-scale market for automotive fuel cells appears to be several years away and in any case will require a long-term, coordinated commitment by government and industry to insure the co-evolution of hydrogen infrastructure and fuel cell vehicles (Greene et al., 2008). The market for non-automotive PEM fuel cells, on the other hand, may be much closer to commercial viability (Stone, 2006). Cost targets are less demanding and manufacturers appear to be close, perhaps within a factor of two, of meeting them. Hydrogen supply is a significant obstacle to market acceptance but may not be as great a barrier as it is for hydrogen-powered vehicles due to the smaller quantities of hydrogen required. PEM fuel cells appear to be potentially competitive in two markets: (1) Backup power (BuP) supply, and (2) electrically-powered MHE (Mahadevan et al., 2007a, 2007b). There are several Original Equipment Manufacturers (OEMs) of PEM fuel cell systems for these applications but production levels have been quite low (on the order of 100-200 per year) and cumulative production experience is also limited (on the order of 1,000 units to date). As a consequence, costs remain above target levels and PEM fuel cell OEMs are not yet competitive in these markets. If cost targets can be reached and acceptable solutions to hydrogen supply found, a sustainable North American PEM fuel cell industry could be established. If not, the industry and its North American supply chain could disappear within a year or two. The Hydrogen Fuel Cell and Infrastructure Technologies (HFCIT) program of the U.S. Department of Energy (DOE) requested a rapid assessment of the potential for a government acquisition program to bootstrap the market for non-automotive PEM fuel cells by driving down costs via economies of scale and learning-by-doing. The six week study included in-depth interviews of three manufacturers, visits to two production facilities, review of the literature on potential markets in North America and potential federal government procurements, development of a cost model reflecting economies of scale and learning-by-doing, and estimation of the impact of federal PEM fuel cell procurements on fuel cell system costs and the evolution of private market demand. This report presents the findings of that study. Section 2 outlines the status of the industry and describes potential markets based on interviews of manufacturers and the existing literature. Section 3 describes the modeling methodology including key premises and assumptions, and presents estimates of market evolution under four scenarios: (1) Base Case with no federal government procurement program, (2) Scenario 1, an aggressive program beginning with less than 200 units procured in 2008 ramping up to more than 2,000 units in 2012, (3) Scenario 2 which is identical to Scenario 1 except that the private market is assumed to be twice as sensitive to price, and (4) Scenario 3, a delayed, smaller federal procurement program beginning in 2011 increasing to a maximum of just over 1,000 units per year in 2012. The analysis suggests that the aggressive program of Scenario 1 would likely stimulate a sustainable, competitive North American non-automotive PEM fuel cell industry. Given plausible assumptions about learning rates and scale economies, the procurements assumed in Scenario 1 appear to be sufficient to drive down costs to target levels. These findings are conditional on the evolution of acceptable hydrogen supply strategies, which were not explicitly analyzed in this study. Success is less certain under Scenarios 2 and 3, and there appears to be a strong probability that existing OEMs would not survive until 2011. In the Base Case, no program, a viable North American industry does not emerge before 2020.

08 HYDROGEN↗

Microbial inoculants for soil restoration: A Risk-Proportional Stewardship Framework Integrating Strain-Resolved Genomics and Adaptive Governance

Global soil degradation and increasing reliance on chemical inputs threaten agricultural sustainability, driving interest in microbial inoculants as tools for soil restoration. These biological products have the potential to enhance nutrient cycling, improve soil structure, and support plant resilience, but their environmental release raises important safety and stewardship considerations. Here, we propose a risk-proportional framework for the responsible deployment of microbial inoculants grounded in release-based stewardship. The framework integrates genome-resolved strain identification, exclusionary hazard screening, bioassay-based risk triage, ecological testing under realistic conditions, and monitored field deployment. Drawing on evidence from microbial ecology and invasion biology, we highlight how inoculants can alter resident microbial communities, influence ecosystem function, and, in some cases, facilitate gene flow, underscoring the need for risk assessment. We further outline a federated, genome-informed data infrastructure to support traceability, cross-jurisdiction learning, and adaptive management. Together, this approach provides a scalable and scientifically grounded pathway to balance innovation and safety, enabling microbial technologies to contribute to soil restoration and climate-resilient agriculture.

