Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “resource optimization”

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 937 records · Page 52

Adaptive Computing and Multi-Fidelity Learning

We describe our ongoing research in adaptive computing. Our goal is to use a combination of low- and high-fidelity simulation models to enable computationally efficient optimization and uncertainty quantification. We develop optimization formulations that take into account the compute resources currently available, which act as a constraint with regards to the fidelity level simulation we can run while maximizing information gain. We will discuss a few application examples that can benefit from this approach, especially when considering challenges arising in scaling up experiments and simulations.

97 MATHEMATICS AND COMPUTING↗

OPTICHEM (OPTimizer for Industrial CHEMical pathways) [SWR-25-70]

Using alternative feedstocks such as biomass and waste could help the chemical sector address growing challenges from supply chain disruptions. This project aims to identify optimal combinations of chemical production pathways that achieve user-defined priorities within set resource constraints. This project contains two main Python modules that work together to perform multi-objective optimization of feedstock usage and post-optimization analysis. The outputs from both modules (e.g., CSV files, PDF diagrams, HTML reports, and pickle files) are automatically saved in dedicated output folders. The folder names include key parameters such as the optimization metric, target year, and whether 2030 results are fixed.

Ghosh, Tapajyoti [National Renewable Energy Labora↗

Final Report for ARPA-E NODES "Real-Time Optimization and Control of Next-Generation Distribution Infrastructure" Project

The project examined next-generation power distribution systems with high levels of power- electronics-interfaced distributed energy resources (DERs) that include: renewable energy systems (RESs), energy-storage devices, electric vehicles, fuel cells, small-scale diesel generators, and controllable loads. The project developed a comprehensive distribution- network management framework that unifies real-time voltage and frequency control with network-wide energy management under an integrated framework. The aim of the project was to: i) systematically optimize network-wide operation and congruently regulate voltages and frequency in the face of high volatility induced by rapidly varying RES and uncontrolled loads; ii) facilitate high renewable integration beyond 50% on an energy basis; iii) meet power-quality requirements and operational constraints; and, iv) respect response, ramp- time, and hold-time requirements for synthetic frequency and regulating reserves via fast- and longer-term dynamic energy management.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Evaluating adaptive and predictive power management strategies for optimizing visualization performance on supercomputers

Power is becoming an increasingly scarce resource on the next generation of supercomputers, and should be used wisely to improve overall performance. One strategy for improving power usage is hardware overprovisioning, i.e., systems with more nodes than can be run at full power simultaneously without exceeding the system-wide power limit. With this study, we compare two strategies for allocating power throughout an overprovisioned system – adaptation and prediction – in the context of visualization workloads. While adaptation has been suitable for workloads with more regular execution behaviors, it may not be as suitable on visualization workloads, since they can have variable execution behaviors. This study considers a total of 104 experiments, which vary the rendering workload, power budget, allocation strategy, and node concurrency, including tests processing data sets up to 1 billion cells and using up to 18,432 cores across 512 nodes. Overall, we find that prediction is a superior strategy for this use case, improving performance up to 27% compared to an adaptive strategy.

97 MATHEMATICS AND COMPUTING↗

Hybrid Energy Resources Bidding Model (HERB) v1.0

The HERB Model provides a stochastic optimization framework for hybrid power plants (Storage plus Renewables) participating in day-ahead electricity markets. It considers uncertainty in market prices and renewable energy generation and generated risk-constrained price-quantity bid curves with limited, non-decreasing price steps.

Heleno, Miguel [Lawrence Berkeley National Laborat↗

An assessment of flexibility reserves in stochastic modeling at multiple timescales

