Search NASA⌕ Search

SEARCH · Search NASA

Results for “Risk algorithm”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Tactical Analysis for Calculating Contextual Risk at Boundaries: Summary of Laboratory Directed Research & Development Effort

The Tactical Analysis for Calculating Contextual Risk at Boundaries (TACCRAB) tool is an innovative digital twin (DT) platform and automated risk algorithm designed to transform operational decision-making in structured screening environments, with an initial focus on Southern Border Land Ports of Entry (POEs). The invention provides integration points for advanced artificial intelligence, predictive modeling, and real-time data analysis to produce a comprehensive risk management tool that enables proactive, data-informed security strategies. The core inventive features of TACCRAB center on its unique risk algorithm, which dynamically calculates contextual risk by synthesizing historical data, near real-time streaming data from the checkpoints themselves, and AI-generated predictions. Unlike traditional risk assessment methods, TACCRAB utilizes a DT to provide comprehensive operational insights, allowing stakeholders to visualize, simulate, and optimize checkpoint configurations with unprecedented speed and contextual awareness. TACCRAB's key innovation lies in its ability to combine multiple complex inputs - including technology detection probabilities, resource availability, screening pathway characteristics, and threat actor behavioral patterns - into a unified risk calculation and update these inputs based on changing operational and environmental conditions. By leveraging a DT that continuously updates and learns from linked data, TACCRAB can suggest adaptive mitigation strategies that minimize risk while maintaining operational efficiency. Particularly novel is the platform's approach to decision support, which goes beyond static risk assessment. The DT provides dynamic metrics such as wait times, resource allocation effectiveness, and potential emerging threat scenarios, enabling users to view sophisticated, relevant what-if simulations and optimize checkpoint operations in near real-time. The system's architecture allows for generalized application across different screening environments, such as secure facilities, ports of entry, and soft targets, making it a versatile tool for security and operational management. The invention distinguishes itself through its comprehensive integration of predictive modeling, AI-driven pattern discovery, and user-friendly interface design. By combining these elements, TACCRAB transforms complex risk data into actionable insights, supporting decision-makers at various organizational levels - from booth agents making split-second screening decisions to checkpoint managers optimizing the day's resource allocation to strategic planners managing long-term investments.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2024

Aviation security screening optimizer for risk and throughput (ASSORT)

The increasing number of air travelers each year presents a challenge as many airports are near their capacity in terms of resources and space for passenger screening. Fortunately, advancements in technologies like next-generation millimeter wave scanning offer solutions to ease this strain. The focus remains on managing risk while enhancing the passenger experience for the traveling public. The risk model presented in this paper known as the Aviation Security Screening Optimizer for Risk and Throughput (ASSORT) is designed to assess risk-based approaches for passenger screening and checkpoint operations. Additionally, ASSORT is exploring various traveler categories — general, trusted, and trusted-plus — along with different checkpoint screening Concept of Operations tailored to each traveler type. For instance, travelers with a higher trust level may experience fewer screening technologies, resulting in quicker processing times at the checkpoint. The output of ASSORT provides a risk score for predefined threat scenarios, as well as the overall risk to the checkpoint, aircraft, and airport by traveler type. In conclusion, benefits of using this tool include assessing the trade-offs between the overall risk associated with checkpoints and the throughput rate of passengers screened. We show for example the impact that different passenger volumes at the checkpoint can have on risk.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

Peer-to-peer communication control for resilient operations of networked cyberphysical systems