Edlund, Anna [OATH Inc]↗

Microgrid Procurement Checklist Training: Part 1

Learn how to navigate the Microgrid Procurement Checklist, a key resource for federal agencies developing microgrid projects. This first session will provide a step-by-step walkthrough of the checklist, helping participants understand its structure, key tasks, and how to apply it in project planning.

25 ENERGY STORAGE↗

Strategies Which Foster Broad Use and Deployment of Earth and Space Science Informal and Formal Education Resources

Education projects supported by federal agencies and carried out by a wide range of organizations foster learning about Earth and Space systems science in a wide array of venues. Across these agencies a range of strategies are employed to ensure that effective materials are created for these diverse venues. And that these materials are deployed broadly so that a large spectrum of the American Public, both adults and children alike, can learn and become excited by the Earth and space system science. This session will highlight some of those strategies and will cover representative examples to illustrate the effectiveness of the strategies. Invited speakers from selected formal and informal educational efforts will anchor this session. Speakers with representative examples are encouraged to submit abstracts for the session to showcase the strategies which they use.

Meeson, Blanche W.↗

Lessons Learned from the Private Sector

This session is focused on lessons learned from private sector energy projects that could be applied to the federal sector. This presentation tees up the subsequent presentations by outlining the differences between private and federal sectors in objectives, metrics for determining success, funding resources/mechanisms, payback and ROI evaluation, risk tolerance/aversion, new technology adoption perspectives, and contracting mechanisms.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Towards FAIR Workflows for Federated Experimental Sciences

A de-centralized, peer-to-peer AI metadata framework is demonstrated which can enable end-to-end metadata & lineage tracking for distributed Machine Learning pipelines spanning edge, High Performance Computing, and cloud environments. With a specific example of end-to-end microscopy algorithm and datasets, the proposed method shows how to enable reproducibility, audit trail, provenance of metadata artifacts. The emerging needs of automation in experimental sciences, ML-centric workflows, and FAIR metadata management across federated compute environments is addressed.

