Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Intelligent Systems”

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 1,099 records · Page 61

Computer Science Research Needs for Parallel Discrete Event Simulation (PDES)

Historically, scientific computing efforts have demonstrated the clear need for, and effective use of, supercomputing with traditional time-stepped simulations. Nevertheless, there are several areas in the mission spaces of the U.S. Department of Energy and other agencies waiting to tap advanced computing research using a different, discrete event style of modeling, simulation, and analysis. These span a wide spectrum of applications including energy grid resilience, urban planning and policy, transportation science, building technologies, emergency response and planning, environmental impact analysis, computational epidemiology, Internet communications, cyber security, and cyber-physical systems, to name only a few. Even within traditional scientific applications, the role of discrete event modes of execution is increasing in the form of new event-based mathematical solvers such as quantized state integration methods and discrete-continuous hybrid system solvers. Co-design of advanced supercomputing hardware systems is another area that exploits discrete event simulation at its core for effective analyses. Complex systems, entity behaviors and interconnections play a significant role in all these applications, which are mapped to large-scale models with discrete event formulations. To make advancements in all the aforementioned scientific areas, many technical aspects need to be more thoroughly studied and deeply understood in parallel discrete event simulation (PDES). The unique dynamics inherent in a discrete event modeling approach, by their very nature, intersect and influence the entire stack of the computing system, including (a) the unique nature of the instruction sets exercised in PDES workloads without a predominance of high-precision floating point operations, (b) virtual time-constrained multi-threaded execution of many logical processes per processor, (c) extremely variable and difficult to predict network traffic characteristics, (d) interfaces and inter-dependencies with machine learning and artificial intelligence codes at higher software layers, and (e) highly challenging load balancing needs, especially in effectively accounting for accelerated/extremely heterogeneous computing in current and future high-performance computing systems. Efficient and accurate parallel execution of PDES workloads is also dominated by challenges in dealing with their asynchronous concurrency fundamentally present at the model level. Conservative synchronization, optimistic/speculative synchronization, and their hybrid schemes open new questions in fundamental computer science with respect to reversibility of computation and prediction (lookahead) of behaviors inherent within model codes. On the implementation front, there are relatively few scalable, general-purpose parallel discrete event simulators in the world, and even fewer have been studied on emerging hardware platforms. To enable scientific advances using PDES, the research needs in computer science must also be pursued and met in the intersection of the algorithmic and hardware-aware aspects of scalable PDES engines. This report is aimed at capturing a computer science-oriented view of this important area of research in PDES, presenting a sample of important applications with their inherent discrete event technology elements. Needs are outlined in core areas of parallel discrete event research as well as cross-cutting directions in computer science research that positively impact scientific advancements across several important application areas. A selection of priority research opportunities in advanced computing for PDES is identified to serve as reference for key research topics and their order of importance for scientific advancements.

97 MATHEMATICS AND COMPUTING↗

Smart connected worker edge platform for smart manufacturing: Part 1—Architecture and platform design

Abstract The challenge of sustainably producing goods and services for healthy living on a healthy planet requires simultaneous consideration of economic, societal, and environmental dimensions in manufacturing. Enabling technology for data driven manufacturing paradigms like Smart Manufacturing (a.k.a. Industry 4.0) serve as the technological backbone from which sustainable approaches to manufacturing can be implemented. Unfortunately, these technologies are typically associated with broader and deeper factory automation that is often too expensive and complex for the small and medium sized manufacturers (SMMs) that comprise the majority of manufacturing business in the USA and for whom their most valuable asset are the people whose jobs automation while replace. This paper describes an edge intelligent platform to integrate internet‐of‐things technologies with computing hardware, software, computational workflows for machine learning, and data ingestion, enabling SMMs to transition into smart manufacturing paradigms by leveraging the intelligence of their people. The platform leverages consumer grade electronics and sensors (affordable and portable), customized software with open source software packages (accessible), and existing communication network infrastructures (scalable). The software systems are implemented via Kubernetes orchestration of Docker containerization to ensure scalability and programmability. The platform is adaptive via computational workflow engines that produce information from data by processing with low‐cost edge computing devices while efficiently accessing resources of cloud servers as needed. The proposed edge platform connects workers to technological resources that provide computational intelligence (i.e., silicon‐based sensing and computation for data collection and contextualization) to enable decision making at the edge of advanced manufacturing.

