Search NASA⌕ Search

SEARCH · Search NASA

Results for “Optimal Allocation”

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 253 records · Page 14

Water foraging with dynamic roots in E3SM; The role of roots in terrestrial ecosystem memory on intermediate timescales (Final Technical Report)

Terrestrial ecosystems can show sustained responses to stress events that may last for years after the initial perturbation. This phenomenon is referred to as legacy or memory and it emerges from a set of ecosystem processes that are poorly captured by Earth System and Land Surface Models. Consequently, these models struggle to predict the impact that extreme climate events have on surface energy, carbon and hydrological exchange once a stressor such as drought has relaxed or in response to repeated exposure to stress. In this project, we set out to test how the addition of dynamic root profiles in land surface models impact the capacity for Earth System Models, such as the Department of Energy’s E3SM, to capture realistic legacy effects. Observations have shown that vegetation shifts their root profiles during stress events to forage for water and these altered root profiles may take years to relax back to the initial state. We hypothesized that the alteration of the belowground root structures may be a source of terrestrial ecosystem legacy that is missing from models. To test this idea we undertook three core activities. (1) We developed a global-scale analysis of the impact of dynamic roots on ecosystem legacy building from a recently developed dynamic root module. (2) We developed new root dynamics in the DOE’s Energy Land Model (ELM) that allowed not only root profiles to shift their profile but also simultaneously alter carbon allocation to fine root pools. We then tested the impact of these new dynamics with intensive sensitivity analysis at four long-term AmeriFlux sites. (3) We undertook detailed isotopic analysis of tree rings from these AmeriFlux sites to assess ecophysiological and ecohydrological legacy to stress events that can be used to benchmark the sensitivity experiments with ELM. From these core activities, we report the following key findings. Firstly, on a global scale, the addition of dynamic roots led to chronically water-stressed ecosystems recovering faster to climate stress while wetter ecosystem showed enhanced legacy. This is because across ecosystems, stress events were almost universally associated with water shortages that led to the development of deeper root profiles. These deeper root profiles proved beneficial for recovery from drought stress. While the root dynamics did not universally improve the modeled representation of legacy it showed complex transient dynamics that emerge from the addition of dynamic roots. Secondly, the sensitivity analysis illustrated long term shifts in rooting depths away from the prescribed default profile suggesting that initializing of root profiles could benefit from spin-up simulations that converge on locally optimized root profiles. In addition, by enabling dynamic allocation some of the sites predicted unrealistically low allocation to roots (and high allocation to leaves). While these changes did not dramatically alter modeled gross primary productivity, they illustrated that without more sophisticated root processes in models, there is little penalty to dramatically disinvest in roots. Thirdly, the isotopic analysis of tree rings showed highly distinct legacy responses across species and sites. For example, T. canadensis showed reduced transpiration the year after stress events illustrated by sustained elevated $\delta^{18}$O. In contrast, A saccharum displayed elevated $\delta^{13}$C associated with reduced stomatal conductance in response to the previous years’ stress event. These geochemical signatures of legacy were present despite tree growth returning to normal the year after the stress. The results show the importance of species-level dynamics in legacy that are absent in modeling that assumes common traits within plant functional types. In summary, the work here established new avenues to explore root dynamics in models while illustrating how additional root processes are needed before dynamic carbon allocation can be implemented. Lastly, this project provided mentorship to a postdoctoral fellow, training for an early career scientist and multiple undergraduate students recruited from a minority serving institution.

54 ENVIRONMENTAL SCIENCES↗

Optimal control technology for distributed energy resources

Devices and methods of allocating distributed energy resources (DERs) to loads connected to a microgrid based on the cost of the DERs are provided. The devices and methods may determine one or more microgrid measurements. The devices and methods may determine one or more real-time electricity prices associated with utility generation sources. The devices and methods may determine one or more forecasts. The devices and methods may determine a cost associated with one or more renewable energy sources within the microgrid. The devices and methods may determine an allocation of the renewable sources to one or more loads in the microgrid.

Meeker, Richard H.↗

Optimal control technology for distributed energy resources

Devices and methods of allocating distributed energy resources (DERs) to loads connected to a microgrid based on the cost of the DERs are provided. The devices and methods may determine one or more microgrid measurements. The devices and methods may determine one or more real-time electricity prices associated with utility generation sources. The devices and methods may determine one or more forecasts. The devices and methods may determine a cost associated with one or more renewable energy sources within the microgrid. The devices and methods may determine an allocation of the renewable sources to one or more loads in the microgrid.