machine learning↗

A Machine Learning Approach to Improve Air Traffic Management Initiatives

Collaborating closely with commercial air carriers and related organizations, the Federal Aviation Administration(FAA) regulates air traffic and ensures the safety and efficiency of air operations. Air traffic controllers make strategic decisions, such as delaying, rerouting, or canceling flights, partly based on guidance provided by the FAA’s Air TrafficControl System Command Center (ATCSCC). The guidance includes, among other things, control measures known asTraffic Management Initiatives (TMIs) designed to enhance safety and improve operational efficiency. TMIs play a crucial role in managing the demand and capacity within the U.S. National Airspace System (NAS). Two major TMIs that are routinely used (primarily to mitigate the adverse effects of bad weather) are Ground Delay Programs (GDPs) andGround Stops (GSs). In a GDP, flights destined for airports facing thunderstorm activity experience delays at their origin airports. This proactive approach minimizes the risk of routing aircraft through hazardous weather conditions and also replaces (fuel burning) airborne delays with ground delays. In a GS, a temporary restriction is imposed on the departure or arrival of aircraft at a specific airport or within a designated airspace. Although other TMIs (e.g., miles-in-trail) are also implemented as part of (air) traffic flow management in the NAS, the focus of this work is on GDPs and GSs. Since TMIs, by design, lead to flight delays or cancellations, it is crucial to put in place the right set of parameters(e.g., scope and duration of the GDP). For example, when the end time of a GDP extends beyond what is necessary, it imposes unnecessary delays on departing flights. This situation could occur as a result of inaccurate prediction of the(required) duration of the GDP based on the weather forecast. On the other hand, if a GDP ends prematurely before the underlying capacity constraints are resolved at the destination airport, it may result in airborne holding. The delicate balance lies in matching the termination of the GDP precisely with the resolution of capacity constraints, avoiding both the imposition of unnecessary ground delays and the need for airborne holding due to premature program termination.Failing to specify the right parameters for TMIs also leads to flight delays, creating a significant obstacle in managing the increasing traffic volumes causing increased work load for the controllers. To address this issue, we propose the integration of Machine Learning (ML) models in the traffic flow management(TFM) pipeline. In current operations, decisions are made by human experts based on extensive training, historical patterns, available traffic and weather data. Since we have an abundance of data from past events that tell us the likely impact of various TMIs, by ingesting historical data, properly trained ML models can offer valuable insights and aid human decision-making. With the FAA increasingly exploring advanced analytics, ML emerges as a focal point for enhancing TFM within the National Airspace System (NAS). As a first step, this study aims to provide traffic controllers with decision-making support for the issuance and adjustment of TMIs. Data analytics and machine learning have been previously employed to address some of the challenges associated with TMIs. Numerous studies have concentrated on various facets of TMI issuance, exploring factors influencing TMI parameters, including arrival rate, airport capacity, and delay prediction. For example, using weather forecasts, several statistical methods were used to produce probabilistic capacity profiles which in conjunction with deterministic models provided insights into the GDP planning process [1–4]. The downside of using deterministic models is that they rely on fixed inputs and predetermined rules, which lack the ability to account for the inherent uncertainty and variability present in real-world scenarios. In a separate series of studies, researchers aimed to predict the occurrences of GDPs and GSs. The majority of these studies utilized various supervised learning methods, including Decision Trees, Naive Bayes, Support VectorMachines, and Random Forests to analyze the influence of weather conditions and arrival demand on TMI incidents[5–8]. However, these studies primarily focused on predicting the incidence of TMIs without explicitly addressing the scope of TMIs, including their duration and their geographical coverage. Furthermore, the emphasis of these studies was largely on GDPs, given their higher frequency and longer duration when compared to GSs. A limited number of studies focused on predicting the parameters of TMIs, specifically addressing their duration and extent. In one such study focusing on optimizing the TMI parameters at San Francisco International Airport (SFO),the authors utilized a probabilistic forecast of fog [9]. They simulated various capacity scenarios based on the (fog)burn-off forecasts, selecting GDP parameters that minimized airborne and overall ground delays. However, this approach exclusively emphasizes stratus (fog) burn-off as the primary determinant of GDP and GS, neglecting other influential factors like severe weather events, runway closures, lower capacity than traffic demand, and other important variables. Given the complexity of predicting the TMI and determining its scope, we seek a more holistic approach. We aim to consider all significant factors that could impact TMIs and their parameters. What sets this research apart is the fusion of all data sources relevant