Kim, Yoon G.↗

A Framework for the Systematic Collection of Open Source Intelligence

Following legislative directions, the Intelligence Community has been mandated to make greater use of Open Source Intelligence (OSINT). Efforts are underway to increase the use of OSINT but there are many obstacles. One of these obstacles is the lack of tools helping to manage the volume of available data and ascertain its credibility. We propose a unique system for selecting, collecting and storing Open Source data from the Web and the Open Source Center. Some data management tasks are automated, document source is retained, and metadata containing geographical coordinates are added to the documents. Analysts are thus empowered to search, view, store, and analyze Web data within a single tool. We present ORCAT I and ORCAT II, two implementations of the system.

99 GENERAL AND MISCELLANEOUS↗

Operando microscopy for neuromorphic hardware

Microscopy techniques can uncover the physical properties and dynamic behaviours of materials, driving the discovery of emergent phenomena and guiding the design of next-generation computing hardware. As artificial intelligence becomes pervasive, the demand for high-performance materials to support sustainable information technologies is growing. Here, this Review highlights state-of-the-art imaging from electron and X-ray to optical techniques to probe the dynamics of neuromorphic materials, including operando characterization of devices. We examine design principles for neuromorphic materials, along with obstacles that hinder their development. Emphasis is placed on spatially and temporally resolved approaches that capture state changes including phase transitions, ferroic switching and spin-wave propagation that emulate biological components such as neurons, synapses and their connectivity. We discuss challenges in operando characterization and the integration of artificial intelligence-driven analysis for feedback-guided material discovery. Finally, we outline opportunities for real-time imaging of neuromorphic systems, paving the way towards adaptive, brain-inspired hardware.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows

While in-situ workflow formulations have addressed some of the data-related challenges associated with extreme-scale scientific workflows, these workflows involve complex interactions and different modes of data exchange. In the context of increasing system complexity, such workflows present significant resource management challenges, requiring complex cost-performance tradeoffs. This paper presents RISE, an intelligent staging-based data management middleware, which builds on the DataSpaces framework and performs intelligent scheduling of data management operations to reduce I/O contention. In RISE, data are always written immediately to local buffers to reduce the effect of the transfer impact upon application performance. RISE identifies applications’ data access patterns and moves data towards data consumers only when the network is expected to be idle, reducing the impact of asynchronous background data movement upon critical data read/write requests. Here, we experimentally demonstrate that RISE can take advantage of staging nodes to offload data during writes without degrading application data movement performance.

97 MATHEMATICS AND COMPUTING↗

A Workflow-based Intelligent Network Data Movement Advisor with End-to-end Performance Optimization

Next-generation eScience applications often generate large amounts of simulation, experimental, or observational data that must be shared and managed by collaborative organizations. Advanced networking technologies and services have been rapidly developed and deployed to facilitate such massive data transfer. However, these technologies and services have not been fully utilized mainly because their use typically requires significant domain knowledge and in many cases application users are even not aware of their existence. By leveraging the functionalities of an existing Network-Aware Data Movement Advisor (NADMA) utility, we propose a new Workflow-based Intelligent Network Data Movement Advisor (WINDMA) with end-to-end performance optimization for this DOE funded project. This WINDMA system integrates three major components: resource discovery, data movement, and status monitoring, and supports the sharing of common data movement workflows through account and database management. This system provides a web interface and interacts with existing data/space management and discovery services such as Storage Resource Management, transport methods such as GridFTP and GlobusOnline, and network resource provisioning brokers such as ION and OSCARS. We demonstrate the efficacy of the proposed transport-support workflow system in several use cases based on its implementation and deployment in DOE wide-area networks.

97 MATHEMATICS AND COMPUTING↗

Advanced Load Identification and Management for Buildings: Cooperative Research and Development Final Report

The goal of this CRADA work is to support Eaton Innovation Center (Eaton) efforts to develop advanced load identification, management technologies, and solutions to reduce building energy consumption by providing fine granular visibility of energy usage information and safety protection of miscellaneous electric loads (MELs) in commercial and residential buildings. MELs load identification and prediction technology will be employed in a novel "Smart eOutlet*" to provide critical intelligence and information to improve the capability and functionality of building load analysis and design tools and building power management systems. The work scoped in this CRADA involves the following activities: development and validation of business value proposition for the proposed technologies through voice of customer investigation, market analysis, and third-party objective assessment; development and validation of energy saving impact as well as assessment of environmental and economic benefits; "smart eOutlet" concept design, prototyping, and validation; field validation of the developed technologies in real building environments. (*Another name denoted as "Smart Power Strip (SPS)" will be used as an alternative of the name "Smart eOutlet" for a clearer definition of the product market position in future work.)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Detailed Structural and Chemical Analysis of Amorphous Compounds in Superconducting Qubit Systems