This report includes two main accomplishments of the peer-to-peer communication control for resilient operation of networked microgrids project in FY24, which include a scheme for cyberattack-aware coordination of networked microgrids for supporting voltages of bulk power systems and a scheme for price signal-based operations of EV-rich networked microgrids with mixed ownership. First, the cyberattack-aware scheme enables networked microgrids to distributedly determine the amount of reactive power injection to support the voltage of bulk power system (BPS) in a fair manner. In this scheme, a risk-informed algorithm is presented to generate the peer-to- peer (P2P) communication graph with minimal risk of attack on communication links. To deal with cyberattacks on MG controllers, the resilient consensus algorithm (CA) is utilized for MG controllers to robustly estimate the total reactive power headroom, from which the MGs can accurately provide the needed amount of reactive power injection for supporting the voltage of BPS. The CA implementation and performance within the P2P communication framework are demonstrated on the IEEE 39-bus system with 6 microgrids contained in the distribution feeder under different cyberattack scenarios. Second, the price-based scheme enables the usage of the real-time price signal for the operations of electric vehicle (EV)-rich networked-microgrids with mixed ownership, in which not all the microgrids can communicate with the distribution system operator (DSO). In this scheme, a max consensus is introduced to enable the real-time price signal to be propagated from the DSO to all the microgrids, from which each microgrid controller will manage the DERs to balance the load demand and the power injection from the EV charging stations within its microgrid. Numerical results over one day with 288 slots of 5-minute intervals on the modified 123-node test feeder including 3 microgrids with high penetration of EV are presented to evaluate how the price signal affects the operations of networked microgrids under different charging strategies of the EV charging stations. The result indicates that our proposed EVCS (dis)charging strategy, which leverages the flexibility of EVs to support the grid through discharging during peak demand, proves to be a cost-effective solution that reduces operational costs while improving the social welfare of EV charging.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers

Here, we propose a containment query that is robust to the watertightness of regions bound by trimmed NURBS surfaces, as this property is difficult to guarantee for in-the-wild CAD models. Containment is determined through the generalized winding number (GWN), a mathematical construction that is indifferent to the arrangement of surfaces in the shape. Applying contemporary techniques for the 3D GWN to trimmed NURBS surfaces requires some form of geometric discretization, introducing computational inefficiency to the algorithm and even risking containment misclassifications near the surface. In contrast, our proposed method leverages properties of the 3D solid angle to solve the relevant surface integral using a boundary formulation with rapidly converging adaptive quadrature. Batches of queries are further accelerated by memoizing (i.e., caching and reusing) quadrature node positions and tangents as they are evaluated. We demonstrate that our GWN method is robust to complex trimming geometry in a CAD model, and is accurate up to arbitrary precision at arbitrary distances from the surface. The derived containment query is therefore robust to model non-watertightness while respecting all curved features of the input shape.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

COMPASS-FME Terrestrial Ecosystem Manipulation to Probe the Effects of Storm Treatments (TEMPEST) Experiment Level 2 Sensor Data v2-1

This is the version v2-1 Level 2 (L2) data release for COMPASS-FME environmental sensors located at our Terrestrial Ecosystem Manipulation to Probe the Effects of Storm Treatments (TEMPEST) experimental site. This manipulative, ecosystem-scale TEMPEST experiment addresses the potential for freshwater and estuarine-water disturbance events to alter tree function, species composition, and ecosystem processes in a deciduous coastal forest in MD, USA. The experiment uses a large-unit (2000 m2), un-replicated experimental design, with three 50 m × 40 m plots serving as control, freshwater, and estuarine-water treatments. Level 2 (L2) data consist of sensor observations from the COMPASS-FME synoptic sites, TEMPEST, and DELUGE. Compared to the L1 data, these are more consistent (always 15-minute timestamps for the entire year); better QA/QC’d (out of bounds, out of service, and extreme outlier values are removed); and more complete, with a gap-filled time series available alongside the main observations, and additional derived (calculated) variables. L2 data are intended to be rapidly and easily usable in analyses and simulations. However, algorithmic outlier identification always carries the risk of removing valid data, and Level 1 data may be more suitable for analyses that focus on variability or extreme events. This dataset includes: - An overall dataset README file that describes the current version, gives citation and contact information, etc. - Site- and year-specific folders, each holding variable-specific Parquet (a high performance, space efficient format; see https://parquet.apache.org) data files for each site and plot in that year. - Metadata files within each site-year folder provide full information on data units, expected ranges, contact information, detailed flood times, as well as a general description of the site. - Environmental sensor types that appear in the data files include weather (ClimaVUE50, CS, RM Young, and LI instruments in the graphs below); soil conditions (TEROS12); soil redox state (Redox); groundwater variables (AquaTROLL200 and AquaTROLL600); open water sondes (Exo); tree sap velocity (Sapflow); and system voltage and state (Datalogger). Data are reported every 15 minutes. Please see v2-1 TEMPEST L2 Sensor Package Quick Start.pdf for detailed information on data package structure, temporal coverage, and versioning. Data files are in Apache Parquet, a high performance, space efficient format for tabular data. These files can be read using R's `arrow` package (https://arrow.apache.org/docs/r/), with similar tools available in other languages. The TEMPEST flood events occurred on the following dates. They lasted for ~10 hours each day and delivered ~80,000 gallons to each plot; many data streams are available at 1 or 5 minute frequency during these periods. * Tests: Aug 25 (fresh plot) and Sep 9 (salt plot), 2021 * TEMPEST 1: June 22, 2022 * TEMPEST 2: June 6-7, 2023 * TEMPEST 3: June 11-13, 2024

EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC TEMPERATU↗
DOE OSTI2026

COMPASS-FME Synoptic Sites Level 2 Sensor Data v2-1

This is the version 2-1 Level 2 (L2) data release for COMPASS-FME environmental sensors located at our synoptic field sites. COMPASS-FME is studying sites in two distinct regions, the Chesapeake Bay and the Western Lake Erie Basin. We established the network at seven "synoptic" (observational) sites along the Chesapeake Bay and Lake Erie coastlines, collectively generating over three million observations per month, to track and comprehend environmental changes where land and water intersect. Additionally, the two regions provide an interesting contrast of saltwater and freshwater coasts that allow us to differentiate the impacts of inundation and coastal water chemistries in two nationally important coastal systems. Level 2 (L2) data consist of sensor observations from the COMPASS-FME synoptic sites, TEMPEST, and DELUGE. Compared to the L1 data, these are more consistent (always 15-minute timestamps for the entire year); better QA/QC’d (out of bounds, out of service, and extreme outlier values are removed); and more complete, with a gap-filled time series available alongside the main observations, and additional derived (calculated) variables. L2 data are intended to be rapidly and easily usable in analyses and simulations. However, algorithmic outlier identification always carries the risk of removing valid data, and Level 1 data may be more suitable for analyses that focus on variability or extreme events. This dataset includes: - An overall dataset README file that describes the current version, gives citation and contact information, etc. - Site- and year-specific folders, each holding variable-specific Parquet (a high performance, space efficient format; see https://parquet.apache.org) data files for each site and plot in that year. - Metadata files within each site-year folder provide full information on data units, expected ranges, contact information, detailed flood times, as well as a general description of the site. - Environmental sensor types that appear in the data files include weather (ClimaVUE50, CS, RM Young, and LI instruments in the graphs below); soil conditions (TEROS12); soil redox state (Redox); groundwater variables (AquaTROLL200 and AquaTROLL600); open water sondes (Exo); tree sap velocity (Sapflow); and system voltage and state (Datalogger). Data are reported every 15 minutes. Data files are in Apache Parquet, a high performance, space efficient format for tabular data. These files can be read using R's `arrow` package (https://arrow.apache.org/docs/r/), with similar tools available in other languages. Please see v2-1 L2 Sensor Package QStart.pdf for detailed information on data package structure, temporal coverage, and versioning.

EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC TEMPERATU↗
DOE OSTI2025

Considerations for a Medium-Voltage DC Electrolysis Testbed

Here we present the results of a study focused on the feasibility of using Medium Voltage DC (MVDC) power distribution from wind power generation to electrolyzers for hydrogen production. This approach, using hybrid energy generation in a MVDC microgrid, offers many advantages. These include possible improvements in efficiency, reliability and installation cost compared to a more typical state-of-the-art AC distribution configuration. It also eliminates the need for transformers, which have recently been subject to price volatility and availability concerns. This study highlights the practical feasibility of MVDC distribution networks for integrating various energy sources, offering improved efficiency and reduced system complexity compared to conventional AC-based solutions. Future work will focus on enhancing fault protection strategies, scaling the system to larger renewable installations, and conducting hardware implementation at the National Renewable Energy Laboratory's (NREL) Flatirons Campus (FC). In the sections that follow we show that a DC Collection and Distribution System (DC CDS) reduces the losses associated with the electrical conversion / distribution process relative to a state-of-the-art AC approach, improving overall efficiency by 5%. On the qualitative side, reducing the number of conversion stages is likely to improve reliability, reduce capital investment cost, and enable simpler control algorithms to be used, and reduced risk of instabilities and malfunctions.