to the issuance and adjustment of TMIs and it represents the first comprehensive attempt to optimize TMIs in this manner. Since this comprehensive solution involves various aspects, we break down the problem into smaller components and input all parameters into a unified model called the “TMI Adjuster”. Figure 1 shows the overall framework and the list of datasets used in each model. The objective of the TMI Adjuster module is to deliver reliable, consistent and expedited recommendations for the progression, adjustment, and termination of TMIs. The ML solution entails developing a pipeline capable of predicting the necessity of a TMI (e.g., GS or GDP) along with its various parameters. For example, in the case of a GS, this includes the scope of the GS either in terms of distance from the destination airport or based on pre-defined airspace sectors. Here, scope refers to those regions and departing airports that are subject to the GS. In this paper, we concentrate on the issuance of GSs in the three major airports in the New York area — LaGuardia(LGA), John F. Kennedy International (JFK), and Newark Liberty International (EWR). We fuse traffic, weather and other relevant aviation data from years 2017 to 2019 to train and validate the ML models. In particular, we use the following datasets: •Terminal Aerodrome Forecast (TAF): meteorological forecasts specific to each airport, issued four times a day, covering predefined time periods. •TMI data: includes all GSs and GDPs along with their respective parameters. •Aviation System Performance Metrics (ASPM): includes traffic related data such as aircraft delays, arrival, and departure rates. •Notices to Airmen (NOTAMs): utilized to extract runway closure data and manage interdependencies between terminals in close proximity. •Flight cancellation data •Airspace Flow Programs (AFP): includes information on flight airborne holdings caused by TMIs. The data preprocessing entails transforming ASPM, TMI, AFP, NOTAMs, and weather data into an hourly format and consolidating all datasets by merging them based on date and time as the primary key. The TMI Adjuster framework comprises two parallel models: one dedicated to GS and a second model focused on GDP. As previously mentioned, our specific focus is on the GS model as a multi-classification problem. In this framework, each data point of the GS model input summarizes ten hours of data. Specifically, the data loader for the GS model generates the input and output of the model as follows: at a given time step, the input includes the actual traffic, weather, and TMI data from the two-hour window before the time step, alongside the weather forecast and scheduled traffic for the next 8 hours starting from the time step. Based on this information, the output of the GS model for each time interval consists of three dimensions. The first dimension represents a binary decision on whether there should be a GS in place for the next hour or not. The second dimension is related to the scope of the GS in the United States, and the third dimension is related to the scope of the GS in Canada (i.e., to determine if the GS impacts airports in Canada).One of the challenges with TMI modeling is the sparsity of TMI events, particularly regarding its scope. To address this challenge in the scope of the GS model output, we implement grouping. The GS scope for the US region is defined based on a list of centers that should be included when the GS is in place. With 20 centers in the US, we utilized historical data to group them into 4 categories. In particular, we summarized our historical data in a graph format where nodes represent centers, and link weights are defined based on the co-occurrence of centers in the scope parameter ofTMIs. By identified strongly connected components in this graph, we were able to partition the centers into four groups. We consider two model structures for the GS Model. Firstly, a hierarchical classification model [10], where the human decision-making for a GS is of hierarchical nature. The decision-maker first decides whether there is a need fora GS, and if the answer is yes, determines the scope. A hierarchical classification model organizes the problem into a class hierarchy, typically a tree or a Directed Acyclic Graph (DAG) structure, and considers the dependency of the decision in the previous step to the next component [10]. Here, we employ the local classifier per level approach, which involves training one multi-class classifier for each level of the class hierarchy. The second structure is the independent structure. In this setting, as the name suggests, we do not consider the dependency of the decisions in the different dimensions of the output of the model. Instead, for each dimension, we train a multi-class classifier independently. Table 1 summarizes GS model statistics for training, validation and testing. The table documents the effect of limiting data to the time steps when there was actually a TMI in place or when a TMI had just terminated. This resulted in a more balanced distribution of the GS class(GS positive class)versus “No GS”(GS negative class), which might help the training process. While JFK and LGA follow very similar distributions, with 40% and 42% GS positive class respectively, EWR has proportionally fewer GS incidents at 28%. Our subsequent phase involves evaluating the performance of both hierarchical structure and independent structure using different state-of-the-art multi-class classifier models such as Random Forest, Decision Trees, K-nearest Neighbors, and Logistic Regression and forecast the duration and scope of the GSs.