With massive improvements in device coherence times and gate fidelity over the past two decades, superconducting quantum devices have emerged as a leading technology platform for next generation quantum computing. While many of these improvements have been driven through optimized device designs and geometries, the presence of defects, impurities, interfaces, and surfaces in the constituent materials continue to limit performance and present a critical barrier in achieving scalable quantum systems with long coherence times. As part of the Superconducting Quantum Materials and Systems (SQMS) center, we have applied state-of-the-art materials characterization techniques, such as scanning/transmission electron microscopy, secondary ion mass spectrometry, and atom probe tomography, to identify structural defects and chemical inhomogeneities in superconducting qubits. In this review, we discuss the findings of these efforts as they relate to the inherent surfaces, interfaces, impurities, and defects in superconducting qubits. Through this comprehensive investigation, we provide insight into possible sources of dissipation in these systems. Further, we supplement these findings with potential strategies for mitigating these undesired features in an effort to systematically and intelligently improve the coherence times of superconducting qubits.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Environmentally Assisted Fatigue in Light Water Reactor Environment

This report summarizes the Environmentally Assisted Fatigue (EAF) research conducted at ANL under the US DOE Light Water Reactor Sustainability (LWRS) program. Starting from a rich background in theoretical and experimental EAF, ANL previously developed an approach to evaluate fatigue performance of reactor materials in light water reactor environments with the correction factor F en . The approach was based on a large body of experimental work performed at ANL and elsewhere, and was consistent with American Society of Mechanical Engineers (ASME)’s methodology governing the design and construction of reactor components. In recent years, the program was focused on component fatigue prediction and made several major and fundamental contributions in this area. These accomplishments help meet the needs identified by the industry concerning component level fatigue predictions in complex, transient conditions. The main contribution of the ANL program involved the development of a system-level model for estimating residual strain and life of nuclear reactor coolant system components under connected-system-thermal-mechanical boundary conditions. The goal was to predict the stress hotspots, strain residuals, strain amplitudes and the resulting fatigue lives. Thermal-mechanical stress analysis was performed considering thermal stratification and a design-basis reactor loading cycle. Based on the finite element (FE) model results, the strain residuals, strain amplitudes and resulting fatigue lives of reactor coolant system (RCS) components were predicted. The results show that some of the RCS components can have significantly different strain amplitudes, residual strain, and fatigue lives, despite having similar geometry and material. In addition, the simulated component-level strain profile can guide the selection of appropriate test inputs for conducting laboratory-scale EAF tests. Building upon the system-level model, ANL developed a digital twin (DT) framework to predict the structural states and associated fatigue life of components in real-time. This framework is a comprehensive system designed to predict the structural states and fatigue lives of reactor components. It includes multiple models and integrates artificial intelligence (AI), machine learning (ML), and FE based modeling tools to evaluate the structural states and fatigue lives.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