08 HYDROGEN↗
DOE OSTI2025

DONKEY: A Flexible and Accurate Algorithm for Clustering

We propose an accurate clustering algorithm suitable for the varied and multidimensional data sets that correspond to temporal snapshots from on-the-fly nonadiabatic trajectory-based simulations of photoexcited dynamics. The algorithm approximates the underlying probability density function using variable kernel density estimation, with local maxima corresponding to cluster centers. Each data point is then assigned to one of the maxima by employing a maximization procedure. Finally, clusters artificially separated by minor fluctuations in the probability density are merged. The algorithm does not require parameter tuning, which ensures flexibility and reduces the risk of bias. It is tested on several synthetic data sets, where it consistently outperforms conventional clustering algorithms. As a final example, the algorithm is applied to the excited dynamics of the norbornadiene ⇌ quadricyclane (C 7 H 8 ) molecular photoswitch, demonstrating how distinct reaction pathways can be identified.

algorithms↗
DOE OSTI2024

Binary Quantum Control Optimization with Uncertain Hamiltonians

Optimizing the controls of quantum systems plays a crucial role in advancing quantum technologies. The time-varying noises in quantum systems and the widespread use of inhomogeneous quantum ensembles raise the need for high-quality quantum controls under uncertainties. In this paper, we consider a stochastic discrete optimization formulation of a discretized binary optimal quantum control problem involving Hamiltonians with predictable uncertainties. We propose a sample-based reformulation that optimizes both risk-neutral and risk-averse measurements of control policies, and solve these with two gradient-based algorithms using sum-up-rounding approaches. Furthermore, we discuss the differentiability of the objective function and prove upper bounds of the gaps between the optimal solutions to binary control problems and their continuous relaxations. We conduct numerical simulations on various sized problem instances based on two applications of quantum pulse optimization; we evaluate different strategies to mitigate the impact of uncertainties in quantum systems. In conclusion, we demonstrate that the controls of our stochastic optimization model achieve significantly higher quality and robustness compared with the controls of a deterministic model.

conditional value-at-risk (CVaR)↗
DOE OSTI2025

Performance Evaluation of Intelligent Solar Control Software Through Hardware-in-the-Loop (CRADA Final Report)

Recent research has highlighted the potential for solar to act as a zero-marginal-cost and zero-emission flexibility resource on the bulk power system when operated with advanced control systems. To increase the performance of these systems, leading technologies, including machine learning (ML) and hierarchical inverter set point allocation, have been developed by Latimer Controls, Inc. to estimate the headroom of large PV plants for grid operation and control; however, these technologies lack comprehensive validation under real-world application scenarios. Latimer Controls, Inc. received two voucher awards for research at a national laboratory from the Department of Energy American Made Solar Prize Round 6. The National Renewable Energy Laboratory (NREL) was selected to collaborate with Latimer staff to conduct a performance evaluation of Latimer PV control software. The NREL team will develop a hardware-in-the-loop (HIL) testbed to perform testing and validation of the Latimer PV control technology in a de-risked yet realistic testbed environment. Latimer and NREL worked together to analyze the test data, draw conclusions from the results, and disseminate the resulting scientific findings. In this CRADA work, we propose to test and validate the real-world application of the Latimer Control solution in an HIL environment. We evaluate the performance of different flexible solar technologies in responding to automatic generation control signals in a closed-loop fashion. In particular, a data-driven potential high limit (PHL) estimation is developed for large solar plants to accurately estimate their headroom so that they have fast and short-time regulation and control capability to participate in grid services and respond to grid signals in real time (e.g., AGC). This PHL estimation algorithm is embedded in a hardware power plant controller (PPC) and tested with an IEEE-39 bus system model developed in RTDS. To account for the varying cloud conditions and diverse inverter dispatches, we developed a 135-MW PV plant with detailed modeling of 27 individual PV modules and inverters using RTDS. The real-world communications used in such big plants, such as ModBus TCP/IP for inverter level and DNP3 for plant level, were developed to emulate the real-world applications in big PV plants. The ML-based PHL estimation method is tested under nine separate weather scenarios against the ‘reference-control’ solution, hereafter referred to as the baseline solution. The baseline method reserves a subset of inverters (reference group) to operate at their PHL at all times and dispatches only the remaining inverters (control group) at curtailed levels to fulfill the flexibility need. Despite being successfully piloted by NREL in California in 2017 and Chile in 2020, there exist two gaps in the state of the art to fully unlock the flexibility of PV plants: a. There is a trade-off between the PHL estimation accuracy and the flexibility range. b. There lacks granularity in the PHL estimation to capture the variation across inverters. The Latimer solution seeks to address these gaps by applying machine learning methods to improve PHL estimation accuracy while accounting for variability at every inverter. Performance metrics were taken from the 2023 Georgia Power CARES utility-scale RFP. The results demonstrate that the ML-based approach outperforms the traditional baseline method in PHL estimation accuracy for 7 of 9 scenarios. The average PHL error across the nine scenarios was 7.40% for the ML-based method, 2.06% less than the 9.46% PHL error average across scenarios that was exhibited by the baseline method. Additionally, the PHL error was below 5% for at least 95% of the testing interval for 3 of 9 tested intervals with the ML approach, whereas it did not achieve this metric for any of the baseline tests. Overall, simulation results indicate the superior performance of an ML-based approach compared to the conventional baseline reference-control approach, showcasing its potential to support grid stability and operational efficiency. This laboratory HIL testing using real PPC, representative power system simulation models in real-time with detailed PV plant and inverter models, and real-world communication protocols gives us confidence that this machine learning based PHL estimation algorithm works well in the hardware PPC and therefore de-risks future field commissioning. The end goal of this project is to advance grid technology to address the grid operation challenges brought by solar plant’s variability and uncertainties in power generation.