Farzan Masrour Shalmani↗

Equity Considerations in Siting Consolidated Interim Storage Facilities for Commercial Spent Nuclear Fuel

Questions of equity and fairness are often raised by representatives from State, Tribal and local governments and members of the public when resolving conflicts over siting of nuclear facilities. However, the two terms are not synonymous: equity can be quantified while fairness is much more subjective. The Department of Energy's (DOE) December 2021 Request for Information sought input on how to site federal facilities for the temporary, consolidated storage of spent nuclear fuel (SNF) using a consent-based approach. It is anticipated that just such questions about equity and fairness associated with the potential emergence of more than one host site may be raised by the twelve groups of university, nonprofit and private sector partners (Consortia) working to support community engagement, inclusively involve stakeholders, build relationships, and develop innovative forms of mutual learning and public capacity to participate in the consent-based siting process for a federal consolidated interim storage facility during the current Planning & Capacity Building stage of the consent-based siting process. In terms of DOE's Integrated Waste Management System (IWMS), sociopolitical equity concepts are a factor in all aspects of IWMS development and operations and will be particularly applicable should two or more host sites become a possibility, either by the emergence of multiple volunteer hosts or by pursuit as a IWMS program strategy. This paper summarizes recent analyses that explore how four equity metrics - number of states, division of the projected SNF total by the year 2083, current population and land area - might be perceived by host communities, states and regions if two, three or four sites for hosting federal consolidated interim storage facilities were to be contemporaneously realized. Existing institutional arrangements, including Nuclear Regulatory Commission regions, Federal Energy Regulatory Commission regions and Low-Level Radioactive Waste Disposal Compacts, were selected to create hypothetically merged two, three and four-region scenarios to calculate how the four metrics balance out. Projected SNF burden was prioritized with regional contiguity of the consolidated regions a requirement for a functional scenario. The intent was not to promote or suggest any construct as a program objective; the configurations are geopolitical abstractions only to explore potential perceptions of equity. Understanding the possible issues of equity that could arise may benefit program efforts toward achieving a cooperative federalism wherein both the federal and multiple State governments share the goal of manifesting more than one federal consolidated interim storage facility. The main finding is that it is not possible to optimize for all four metrics simultaneously. The analyses demonstrate that trying to create a sense of equity by backfitting a solution to a random population and land distribution will always contain a degree of artificiality.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks

The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings between infinite-dimensional spaces. Traditionally, DeepONets are trained using a centralized strategy that requires transferring the training data to a centralized location. Such a strategy, however, limits our ability to secure data privacy or use high-performance distributed/parallel computing platforms. To alleviate such limitations, in this paper, we study the federated training of DeepONets for the first time. That is, we develop a framework, which we refer to as Fed-DeepONet, that allows multiple clients to train DeepONets collaboratively under the coordination of a centralized server. To achieve Fed-DeepONets, we propose an efficient stochastic gradient-based algorithm that enables the distributed optimization of the DeepONet parameters by averaging first-order estimates of the DeepONet loss gradient. Then, to accelerate the training convergence of Fed-DeepONets, we propose a moment-enhanced (i.e., adaptive) stochastic gradient-based strategy. Finally, we verify the performance of Fed-DeepONet by learning, for different configurations of the number of clients and fractions of available clients, (i) the solution operator of a gravity pendulum and (ii) the dynamic response of a parametric library of pendulums.

Moya, Christian↗

MO-DE-BRA-05: EUTEMPE-RX: Combining E-Learning and Face-To-Face Training to Build Expert Knowledge, Skills and Competences for Medical Physicists in Diagnostic and Interventional Radiology