IM3 Data Center Driven Grid Stress Dataset for the U.S. Western Interconnection

This dataset provides projected grid stress and reliability results (including all model inputs and outputs from an open-source grid operations modeling framework - GO), for the Integrated Multisector, Multiscale Modeling (IM3) project, under varying levels of data center demand growth between 2025 and 2035 in the U.S. Western Interconnection. The scenarios and sensitivity experiments are combinations of different data center demand growth rates and energy, weather, population and economic pathways. Data center demand growth projections were sourced from the Electric Power Research Institute (EPRI). The data center demand growth projection names are: Low (3.71% annual data center demand growth) Moderate (5% annual data center demand growth) High (10% annual data center demand growth) Higher (15% annual data center demand growth) Energy, weather, population and economic pathways are informed by two Shared Socioeconomic Pathways (SSP3 and SSP5) and two Representative Concentration Pathways (RCP4.5 and RCP8.5) following the hotter general circulation model (GCM) forcing group from a set of perturbed thermodynamics simulations. The resulting pathway names are: rcp45hotter_ssp3 rcp45hotter_ssp5 rcp85hotter_ssp3 rcp85hotter_ssp5 The main scenarios and sensitivity experiments are detailed below. Reference scenario: The projected grid stress and reliability results for the U.S. Western Interconnection from a previous study. This scenario does not consider data center demand growth explicitly. Data center scenario: Building on the reference scenario, this scenario considers various data center growth rates and how they impact the U.S. Western Interconnection. Data center loads are modeled as flat 8760-hr profiles. This scenario does not consider new generation and transmission capacities specifically designed to meet the new data center demands. The related folder is named "flat". Delayed generator retirements sensitivity experiment: Building on the data center scenario, this experiment explores the impact of different levels of natural gas and nuclear generator retirement delays. The resulting scenario names are: (1) postponing 100% nuclear retirements; (2) postponing 100% nuclear and 25% natural gas retirements; (3) postponing only 50% natural gas retirements; (4) postponing 100% nuclear and 50% natural gas retirements; (5) postponing 100% nuclear and 75% natural gas retirements; and (6) postponing 100% nuclear and 100% natural gas retirements. The related folder names are: no_gen_retire_0_gas, no_gen_retire_25_gas, no_gen_retire_50_gas, no_gen_retire_50_gas_only, no_gen_retire_75_gas, and no_gen_retire_100_gas. Demand response through curtailment sensitivity experiment: Building on the data center scenario, this experiment explores the impact of different participation and compensation levels of data center demand response. The resulting scenario names are: (1) 5% demand available for curtailment with 750 $/MWh compensation; (2) 5% demand available for curtailment with 500 $/MWh compensation; (3) 5% demand available for curtailment with 250 $/MWh compensation; (4) 15% demand available for curtailment with 750 $/MWh compensation; (5) 15% demand available for curtailment with 500 $/MWh compensation; and (6) 15% demand available for curtailment with 250 $/MWh compensation. The related folder names are: dr_cost_250_drup_0_drdown_5, dr_cost_250_drup_0_drdown_15, dr_cost_500_drup_0_drdown_5, dr_cost_500_drup_0_drdown_15, dr_cost_750_drup_0_drdown_5, and dr_cost_750_drup_0_drdown_15. Combination of delayed generator retirements and demand response through curtailment sensitivity experiment: The impact of combining postponing 100% nuclear and 25% natural gas retirements with 5% demand available for curtailment with 750 $/MWh compensation is simulated. The related folder is named "dr_cost_750_drup_0_drdown_5_nuc_100_gas_25". Please refer to the README file for a detailed description of the dataset including individual files and references.

Artificial Intelligence↗

When Walls Talk, Buildings Can Be Made Better

What if your building could “tell” you how to save money? PNNL is inventing systems to turn buildings from passive users of energy into active participants in the power system—making the buildings we work or live in “work” for us instead. We’re researching how buildings can respond intelligently to the natural environment, evolving grid conditions and dynamic occupant demands—not simply bracing for those external factors. Why do buildings matter to our energy future? Senior Engineer Nora Wang says it’s because buildings account for 75 percent of U.S. electricity consumption and 40 percent of our nation’s energy use overall. That equates to $430 billion in energy bills every year. Powering U.S. buildings contributes more than 2,200 million metric tons of carbon dioxide to the atmosphere annually—more than the total emissions of Russia and Canada combined.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Open-Loop Control of Adjustable Tuned Mass Dampers for Floating Wind Turbine Platforms

In this study, we demonstrate the ability of adjustable tuned mass dampers (TMDs) to reduce the platform motion of floating offshore wind turbines (FOWTs). The TMDs are located in the hull and provide control authority by varying the amount of water ballast and compressed air in a reservoir over time. The optimal TMD settings depend on the wind and wave conditions of the FOWT. We present an open-loop control scheme that changes the TMD natural frequency based on sea state and a simple method for estimating the peak wave period and significant wave height. The performance of this open-loop control is compared to ideal control of the TMDs (set knowing the exact sea state), a TMD with a constant natural frequency targeting the design load case with the greatest platform motion, and a baseline set of simulations of the platform without TMDs. The constant natural frequency case performs nearly as effectively as the actively controlled case, suggesting that the TMDs can be simply designed for extreme load conditions and provide consistent control over a range of environments; however, the methods used to find the optimal TMD parameters and estimate sea state statistics could be used in other aspects of FOWT control and design.