Meeker, Richard H.↗

Dynamic Asset Allocation with Expected Shortfall via Quantum Annealing

Recent advances in quantum hardware offer new approaches to solve various optimization problems that can be computationally expensive when classical algorithms are employed. We propose a hybrid quantum-classical algorithm to solve a dynamic asset allocation problem where a target return and a target risk metric (expected shortfall) are specified. We propose an iterative algorithm that treats the target return as a constraint in a Markowitz portfolio optimization model, and dynamically adjusts the target return to satisfy the targeted expected shortfall. The Markowitz optimization is formulated as a Quadratic Unconstrained Binary Optimization (QUBO) problem. The use of the expected shortfall risk metric enables the modeling of extreme market events. We compare the results from D-Wave’s 2000Q and Advantage quantum annealers using real-world financial data. Both quantum annealers are able to generate portfolios with more than 80% of the return of the classical optimal solutions, while satisfying the expected shortfall. We observe that experiments on assets with higher correlations tend to perform better, which may help to design practical quantum applications in the near term.

97 MATHEMATICS AND COMPUTING↗

Energy-efficient cooperative resource allocation and task scheduling for Internet of Things environments

Offloading Internet of Things (IoT) tasks to the cloud for further processing might not always lead to an optimal execution time, particularly in situations such as resource contention, under-provisioning, over-provisioning, and fragmentation. In addition, dynamically optimizing the number of Virtual Machines (VMs) for resource scheduling in order to meet application requirements remains a major research challenge. Further, existing resource scheduling algorithms focus primarily on minimizing operational costs while maximizing resource sharing and utilization. Considering energy utilization as part of the resource allocation and scheduling process as an optimization objective for maintaining load balancing has often been neglected. To address these challenges and more, we propose a cooperative energy-aware resource allocation and scheduling strategy based on a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) multi-criteria decision-making method. Here we used the Grid Workloads Archive dataset to evaluate our proposed approach named TOPREAL. Experimental results with respect to the allocation of VM resources when considering processing a large segment of tasks indicate that TOPREAL outperforms existing algorithms in terms of energy savings, with an average improvement of 40.25%, while maintaining an average improvement of 16.21% when it comes to execution time. Results also demonstrate that our method can save an average of 78.06 processing hours and 63,215kJ of energy when compared to existing scheduling algorithms. These results demonstrate the effectiveness of our proposed model and the viability of using multi-criteria decision-making techniques such as TOPSIS to solve the resource allocation and scheduling problem in edge environments.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Building a Wide-Area File Transfer Performance Predictor: An Empirical Study

Wide-area data transfer is central to geographically distributed scientific workflows. Faster delivery of data is important for these workflows. Predictability is equally (or even more) important. With the goal of providing a reasonably accurate estimate of data transfer time to improve resource allocation & scheduling for workflows and enable end-to-end data transfer optimization, we apply machine learning methods to develop predictive models for data transfer times over a variety of wide area networks. To build and evaluate these models, we use 201,388 transfers, involving 759 million files totaling 9 PB transferred, over 115 heavily used source-destination pairs (“edges”) between 135 unique endpoints. We evaluate the models for different retraining frequencies and different window size of history data. In the best case, the resulting models have a median prediction error of ≤21% for 50% of the edges, and ≤32% for 75% of the edges. We present a detailed analysis of these results that provides insights into the cause of some of the high errors. We envision that the performance predictor will be informative for scheduling geo-distributed workflows. The insights also suggest obvious directions for both further analysis and transfer service optimization.

Liu, Zhengchun↗

Optimization of Composite Cloud Service Processing with Virtual Machines

By leveraging virtual machine (VM) technology, we optimize cloud system performance based on refined resource allocation, in processing user requests with composite services. Our contribution is three-fold. (1) We devise a VM resource allocation scheme with a minimized processing overhead for task execution. (2) We comprehensively investigate the best-suited task scheduling policy with different design parameters. (3) We also explore the best-suited resource sharing scheme with adjusted divisible resource fractions on running tasks in terms of Proportional-share model (PSM), which can be split into absolute mode (called AAPSM) and relative mode (RAPSM). We implement a prototype system over a cluster environment deployed with 56 real VM instances, and summarized valuable experience from our evaluation. As the system runs in short supply, lightest workload first (LWF) is mostly recommended because it can minimize the overall response extension ratio (RER) for both sequential-mode tasks and parallel-mode tasks. In a competitive situation with over-commitment of resources, the best one is combining LWF with both AAPSM and RAPSM. It outperforms other solutions in the competitive situation, by 16 + % w.r.t. the worst-case response time and by 7.4 + % w.r.t. the fairness.