14 SOLAR ENERGY↗
DOE OSTI2024

Application of Banking Scoring and Rating for Coherent Risk Measures in Electricity Systems ABSCORES

This project developed a framework for asset and system risk management that can be incorporated into current electricity system operations to improve economic efficiency and establish an Electric Assets Risk Bureau. We leveraged scoring and ratings from banking and financial institutions alongside current optimization methods in dispatching power systems to help system operators and electricity markets schedule resources. This approach is based on the observation that there are major discrepancies between the power scheduled by a system operator and the actual power generated/consumed. These discrepancies—exacerbated by unplanned contingencies (e.g., natural disasters)—are caused by multiple factors, including the different financial, environmental and risk preferences of power producers, consumers, and aggregators. We developed a framework that counteracts two failures in electricity system operations: imperfect information and missing markets for products. The technical approach included five tasks. Tasks 1 and 2 supported the development of risk scores at the asset level with historical data collected for this project. Tasks 3, 4, and 5 incorporated scoring into decision-making at the system level. The proposed effort achieved PERFORM's Program Objectives because the proposed outputs and algorithms do not exist in the electricity industry and are an innovative approach to managing risk. Since the acknowledged need to better assess and act upon risk profiles for grid assets has not been met by the industry, this project will also impact ARPA-E's Mission Areas, including improving energy efficiency and giving the U.S. a technological lead in advanced energy technologies.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

Novel CHI3L1 ‐Associated Angiogenic Phenotypes Define Glioma Microenvironments: Insights From Multi‐Omics Integration

ABSTRACT The CHI3L1 signaling pathway significantly influences glioma angiogenesis, but its role in the tumor microenvironment (TME) remains elusive. We propose a novelCHI3L1‐associated vascular phenotype classification for glioma through integrative analyses of multiple datasets with bulk and single‐cell transcriptome, genomics, digital pathology, and clinical data. We investigated the biological characteristics, genomic alterations, therapeutic vulnerabilities, and immune profiles within these phenotypes through a comprehensive multi‐omics approach. We constructed the vascular‐related risk (VR) score based onCHI3L1‐associated vascular signatures (CAVS) identified by machine learning algorithms. Utilizing unsupervised consensus clustering, gliomas were stratified into three distinct vascular phenotypes: Cluster A, marked by high vascularization and stromal activation with a relatively low levels of tumor‐infiltrating lymphocytes (TILs); Cluster B, characterized by moderate vascularization and stromal activity, coupled with a high density of TILs; and Cluster C, defined by low vascularization and sparse immune cell infiltration. We observed that the CAVS effectively indicated glioma‐associated angiogenesis and immune suppression by single‐cell RNA‐seq analysis. Moreover, the high‐VR‐score group exhibited enhanced angiogenic activity, reduced immune response, resistance to immunotherapy, and poorer clinical outcomes. The VR score independently predicted glioma prognosis and, combined with a nomogram, provided a robust clinical decision‐making tool. Potential drug prediction based on transcription factors for high‐risk patients was also performed. Our study reveals thatCHI3L1‐associated vascular phenotypes shape distinct immune landscapes in gliomas, offering insights for optimizing therapeutic strategies to improve patient outcomes.