Due to recent technological achievements, stochastic optimization, which inherently captures the uncertainty of intermittent resources, is being used to capture the variability and uncertainty of wind and solar resources. However, due to persistent computational limitations, it is not practical to consider all possible variable generation scenarios. As a result, a reduced number of most likely scenarios is usually considered. While this helps reduce the computational burden, it also leaves the system operator vulnerable to some risk. In order to address this issue, this paper aims at providing insight into using an explicit reserve requirement in a stochastic modeling framework in order to provide system operators with greater confidence in stochastic dispatch solutions. This is accomplished by simulating a modified version of the IEEE 118 bus system in a fully stochastic, multi-timescale framework with flexibility reserve requirements. Results show that utilizing a stochastic flexibility reserve requirement within the stochastic modeling framework offers the most reliability benefit.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Revenue estimation for integrated renewable energy and energy storage systems is important to support plant owners or operators’ decisions in battery sizing selection that leads to maximized financial performances. A common approach to optimizing revenues of a hybrid hydro and energy storage system is using mixed-integer linear programming (MILP). Although MILP models can provide accurate production cost estimations, they are typically very computationally expensive. To provide a fast yet accurate first-step information to hydropower plant owners or operators who consider integrating energy storage systems, we propose an innovative approach to predicting optimal revenues of an integrated energy generation and storage system. In this study, we examined the performance of two prediction techniques: Generalized Additive Models (GAMs) and machine learning (ML) models developed based on artificial neural networks (ANN). Predictive equations and models are generated based on optimized solutions from a market participation optimization model, the Conventional Hydropower Energy and Environmental Resource System (CHEERS) model. The two predicting techniques reduce the computational time to evaluate annual revenue for one set of battery configurations from 3 h to 1 to 4 min per run while also being implementable with significantly less data. The model validation prediction errors of developed GAMs and ML models are generally below 5%; for model testing predictions, the ML models consistently outperform the regression equations in terms of root mean square errors. This new approach allows plant owners, operators, or potential investors to quickly access multiple battery configurations under different energy generation and market scenarios. This new revenue prediction method will therefore help reduce the barriers, and thereby promoting the deployment of battery hybridization with existing renewable energy sources.

13 HYDRO ENERGY↗

A systems engineering framework for the optimization of food supply chains under circular economy considerations

The current linear “take-make-waste-extractive” model leads to the depletion of natural resources and environmental degradation. Circular Economy (CE) aims to address these impacts by building supply chains that are restorative, regenerative, and environmentally benign. This can be achieved through the re-utilization of products and materials, the extensive usage of renewable energy sources, and ultimately by closing any open material loops. Such a transition towards environmental, economic and social advancements requires analytical tools for quantitative evaluation of the alternative pathways. Here, in this work, we present a novel CE system engineering framework and decision-making tool for the modeling and optimization of food supply chains. First, the alternative pathways for the production of the desired product and the valorization of wastes and by-products are identified. Then, a Resource-Task-Network representation that captures all these pathways is utilized, based on which a mixed-integer linear programming model is developed. This approach allows the holistic modeling and optimization of the entire food supply chain, taking into account any of its special characteristics, potential constraints as well as different objectives. Considering that typically CE introduces multiple, often conflicting objectives, we deploy here a multi-objective optimization strategy for trade-off analysis. A representative case study for the supply chain of coffee is discussed, illustrating the steps and the applicability of the framework. Single and multi-objective optimization formulations under five different coffee-product demand scenarios are presented. The production of instant coffee as the only final product is shown to be the least energy and environmental efficient scenario. On the contrary, the production solely of whole beans sets a hypothetical upper bound on the optimal energy and environmental utilization. In both problems presented, the amount of energy generated is significant due to the utilization of waste generated for the production of excess energy.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

On Distribution Grid Optimal Power Flow Development and Integration

Due to changes in electric distribution grid operation, new operation regimes have been recommended. Distribution grid optimal power flow (DOPF) has received tremendous attention in the research community, yet it has not been fully adopted across the utility industry. Our paper recognizes this problem and suggests a development and integration procedure for DOPF. We propose development of DOPF as a three step procedure of 1) processing the grid, 2) obtaining a tractable solution, and 3) implementing multiple solution algorithms and benchmarking them to improve application reliability. For the integration of DOPF, we demonstrate how a DOPF federate may be developed that can be integrated in a co-simulation environment to mimic the real-world conditions and hence improve its practicality to be deployed in the field. To demonstrate the efficacy of the proposed methods, tests on IEEE 123 bus system are performed where the usage of tractable formulation in DOPF algorithm development and its comparison to the benchmark solution are demonstrated.