artificial intelligence↗

Next Generation Fast RF Interlock Module and ATCA Adapter for ILC High Availability RF Test Station Demonstration

High availability interlocks and controls are required for the ILC (International Linear Collider) L-Band high power RF stations. A new F3 (Fast Fault Finder) VME module has been developed to process both fast and slow interlocks using FPGA logic to detect the interlock trip excursions. This combination eliminates the need for separate PLC (Programmable Logic Controller) control of slow interlocks. Modules are chained together to accommodate as many inputs as needed. In the next phase of development the F3's will be ported to the new industry standard ATCA (Advanced Telecom Computing Architecture) crate (shelf) via a specially designed VME adapter module with IPMI (Intelligent Platform Management Interface). The goal is to demonstrate auto-failover and hot-swap for future partially redundant systems.

43 PARTICLE ACCELERATORS↗

Storing Affordability: Battery Storage as an Asset to Reduce Data Center Cost Shifts

This report examines how battery energy storage systems (BESS) can help utilities accommodate large load growth while protecting affordability for existing ratepayers. Rapid growth in electricity demand from artificial intelligence (AI) data centers is straining the U.S. grid. Furthermore, many new data centers are entering rural markets, which could offer economic benefits but may also pose implementation challenges for smaller utilities. At the same time, retail electricity prices are increasing faster than inflation, elevating customer affordability as a key challenge. While data centers have not been the primary driver of increases in residential prices to date, they have pushed wholesale energy and capacity prices higher in several markets. Fundamental utility cost-allocation principles show that data center growth can be rate-positive for existing customers only if new peak demand grows faster than the costs a utility must incur to serve it. Several factors, including a utility’s degree of wholesale market exposure, forecast uncertainty and stranded-asset risk, and tariff design can determine the outcome of load growth on retail rates. Energy storage can make several affordability contributions in the face of this landscape of uncertainty and market volatility, including deferral of higher-cost grid investments through improved utilization of existing assets and flexibility of new large loads, insulation from volatile wholesale prices through peak shaving, and reliability support to address grid risks stemming from the behavior of AI data center loads. Different potential BESS deployment pathways—utility-scale front-of-the-meter systems, aggregated small-scale storage installations, and data center-sited behind-the-meter storage—are compared against each other and against conventional capacity alternatives. This framework is intended as a conceptual resource to utilities, particularly smaller public utilities with rural service territories, who may be considering the role that energy storage can play in insulating existing ratepayers from data center cost shifts.