Oncology↗
DOE OSTI2026

Classical-Quantum Algorithm for Solving Stochastic Programs

Stochastic programming provides a rigorous mathematical framework for making decisions under uncertainty in a risk-aware manner. Two-stage stochastic programming is, perhaps, the simplest form of this framework. Here the first-stage variables represent decisions that must be made "here and now" in the face of uncertainty, while the second-stage variables are decisions made after uncertain events. However, the broad adoption of stochastic programming has been hindered by computational challenges caused by the two-stage stochastic programming formulation which requires solving an ensemble of optimization problems. Using quantum amplitude estimation (QAE), quantum computers have shown the theoretic ability to compute expectations with Monte-Carlo methods with quadratically fewer samples than classical methods. In this work, we present a quantum algorithm for computing the expectation term using QAE for given first-stage decisions. Further, we detail methods of computing gradient information from the quantum calculation enabling the application of classical gradient-based optimization techniques. The result is a classical-quantum hybrid method of solving two-stage stochastic programs. These techniques are demonstrated with computational experiments based an engineering optimization problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Integrated Transmission-Distribution Multi-Period Switching for Wildfire Risk Mitigation: Improving Speed and Scalability with Distributed Optimization: Preprint

With increasingly severe wildfire conditions driven by climate change, utilities must manage the risk of wildfire ignitions from electric power lines. During "public safety power shutoff'" events, utilities de-energize power lines to reduce wildfire ignition risk, which may result in load shedding. Distributed energy resources provide flexibility that can help support the system to reduce load shedding when lines are de-energized. We investigate a coordinated transmission-distribution optimization problem that balances wildfire risk mitigation and load shedding. We model distribution systems that include battery energy storage systems which may support loads when transmission lines are de-energized. This multi-period integrated transmission-distribution optimal switching problem jointly optimizes line switching decisions, the generators' setpoints, load shedding, and the batteries' states of charge, resulting in significant computational challenges. To improve scalability, we decompose the problem over both space and time and apply a distributed optimization algorithm. Using a large-scale synthetic California test case with realistic distribution models and real wildfire risk data, we show that distributed optimization can solve large-scale multi-period switching problems that are otherwise intractable for centralized solvers. We also discuss challenges and future directions for improving the distributed algorithm's convergence performance as the number of time periods increases.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

A Systems-Level Approach to Address Risks and Ethics in Artificial Intelligence Systems

Artificial intelligence (AI) is rapidly changing the world, from completely controlling routine or mundane tasks like text and image generation, to powering advanced algorithms that control critical systems. The recent advances in generative AI quickly overwhelmed multiple industries from education to finance as first adopters rushed (and continue to rush) to take advantage of the technology. The expanding AI ecosystem presents novel risks and ethical challenges that must be handled to ensure that technology is leveraged fairly and ethically. There are intertwined risks and ethical challenges stemming from the stochastic nature of AI (i.e., intrinsic risks), as well as from specific applications (i.e., extrinsic risks). Appropriately regulating AI requires a systems-approach to develop an integrated solution to these dependent challenges. Thus far, however, questions of risk, ethics and regulation appear to occupy separate spaces. This paper reviews the risks and ethical implications of AI and proposes a system-level approach to integrating ethics and regulation for the nascent industry.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

FIRE: A Failure-Adaptive RL Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated between edge servers due to user mobility. Reinforcement Learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like AR/VR and real- time obstacle detection. These rare failures, being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. We introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose FIRE-ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove FIRE-ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (FIRE-ImDQL) and actor critic (FIRE-ImACRE) versions of our algorithm to enhance scalability. Here, we extend our framework to accommodate users with varying risk tolerances of rare failure events. Through trace-driven experiments, we show that FIRE reduces edge computing costs compared to vanilla RL and the greedy baseline in the event of failures.

Edge computing↗