Hanif, Sarmad↗

iez: Resource Contention Aware Load Balancing for Large-Scale Parallel File Systems

Parallel I/O performance is crucial to sustaining scientific applications on large-scale High-Performance Computing (HPC) systems. However, I/O load imbalance in the underlying distributed and shared storage systems can significantly reduce overall application performance. There are two conflicting challenges to mitigate this load imbalance: (i) optimizing systemwide data placement to maximize the bandwidth advantages of distributed storage servers, i.e., allocating I/O resources efficiently across applications and job runs; and (ii) optimizing client-centric data movement to minimize I/O load request latency between clients and servers, i.e., allocating I/O resources efficiently in service to a single application and job run. Moreover, existing approaches that require application changes limit wide-spread adoption in commercial or proprietary deployments. We propose iez, an “end-to-end control plane” where clients transparently and adaptively write to a set of selected I/O servers to achieve balanced data placement. Our control plane leverages realtime load information for distributed storage server global data placement while our design model leverages trace-based optimization techniques to minimize I/O load request latency between clients and servers. We evaluate our proposed system on an experimental cluster for two common use cases: synthetic I/O benchmark IOR for large sequential writes and a scientific application I/O kernel, HACC-I/O. Results show read and write performance improvements of up to 34% and 32%, respectively, compared to the state of the art.

Wadhwa, Bharti↗

A Quantitative Study of Deep Learning Training on Heterogeneous Supercomputers

Deep learning (DL) has become a key technique for solving complex problems in scientific research and discovery. DL training for science is substantially challenging because it has to deal with massive quantities of multi-dimensional data. High- performance computing (HPC) supercomputers are increasingly being employed for meeting the exponentially growing demand for DL. Multiple GPUs and high-speed interconnect network are needed for supporting DL on HPC systems. However, the excessive use of GPUs without considering effective benefits leads to inefficient resource utilization of these expensive setups. In this paper, we conduct a quantitative analysis to gauge the efficacy of DL workloads on the latest HPC system and identify viability of next-generation DL-optimized heterogeneous supercomputers for enabling researchers to develop more efficient resource management and distributed DL middleware. We evaluate well- known DL models with large-scale datasets using the popular TensorFlow framework, and provide a thorough evaluation in- cluding scalability, accuracy, variability, storage resource, GPU- GPU/GPU-CPU data transfer, and GPU utilization. Our analysis reveals that the latest heterogeneous supercomputing cluster shows varying performance trend as compared to the existing literature for single- and multi-node training. To the best of our knowledge, this is the first work to conduct such a quantitative and comprehensive study of DL training on a supercomputing system with multiple GPUs.

Han, Jingoo↗

A two-stage service restoration method for electric power distribution systems

Improving the reliability of power distribution systems is critically important for both utilities and customers. This calls for an efficient service restoration module within a distribution management system to support the implementation of self-healing smart grid networks. Although the emerging smart grid technologies, including distributed generators (DGs) and remote-controlled switches, enhance the self-healing capability and allow faster recovery, they still pose additional complexity to the service restoration problem, especially under cold load pickup (CLPU) conditions. Herein, a novel two-stage restoration framework is proposed to generate a restoration solutions with a sequence of control actions. The first stage generates a restoration plan that supports both the traditional service restoration using feeder reconfiguration and the grid-forming DG-assisted intentional islanding methods. The second stage generates an optimal sequence of switching operations to bring the outaged system quickly to the final restored configuration. The problem is formulated as a mixed-integer linear program that incorporates system connectivity, operating constraints, and the CLPU models. It is demonstrated that on using a multi-feeder test case, the proposed framework is effective in utilizing all available resources to quickly restore the service and generate an optimal sequence of switching actions to be used by the operator to reach the desired optimal configuration.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Urban-Scale Control of School Bus Fleet Charging and Discharging Strategies Using Single and Multi-Stage Optimization

This paper presents a dual-strategy approach to optimizing charging and discharging schedules for school bus fleets, using the limited charging infrastructure effectively. We aim to ensure that each bus is fully charged for daily operations and aids in grid stability during peak demand. The first strategy utilizes linear programming to schedule overnight charging at available station sockets and strategic discharging during peak periods, efficiently coordinating limited resources. The second strategy employs metaheuristic techniques for continuous optimization, focusing on precise power requirements and offering greater flexibility than the linear model.

Selim, Alaa↗

Regional Analysis of Building Distributed Energy Costs and CO2 Abatement: A U.S. - China Comparison