25 ENERGY STORAGE↗

A Public-Private-Acadmic Partnership to Advance Solar Power Forecasting

The National Center for Atmospheric Research (NCAR) is pleased to have led a partnership to advance the state-of-the-science of solar power forecasting by designing, developing, building, deploying, testing, and assessing the SunCast™ Solar Power Forecasting System. The project has included cutting edge research, testing in several geographically- and climatologically-diverse high penetration solar utilities and Independent System Operators (ISOs), and wide dissemination of the research results to raise the bar on solar power forecasting technology. The partners include three other national laboratories, six universities, and industry partners. This public-private-academic team has worked in concert to perform use-inspired research to advance solar power forecasting through cutting-edge research to advance both the necessary forecasting technologies and the metrics for evaluating them. The project has culminated in a year-long, full-scale demonstration of provide irradiance and power forecasts to utilities and ISOs to use in their operations. The project focused on providing elements of a value chain, beginning with the weather that causes a deviation from clear sky irradiance and progresses through monitoring and observations, modeling, forecasting, dissemination and communication of the forecasts, interpretation of the forecast, and through decision-making, which produces outcomes that have an economic value. The system has been evaluated using metrics developed specifically for this project, which has provided rich information on model and system performance. Research was accomplished on the very short range (0-6 hours) Nowcasting system as well as on the longer term (6-72 hour) forecasting system. The shortest range forecasts are based on observations in the field. The shortest range system, built by Brookhaven National Laboratory (BNL) and based on Total Sky Imagers (TSIs) is TSICast, which operates on the shortest time scale with a latency of only a few minutes and forecasts that currently go out to about 15 min. This project has facilitated research in improving the hardware and software so that the new high definition cameras deployed at multiple nearby locations allow discernment of the clouds at varying levels and advection according to the winds observed at those levels. Improvements over “smart persistence” are about 29% for even these very short forecasts. StatCast is based on pyranometer data measured at the site as well as concurrent meteorological observations and forecasts. StatCast is based on regime-dependent artificial intelligence forecasting techniques and has been shown to improve on “smart persistence” forecasts by 15-50%. A second category of short-range forecasting systems employ satellite imagery and use that information to discern clouds and their motion, allowing them to project the clouds, and the resulting blockage of irradiance, in time. CIRACast (the system produced by the Cooperative Institute for Atmospheric Research [CIRA] at Colorado State University) was already one of the more advanced cloud motion systems, which is the reason that team was brought to this project. During the project timeframe, the CIRA team was able to advance cloud shadowing, parallax removal, and implementation of better advecting winds at different altitudes. CIRACast shows generally a 25-40% improvement over Smart Persistence between sunrise and approximately 1600 UTC (Coordinated Universal Time) . A second satellite-based system, MADCast (Multi-sensor Advective Diffusive foreCast system), assimilates data from multiple satellite imagers and profilers to assimilate a fully three-dimensional picture of the cloud into the dynamic core of WRF. During 2015, MADCast (provided at least 70% improvement over Smart Persistence, with most of that skill being derived during partly cloudy conditions. That allows advection of the clouds via the Weather Research and Forecasting (WRF) model dynamics directly. After WRF-Solar™ showed initial success, it was also deployed in nowcasting mode with coarser runs out to 6 hours made hourly. It provided improvements on the order of 50-60% over Smart Persistence for forecasts up to 1600 UTC. The advantages of WRF-Solar-Nowcasting and MADCast were then blended to develop the new MAD-WRF model that incorporates the most important features of each of those models, both assimilating satellite cloud fields and using WRF-So far physics to develop and dissipate clouds. MAE improvements for MAD-WRF for forecasts from 3-6 hours are improved over WRF-Solar-Now by 20%. While all the Nowcasting system components by themselves provide improvement over Smart Persistence, the largest benefit is derived when they are smartly blended together by the Nowcasting Integrator to produce an integrated forecast. The development of WRF-Solar™ under this project has provided the first numerical weather prediction (NWP) model specifically designed to meet the needs of irradiance forecasting. The first augmentation improved the solar tracking algorithm to account for deviations associated with the eccentricity of the Earth’s orbit and the obliquity of the Earth. Second, WRF-Solar™ added the direct normal irradiance (DNI) and diffuse (DIF) components from the radiation parameterization to the model output. Third, efficient parameterizations were implemented to either interpolate the irradiance in between calls to the expensive radiative transfer parameterization, or to use a fast radiative transfer code that avoids computing three-dimensional heating rates but provides the surface irradiance. Fourth, a new parameterization was developed to improve the representation of absorption and scattering of radiation by aerosols (aerosol direct effect). A fifth advance is that the aerosols now interact with the cloud microphysics, altering the cloud evolution and radiative properties, an effect that has been traditionally only implemented in atmospheric computationally costly chemistry models. A sixth development accounts for the feedbacks that sub-grid scale clouds produce in shortwave irradiance as implemented in a shallow cumulus parameterization Finally, WRF-Solar™ also allows assimilation of infrared irradiances from satellites to determine the three dimensional cloud field, allowing for an improved initialization of the cloud field that increases the performance of short-range forecasts. We find that WRF-Solar™ can improve clear sky irradiance prediction by 15-80% over a standard version of WRF, depending on location and cloud conditions. In a formal comparison to the NAM baseline, WRF-Solar™ showed improvements in the Day-Ahead forecast of 22-42%. The SunCast™ system requires substantial software engineering to blend all of the new model components as well as existing publically available NWP model runs. To do this we use an expert system for the Nowcasting blender and the Dynamic Integrated foreCast (DICast®) system for the NWP models. These two systems are then blended, we use an empirical power conversion method to convert the irradiance predictions to power, then apply an analog ensemble (AnEn) approach to further tune the forecast as well as to estimate its uncertainty. The AnEn module decreased RMSE (root mean squared error) by 17% over the blended SunCast™ power forecasts and provided skill in the probabilistic forecast with a Brier Skill Score of 0.55. In addition, we have also developed a Gridded Atmospheric Forecast System (GRAFS) in parallel, leveraging cost share funds. An economic evaluation based on Production Cost Modeling in the Public Service Company of Colorado showed that the observed 50% improvement in forecast accuracy will save their customers $819,200 with the projected MW deployment for 2024. Using econometrics, NCAR has scaled this savings to a national level and shown that an annual expected savings for this 50% forecast error reduction ranges from $11M in 2015 to $43M expected in 2040 with increased solar deployment. This amounts to a $455M discounted savings over the 26 year period of analysis.