cloud resource allocation↗

Light Water Reactor Sustainability Program A Reference Plan for Control Room Modernization: Planning and Analysis Phase

The U.S. Department of Energy’s Light Water Reactor Sustainability (LWRS) program is collaborating with a U.S. nuclear utility to bring about a systematic fleet-wide control room modernization. To facilitate this upgrade, a new distributed control system (DCS) is being introduced into the control rooms of these plants. The DCS will upgrade the legacy plant process computer and emergency response facility information system. In addition, the DCS will replace an existing analog turbine control system with a display-based system. With technology upgrades comes the opportunity to improve the overall human-system interaction between the operators and the control room. To optimize operator performance, the LWRS Control Room Modernization research team followed a human-centered approach published by the U.S. Nuclear Regulatory Commission. NUREG-0711, Rev. 3, Human Factors Engineering Program Review Model (O’Hara et al., 2012), prescribes four phases for human factors engineering. This report provides examples of the first phase, Planning and Analysis. The three elements of Planning and Analysis in NUREG-0711 that are most crucial to initiating control room upgrades are: • Operating Experience Review: Identifies opportunities for improvement in the existing system and provides lessons learned from implemented systems. • Function Analysis and Allocation: Identifies which functions at the plant may be optimally handled by the DCS vs. the operators. • Task Analysis: Identifies how tasks might be optimized for the operators. Each of these elements is covered in a separate chapter. Examples are drawn from workshops with reactor operators that were conducted at the LWRS Human System Simulation Laboratory HSSL and at the respective plants. The findings in this report represent generalized accounts of more detailed proprietary reports produced for the utility for each plant. The goal of this LWRS report is to disseminate the technique and provide examples sufficient to serve as a template for other utilities’ projects for control room modernization.

99 GENERAL AND MISCELLANEOUS↗

I/O-aware bandwidth allocation for petascale computing systems

In the Big Data era, the gap between the storage performance and an appli- cation's I/O requirement is increasing. I/O congestion caused by concurrent storage accesses from multiple applications is inevitable and severely harms the performance. Conventional approaches either focus on optimizing an ap- plication's access pattern individually or handle I/O requests on a low-level storage layer without any knowledge from the upper-level applications. In this paper, we present a novel I/O-aware bandwidth allocation framework to coordinate ongoing I/O requests on petascale computing systems. The motivation behind this innovation is that the resource management system has a holistic view of both the system state and jobs' activities and can dy- namically control the jobs' status or allocate resource on the y during their execution. We treat a job's I/O requests as periodical subjobs within its lifecycle and transform the I/O congestion issue into a classical scheduling problem. Based on this model, we propose a bandwidth management mech- anism as an extension to the existing scheduling system. We design several bandwidth allocation policies with different optimization objectives either on user-oriented metrics or system performance. We conduct extensive trace- based simulations using real job traces and I/O traces from a production IBM Blue Gene/Q system at Argonne National Laboratory. Experimental results demonstrate that our new design can improve job performance by more than 30%, as well as increasing system performance.

I/O congestion↗

Valued peaks: Sustainable water allocation for small hydropower plants in an era of explicit ecological needs

Optimizing hydropower operations to balance economic profitability and support functioning ecosystem services is integral to river management policy. In this article, we propose a dynamic, constrained optimization framework for small hydropower plants (SHPs) to evaluate trade-offs between economic profitability and socio-ecological requirements. Specifically, we examine the balance between short-term losses in hydropower generation and the potential for compensatory benefits in the form of revenue from recreational ecosystem services, irrespective of the direct beneficiary. Our framework integrates a fish habitat model, a hydropower optimization model, and a recreational ecosystem service estimate to evaluate different environmental flow scenarios. The optimization process gives three outflow release scenarios, informed by previous streamflow realisations (dam inflow), and designed environmental flow constraints. The framework is applied and tested for the river Kuusinkijoki in North-eastern Finland, which is a habitat for migratory brown trout and grayling populations. We show that the revenue loss due to the environmental flow constraints arises through a reduction in revenue per generated energy unit and through a reduction in turbine efficiency. Additionally, the simulation results reveal that all the designed environmental flow constraints cannot be met simultaneously. Under the environmental flow scenario with both minimum flow and flow ramping rate constraints, the annual hydropower revenue decreases by 16.5 %. An annual increase of 8 % in recreational fishing visits offsets the revenue loss. In conclusion, the developed framework provides knowledge of the costs and benefits of hydropower environmental flow constraints and guides the prioritizing process of environmental measures.