Purpose: In 2013, the EURATOM authorities of the European Commission decided to support the Horizon2020 project submission ‘EUTEMPE-RX’ that aimed for a new set of course modules to train medical physicists in diagnostic and interventional radiology to expert level with small group deep learning. Each module would consist of 2 phases: an e-learning and a face-to-face phase, each phase requiring typically 40h of participant time. Methods: The European Federation (EFOMP) and 13 European partners, all of them selected for their excellent scientific and/or educational skills, led the 12 course modules. A quality manual ensured the quality of course content and organization. Educational workshops familiarized the teachers with e-learning techniques and methods for assessment. Content was set in accordance with the EC document RP174 that lists learning outcomes in terms of knowledge, skills and competences (KSCs) for different specialties and levels of medical physics. Surveys for stake holder satisfaction were prepared. Results: Today the course modules are being realized. The modules cover most of the KSCs in RP174 document. Teachers have challenged the participants with unique tasks: case studies in medical physics leadership, Monte Carlo simulation of a complete x-ray imaging chain, development of a task specific QA protocol, compilation of optimization plans, simulation tasks with anthropomorphic breast models, etc. Participants undertook practical sessions in modern hospitals and visited a synchrotron facility, a calibration lab, screening organizations, etc. Feedback form quality surveys was very positive and constructive. A sustainability plan has been worked out. Conclusion: The modules have enabled the participants to develop their KSCs and cope with challenges in medical physics. The sustainability plan will be implemented to continue the unique combined e-learning and face to face training at high level training in diagnostic and interventional radiology also beyond Europe. The EUTEMPE-RX project is funded by the Horizon2020 - EURATOM program of the European Commission.

60 APPLIED LIFE SCIENCES↗

E3: Education, Experience, Employment The Economic Ladder to Success

Science, Technology, Engineering, and Math (STEM) literate citizenry is critical for Idaho's economy to effectively compete and grow in today's global marketplace and enhance Idaho workforce capabilities. Idaho's blueprint presents a collaboration design developed by a group of Idaho stakeholders including state level (STEM) educators, state and federal government, other agencies, and industry across the state. The purpose the Idaho Learn and Earn Blueprint Design is to describe a comprehensive plan for improving STEM education in Idaho through a collaborative partnerships and a series of grant supported projects underpinning this strategic design process building pathways to overcome hurdles in today's economy, and moving communities and families up their economic ladder. The Idaho Learn and Earn Blueprint Design focuses on three industry sectors; energy, advanced manufacturing, and health care. All are important in Idaho and have room for job growth potential among both displaced workers and graduates. Representatives from each sector are members of the design team and assist in developing grants and implementing the actions outlined in the design as the program goes forward. Idaho's current programs are generally institution specific. Each of the state's two-year colleges, along with regional groups and employers, are already working towards improving STEM education across the state. A key aspect of this design is to bring these groups together to focus on four unique goals: (1) Providing industry driven curriculum directly tied to skill based career needs; (2) Enhancing collaboration among stakeholders; (3) Providing access to learn and earn programs; and (4) Improving public and student awareness and interest in targeted industry sector career and educational opportunities.

99 GENERAL AND MISCELLANEOUS↗

Helping Businesses and Communities Better Cope with Extreme Weather

The U.S. Department of Energy's Argonne National Laboratory is helping organizations – including AT&T – and communities better prepare for and adapt to the impacts of climate change and extreme weather events. Argonne's cutting-edge climate science and infrastructure analysis/resilience capabilities have helped a range of organizations (companies, federal agencies and cities) make more informed decisions and minimize negative impacts. To learn how your organization might collaborate with Argonne in this space, contact partners@anl.gov.

54 ENVIRONMENTAL SCIENCES↗

Rural Hybrid Generation & Microgrids: National Labs are Here to Help

Hear about the tools and technical assistance National Labs can offer to co-ops and other rural utilities seeking to build or enhance hybrid generation projects combining multiple technologies including wind, solar, battery storage, and others resources. These hybrids can deliver additional value by combining complimentary resources and by increasing reliability and resilience, including as part of a microgrid to serve a local load or community. Experienced cooperative and lab experts will share their perspectives on the opportunities there are to make use of their advanced modeling capabilities and expertise to scope, design, and implement these emerging hybrid solutions. Key takeaways for participants will include better understanding of the resilience benefits distributed hybrid systems provide, awareness of National Laboratory assistance programs and resources, tips for successful federal funding applications for these types of projects, and peer-to-peer learning through shared experiences and discussion.