The following paper conducts a regional analysis of the U.S. and Chinese buildings? potential for adopting Distributed Energy Resources (DER). The expected economics of DER in 2020-2025 is modeled for a commercial and a multi-family residential building in different climate zones. The optimal building energy economic performance is calculated using the Distributed Energy Resources Customer Adoption Model (DER CAM) which minimizes building energy costs for a typical reference year of operation. Several DER such as combined heat and power (CHP) units, photovoltaics, and battery storage are considered. The results indicate DER have economic and environmental competitiveness potential, especially for commercial buildings in hot and cold climates of both countries. In the U.S., the average expected energy cost savings in commercial buildings from DER CAM?s suggested investments is 17percent, while in Chinese buildings is 12percent. The electricity tariffs structure and prices along with the cost of natural gas, represent important factors in determining adoption of DER, more so than climate. High energy pricing spark spreads lead to increased economic attractiveness of DER. The average emissions reduction in commercial buildings is 19percent in the U.S. as a result of significant investments in PV, whereas in China, it is 20percent and driven by investments in CHP. Keywords: Building Modeling and Simulation, Distributed Energy Resources (DER), Energy Efficiency, Combined Heat and Power (CHP), CO2 emissions 1. Introduction The transition from a centralized and fossil-based energy paradigm towards the decentralization of energy supply and distribution has been a major subject of research over the past two decades. Various concerns have brought the traditional model into question; namely its environmental footprint, its structural inflexibility and inefficiency, and more recently, its inability to maintain acceptable reliability of supply. Under such a troubled setting, distributed energy resources (DER) comprising of small, modular, electrical renewable or fossil-based electricity generation units placed at or near the point of energy consumption, has gained much attention as a viable alternative or addition to the current energy system. In 2010, China consumed about 30percent of its primary energy in the buildings sector, leading the country to pay great attention to DER development and its applications in buildings. During the 11th Five Year Plan (FYP), China has implemented 371 renewable energy building demonstration projects, and 210 photovoltaics (PV) building integration projects. At the end of the 12th FYP, China is targeting renewable energy to provide 10percent of total building energy, and to save 30 metric tons of CO2 equivalents (mtce) of energy with building integrated renewables. China is also planning to implement one thousand natural gas-based distributed cogeneration demonstration projects with energy utilization rates over 70percent in the 12th FYP. All these policy targets require significant DER systems development for building applications. China?s fast urbanization makes building energy efficiency a crucial economic issue; however, only limited studies have been done that examine how to design and select suitable building energy technologies in its different regions. In the U.S., buildings consumed 40percent of the total primary energy in 2010 [1] and it is estimated that about 14 billion m2 of floor space of the existing building stock will be remodeled over the next 30 years. Most building?s renovation work has been on building envelope, lighting and HVAC systems. Although interest has emerged, less attention is being paid to DER for buildings. This context has created opportunities for research, development and progressive deployment of DER, due to its potential to combine the production of power and heat (CHP) near the point of consumption and delivering multiple benefits to customers, such as cost

25 ENERGY STORAGE↗

NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

28 NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning: Preprint

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

Optimizing DER Deployment for Climate, Health, Resilience, and Energy Bill Benefits Using the REopt Model

Climate change, public health, and resilience to power outages are of critical concern to local governments, federal agencies, and the private sector, and are increasingly motivating investments in distributed energy resources (DERs). However, designing a solar-plus-storage system to co-optimize for climate, health, resilience, and energy bill benefits requires complex trade-offs. To address this need, the National Renewable Energy Laboratory has integrated climate and health impacts of grid-purchased electricity and on-site fuel consumption into the publicly-available REopt web tool and API - a techno-economic model that determines the cost-optimal DER system sizes and dispatch strategy. This presentation will provide an overview of the tool's methodology, datasets, and capabilities, including costing emissions into system sizing and dispatch and setting emissions reductions targets. Results of previous work will demonstrate the use of new emissions accounting capabilities by quantifying the impact of including climate and health costs on the optimal resilient microgrid configurations for a hospital, school, and warehouse across 14 U.S. cities.

climate↗

Application of Site Controllers for Electrification of Commercial Fleet Vehicles

Electrification of transportation fleets presents a significant challenge for commercial customers. These challenges can be specific to region, weather, operating schedule, charging infrastructure, and other factors. This paper presents the value of integrating a site controller to monitor the health of assets and co-optimize the operation of commercial sites with multiple distributed energy resource technologies and electric vehicle fleets. The tests demonstrate smart-charging and vehicle-to-building uses compared to business-as-usual cases. The secondary objectives of power management for the customer vehicle are optimized by a planning tool (REopt) and integrated using the site controller. Any deviations from the planned dispatch are addressed by the real-time controllers offering tertiary controls, such as energy management, and limiting the reverse power flow (back into the grid). The results indicate that site controllers offer an efficient solution to manage the health of the connected assets and a scalable means to optimize the operations of a commercial customer with electrified transportation fleets.

ADVANCED PROPULSION SYSTEMS,POWER TRANSMISSION AND↗