13 HYDRO ENERGY↗

Modelling belowground plant acclimation to low soil nitrogen – a heuristic optimality-based approach

Increased root growth to access greater soil mineral nitrogen resources and increased root exudation to stimulate microbial mineralization of soil organic nitrogen are widely observed plant acclimations to nitrogen limitation. However, their quantitative contribution to plant growth and ecosystem productivity remains largely elusive. Here, we present a novel optimality-based eco-evolutionary model in which plants dynamically regulate carbon partitioning between root growth and exudation to maximize their aboveground growth. Our simulations indicated that the availability of soil mineral and organic nitrogen as well as plant nitrogen demand and nitrogen uptake capacity shape optimal carbon partitioning between root growth and exudation. The simulated carbon allocation patterns aligned with empirical studies on belowground plant responses to varying soil nitrogen resources. Our eco-evolutionary approach represents a paradigmatic change in modelling plant nitrogen foraging, which is essential to generate hypotheses on optimal plant acclimation in future soil environments characterized by more erratic nitrogen availability.

Chakrawal, Arjun (ORCID:0000000345724347)↗

WE-AB-209-10: Optimizing the Delivery of Sequential Fluence Maps for Efficient VMAT Delivery

Purpose: To develop an optimization model and solution approach for computing MLC leaf trajectories and dose rates for high quality matching of a set of optimized fluence maps to be delivered sequentially around a patient in a VMAT treatment. Methods: We formulate the fluence map matching problem as a nonlinear optimization problem where time is discretized but dose rates and leaf positions are continuous variables. For a given allotted time, which is allocated across the fluence maps based on the complexity of each fluence map, the optimization problem searches for the best leaf trajectories and dose rates such that the original fluence maps are closely recreated. Constraints include maximum leaf speed, maximum dose rate, and leaf collision avoidance, as well as the constraint that the ending leaf positions for one map are the starting leaf positions for the next map. The resulting model is non-convex but smooth, and therefore we solve it by local searches from a variety of starting positions. We improve solution time by a custom decomposition approach which allows us to decouple the rows of the fluence maps and solve each leaf pair individually. This decomposition also makes the problem easily parallelized. Results: We demonstrate method on a prostate case and a head-and-neck case and show that one can recreate fluence maps to high degree of fidelity in modest total delivery time (minutes). Conclusion: We present a VMAT sequencing method that reproduces optimal fluence maps by searching over a vast number of possible leaf trajectories. By varying the total allotted time given, this approach is the first of its kind to allow users to produce VMAT solutions that span the range of wide-field coarse VMAT deliveries to narrow-field high-MU sliding window-like approaches.

60 APPLIED LIFE SCIENCES↗

Resource allocatiion: sequential data collection for reliability analysis involving systems and component level data

In analyzing the reliability of complex systems, several types of data from full-system tests to component level tests are commonly available and are used. After a preliminary analysis, additional resources may be available to collect new data. The goal of resource allocation is to identify the best new data to collect to maximally improve the prediction of system reliability. While several possible definitions of 'maximally improve' are possible, we focus on reducing the uncertainty or the width of the uncertainty interval for the prediction of system reliability at a user-specified age(s). In this paper, we present an algorithm that allows us to estimate the anticipated improvement to the analysis with the addition of new data, based on current understanding of all of the statistical model parameters. This quantitative assessment of the anticipated improvement can be helpful to justify the benefits of collecting new data. Additionally by comparing different potential allocations, it is possible to determine what new data should be collected to improve our understanding of the response. This optimization takes into account the relative cost of different data types and can be based on flexible allocation options, or subject to logistical constraints.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

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↗

Decision Analysis Methods For the Analysis of Nuclear Terrorism Threats with Imperfect Information