14 SOLAR ENERGY↗

Toward Solar Photovoltaic Storm Resilience: Learning from Hurricane Loss and Rebuilding Better

This case study report focuses on the rebuild of a 469 kW ground array located at the Almeric L. Christian Federal Building in Christiansted, St. Croix, in the U.S. Virgin Islands. The General Service Administration (GSA) suffered extensive damage to its solar arrays located throughout the Caribbean from Hurricanes Irma and Maria in 2017. While the damage that occurred was unfortunate, there are excellent lessons learned that can be gained and utilized on new systems. The St. Croix site provides a particularly high-value opportunity for lessons learned due to the innovative rebuilding process utilized by GSA managers and the in-depth analysis performed by the project engineers.

14 SOLAR ENERGY↗

Adaptive Stress Testing of Collision Avoidance Systems for Small UASs with Deep Reinforcement Learning

The next-generation Airborne Collision Avoidance System for smaller UASs (ACAS sXu) is currently being developed and tested by the Federal Aviation Administration (FAA) to provide detect-and-avoid capability for small unmanned aircraft operating beyond line-of-sight. Due to the complexity and safety-critical nature of the system, safety validation is important not only for the certification of the final system, but also for informing changes during the iterative development process. In this paper, we analyze a prototype of ACAS sXu in simulated aircraft encounters to discover scenarios of small near mid-air collisions (sNMACs), an important safety event in which two aircraft come closer than 50 feet horizontally and 15 feet vertically. Due to the size and complexity of the system as well as rarity of sNMAC events, traditional methods such as Monte Carlo testing often require informed setup and targeting to elicit failures. However, such a dependence on domain knowledge can be incompatible with the independent verification and validation (IV&V) process, the aim of which is to discover unforeseen issues. To address these challenges, we apply an accelerated validation method called adaptive stress testing (AST) to find the most likely sNMAC scenarios without reliance on system introspection. AST uses reinforcement learning to adapt the search towards the most promising areas of the search space as it progresses. We use a state-of-the-art deep reinforcement learning algorithm, proximate policy optimization, to more efficiently search the large and continuous state space. We find that this approach significantly improves the performance of AST compared to a prior approach based on Monte Carlo tree search. We perform experiments using AST to find sNMAC events under various encounter configurations, varying parameters pertaining to dynamics and coordination. Our experiments show AST to be very effective at finding sNMAC scenarios. We summarize our findings, presenting high-level categories of discovered sNMACs and specific examples of encounters in each category.

aircraft collision avoidance↗

Accelerate Performance (Final Technical Report)

Encouraging commercial building owners to set measurable energy goals before design begins can drive design and contractor teams to develop innovative energy efficiency solutions within conventional building budgets. A federal building owner piloted this technique and created a large-scale zero-energy office building on a budget comparable to local market construction rates. The successes and lessons learned from this performance-based project formed the basis of Accelerate Performance, an expanded program using utilities as the primary outreach channel to replicate the approach. Four utilities partnered with Slipstream, a not-for-profit program implementer, to develop pilot incentive offerings to focus building owners on the whole building rather than on individual building components and systems. The original performance-based procurement process and its successful implementation in a federal building project informed all these efforts. The experiences and lessons learned in different new construction markets led to further process adaptations as well as the development of templates and tools to streamline outreach and technical support efforts. The approach can be adapted to utility new construction programs and is a powerful tool for engaging many building owners early in the project planning process as they make critical energy decisions that impact the performance of the building. The approach has led to real energy savings in building projects by encouraging cost-effective, low-risk, and creative design solutions. The performance-based approach was tested in a variety of applications including different building types and owner types, with many owners adopting performance-based procurement techniques, some with variations, but all maintaining the same core principles. Over the course of the project, nearly 100 building projects were impacted and additional projects will continue to be supported through ongoing program offerings with three leading utilities.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