14 SOLAR ENERGY↗

Ten questions concerning Large Language Models (LLMs) for building applications

Large Language Models (LLMs) are emerging as powerful AI tools capable of transforming how building information is collected, processed, analyzed, and applied across diverse research areas. Their capabilities can help building operators, facility managers and other stakeholders such as designers, architects and engineers by providing actionable insights for decision-making across planning, construction, operations, and maintenance of buildings and facilities. This paper explores ten key questions concerning the role of LLMs in shaping sustainable, intelligent, and human-centric buildings. From fundamental definitions to advanced applications, we examine how LLMs facilitate decision-making across the life cycle of buildings and energy systems. LLMs can enhance life cycle assessments (LCA), building energy simulations, and real-time data integration, empowering more efficient and adaptive human-AI environments. They can also contribute to streamlining regulatory compliance, improving post-occupancy evaluations, and fostering more inclusive and participatory design processes. Additionally, this paper addresses the ethical challenges posed by LLMs, such as bias, data privacy, and environmental impacts, and explores their potentials in advancing intelligent digital twins (DT) for ongoing building operations and maintenance. Built upon our applied research using LLMs and the review of tools, datasets, and research gaps, we provide a forward-looking perspective on how LLMs can drive innovation, collaboration, and productivity in the built environment while supporting ethical and effective implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Searching for pulsars using image pattern recognition

In the modern era of big data, many fields of astronomy are generating huge volumes of data, the analysis of which can sometimes be the limiting factor in research. Fortunately, computer scientists have developed powerful data-mining techniques that can be applied to various fields. In this paper, we present a novel artificial intelligence (AI) program that identifies pulsars from recent surveys by using image pattern recognition with deep neural nets—the PICS (Pulsar Image-based Classification System) AI. The AI mimics human experts and distinguishes pulsars from noise and interference by looking for patterns from candidate plots. Different from other pulsar selection programs that search for expected patterns, the PICS AI is taught the salient features of different pulsars from a set of human-labeled candidates through machine learning. The training candidates are collected from the Pulsar Arecibo L-band Feed Array (PALFA) survey. The information from each pulsar candidate is synthesized in four diagnostic plots, which consist of image data with up to thousands of pixels. The AI takes these data from each candidate as its input and uses thousands of such candidates to train its ∼9000 neurons. The deep neural networks in this AI system grant it superior ability to recognize various types of pulsars as well as their harmonic signals. The trained AI's performance has been validated with a large set of candidates from a different pulsar survey, the Green Bank North Celestial Cap survey. In this completely independent test, the PICS ranked 264 out of 277 pulsar-related candidates, including all 56 previously known pulsars and 208 of their harmonics, in the top 961 (1%) of 90,008 test candidates, missing only 13 harmonics. The first non-pulsar candidate appears at rank 187, following 45 pulsars and 141 harmonics. In other words, 100% of the pulsars were ranked in the top 1% of all candidates, while 80% were ranked higher than any noise or interference. The performance of this system can be improved over time as more training data are accumulated. This AI system has been integrated into the PALFA survey pipeline and has discovered six new pulsars to date.

79 ASTRONOMY AND ASTROPHYSICS↗

Green AI: Insights Into Deep Learning's Looming Energy Efficiency Crisis

As demands grow to integrate artificial intelligence into every aspect of industry, commerce, and life, deep learning's exploding energy cost has become a looming crisis, making AI systems a salient energy-efficiency challenge. One might expect that doubling a neural network's size would halve its error rate, or at least allow it to achieve greater performance given the same amount of time and energy. I will present clear and substantial scientific evidence which indicates that not only is this intuition wildly wrong, but that neural networks scale so poorly that to increase deep learning performance by only a small fraction can easily require an order of magnitude or more increase in computational resources and energy. Further, the marginal trade-off price of to increase model performance rapidly explodes as performance targets are increased. To address this challenge, I will provide a toolkit of techniques that can be applied today to mitigate the inefficiency of modern deep learning. And, I will conclude by illuminating a practical path forward towards efficient, Green AI.

artificial intelligence↗