Protection of commercial nuclear fuel cycles against adversary groups who may attempt to steal weapons-usable material is an issue of interest to the U.S. Department of Energy, Office of Nuclear Energy. The wide array of potential nuclear fuel cycle configurations and the security measures that could be deployed to protect them pose a daunting system design problem. In general, there are billions of potential design configurations. Moreover, the design choices are not independent – the effectiveness of one design feature or security measure can affect the desirability of other design choices. To explore this issue, we develop a mixed-integer optimization problem that solves a complex decision tree to allocate security resources across a commercial nuclear fuel cycle configuration. A nominal UREX+ reprocessing facility is used to demonstrate how the model allocates resources across a particular fuel cycle facility and shows how the problem can be scaled up to include other facilities and design features in the fuel cycle. In our model, the defender first chooses a set of safeguards to implement in order to mitigate the risk of a terrorist theft from various unit operations in the reprocessing facility. The attacker observes the defender’s strategy choice and executes an attack to acquire material, including the possibility of declining to attack at all. The model considers the terrorist as an intelligent adversary with a set of attack strategies known to the defender. The strategic choices made by both the defender and attacker affect the probability of a successful attack by the terrorist and in turn affect the distribution of consequences to the defender. We use a decision tree to illustrate the interactions among costs, decisions, correlated uncertainties, and outcomes, and then show how to formulate the problem as a mixed-integer program with an equivalent solution. The novel features of our formulation include the following. First, as discussed above, we use a sequential game-theoretic formulation (a Stackelberg game). This formulation assumes the attacker can observe the defender’s actions before the attack is executed. Many previous game-theoretic studies have assumed attacker and defender act simultaneously without knowledge of the other’s strategy choice. We believe the sequential game formulation is more applicable for knowledgeable insider adversaries, the focus of this study. Second, we build on our previous work that has developed a methodology to reflect the correlation among probability distributions represented as discrete chance nodes in a decision tree. We illustrate how this methodology can be applied to two chance nodes in a decision tree that relate the quality of the materials that might be stolen or diverted by an adversary with the yield of a weapon that might be constructed from that material. In a decision tree, the dependence of the yield on the quality of the material could be modeled with conditional probabilities of the weapon yield given the quality of the materials obtained. For three outcome discretizations, this would require the assessment of nine conditional probabilities from domain experts as part of the model building effort. In contrast, our methodology will allow this same representation of the tree based on the assessment of the correlation between these two chance nodes by the experts, which we believe is a much easier and more reliable assessment task. The advantage of this approach increases as the number of dependent chance nodes grows in a decision tree representation of this problem. Third, we extend this approach to the approximation of the dependence between discrete binary events such as success or failure represented by binary chance nodes in a decision tree or in the special case of a probabilistic risk analysis (PRA) based on an event tree. This extension is a novel application in this domain, and uses Monte Carlo simulation to determine the appropriate conditional probabilities on the binary chance nodes when the number of correlated uncertainties is more than two. Fourth, we show how these decision trees or probability trees can be formulated and solved as equivalent integer programming (IP) problems. The advantages of the IP representation include the opportunity to use the computing power associated with powerful optimization solver algorithms available on high speed computers to solve very large versions of these trees, and the ability to include several such models of different facilities into a much larger IP with connecting constraints that represent budget restrictions, number of available inspection opportunities in a given time window, or other dependencies among these facilities. Policy makers can use the resulting model to inform their decisions about how to assess terrorism risk and to safeguard the commercial nuclear fuel cycle.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Coordinated resource allocation to plant growth–defense tradeoffs

Summary Plant resource allocation patterns often reveal tradeoffs that favor growth (G) over defense (D), or vice versa. Ecologists most often explain G–D tradeoffs through principles of economic optimality, in which negative trait correlations are attributed to the reconciliation of fitness costs. Recently, researchers in molecular biology have developed ‘big data’ resources including multi‐omic (e.g. transcriptomic, proteomic and metabolomic) studies that describe the cellular processes controlling gene expression in model species. In this synthesis, we bridge ecological theory with discoveries in multi‐omics biology to better understand how selection has shaped the mechanisms of G–D tradeoffs. Multi‐omic studies reveal strategically coordinated patterns in resource allocation that are enabled by phytohormone crosstalk and transcriptional signal cascades. Coordinated resource allocation justifies the framework of optimality theory, while providing mechanistic insight into the feedbacks and control hubs that calibrate G–D tradeoff commitments. We use the existing literature to describe the coordinated resource allocation hypothesis (CoRAH) that accounts for balanced cellular controls during the expression of G–D tradeoffs, while sustaining stored resource pools to buffer the impacts of future stresses. The integrative mechanisms of the CoRAH unify the supply‐ and demand‐side perspectives of previous G–D tradeoff theories.

Monson, Russell K.↗

Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server

Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids

As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