Search NASA⌕ Search

SEARCH · Search NASA

Results for “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 613 records · Page 34

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↗

Preemptive resource management for dynamically arriving tasks in an oversubscribed heterogeneous computing system

We design resource management heuristics that assign serial tasks to the nodes of a heterogeneous high performance computing (HPC) system. The value of completing these tasks is modeled using monotonically decreasing utility functions that represent the time-varying importance of the task. The value of completing a task is equal to its utility function at the time of its completion. The overall performance of this system is measured using the total utility earned by all tasks during some interval of time. To maximize the performance of such a system where the preemption of tasks is possible, we have designed, analyzed, and compared a set of resource allocation heuristic techniques. We combine two utility-aware heuristics with three different preemption techniques to create six preemption-capable heuristics. We also consider the two utility-aware heuristics without preemption. We use simulation studies to evaluate this set of eight heuristics and compare them with an FCFS heuristic, which is often used in real systems, and random assignments. In general, our set of eight heuristics is able to significantly outperform the comparison heuristics, and the preemption-capable heuristics are able to significantly increase the utility earned compared to the heuristics that do not use preemption. We analyze the performance tradeoffs among the different preemption-capable heuristics under a variety of oversubscribed workload environments.

97 MATHEMATICS AND COMPUTING↗

Implementing the OpenACC Data Model

Programming accelerators today usually requires managing separate virtual and physical memories, such as allocating space in and copying data between host and device memories. The OpenACC API provides data directives and clauses to control this behavior where it is required. This paper describes how the data model is supported in current OpenACC implementations, ranging from research compilers (OpenUH and OpenARC) to a commercial compiler (the PGI OpenACC compiler). This includes implementation of the data directives and clauses, testing whether the data is already present on the device, OpenCL support, managing asynchronous data transfers and memory allocations, handling aliased data, reusing device memory, managing partially present data, and support for shared memory between host and device. Lastly, it also discusses on-going work to manage large, complex dynamic data structures.

Wolfe, Michael↗

Adaptive Computing for Scale-Up Problems

Adaptive Computing is an application-agnostic outer loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the allocation adaptive to some objective such as optimization or model training. The framework enables the characterization and management of uncertainties associated with predictive models of complex systems when scale-up questions lead to significant model extrapolation. A key advancement of this framework is its integration of multi-fidelity surrogate modeling, uncertainty management, and automated orchestration of various computing and experimentation resources into a single integrated software package. This enables efficient multi-fidelity modeling across multiple computing resources by incorporating real-world constraints such as relative queue times and throughput on individual machines into the multi-fidelity sampling decision. We discuss applications of this framework to problems in the renewable energy space, including biofuels production, material synthesis, perovskite crystal growth, and building electrical loads.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Post-Disturbance Dynamic Distribution System Restoration with DGs and Mobile Resources

Distributed generations (DGs) can act as emergency power supplies when distribution systems suffer from outages. However, the generation capabilities of DGs are generally limited by a number of factors including weather conditions, fuel limitations, etc. In this context, mobile resources that are able to reallocate resources to desired locations are regarded as important complements to conventional fixed DGs in assisting distribution system restoration. In this paper, a distribution system restoration model with DGs and mobile resources is proposed. Firstly, the dispatch and allocation of mobile resources are modeled with respect to the characteristics of the traffic network. Then the developed mobile resource models are integrated into the distribution system restoration model to co-optimize the scheduling of DGs and mobile resources. Uncertainty factors are managed by a model predictive control approach so that system operators can dynamically adjust the restoration strategy with the up-to-date information. The effectiveness of the proposed method is validated through an IEEE 13-bus test system.

distributed generations (DGs)↗

A Fast and Scalable Genetic Algorithm-Based Approach for Planning of Microgrids in Distribution Networks

As a result of climate change, extreme weather events are occurring more frequently and with increasing impact. This trend poses a significant challenge for distribution utilities and system operators to ensure that there is uninterrupted power supply to critical loads in their networks; thus, the level of proactive preparation of the distribution system to be able to handle severe impacts of extreme weather events represents the system's resilience. One method that distribution system planners can use to prepare for future extreme events is to plan multiple microgrids which can use local generation as much as possible to supply critical loads. But partitioning an existing distribution system such that multiple feasible islands are planned and which are capable of supporting critical loads is still challenging for distribution systems - first, because of the size of the network graph partitioning problem and, second, because of the difficulty in properly formulating the desired attributes of such islands or microgrids. Therefore, this paper presents a genetic algorithm based approach that facilitates incorporating multiple objectives for grid partitioning by formulating two types of problems - node allocation and edge elimination - and it considers multiple topological and resilience-enhancing objectives. The performance of the proposed genetic algorithm-based approach is numerically evaluated on multiple test systems as well as on a real distribution feeder in Colorado, United States.

genetic algorithm↗

A Model for Hybrid Systems for Production Cost Modeling Studies Considering Ancillary Services

This paper introduces a model for simulating hybrid plants participating in energy and ancillary services for bulk power system studies. The model considers a hybrid plant comprised of a renewable energy source, a thermal power unit, a storage unit, fixed power loads, or any combination of these technologies. The model focuses on Production Cost Modeling (PCM) studies under the assumption of centralized dispatch. We present an example case study to illustrate the use of the model in a single-stage production cost model similar to those conducted by planning agencies. We explore the allocation of behind-the-meter ancillary services products and total energy participation to hybrid plant sub-assets and the resulting impacts on the system's ancillary service allocation. The model is implemented and simulated in a unit commitment problem in the RTS test system, which was modified to include a hybrid plant asset.

ancillary services↗

Mapping to Irregular Torus Topologies and Other Techniques for Petascale Biomolecular Simulation, In: SC '14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

Currently deployed petascale supercomputers typically use toroidal network topologies in three or more dimensions. While these networks perform well for topology-agnostic codes on a few thousand nodes, leadership machines with 20,000 nodes require topology awareness to avoid network contention for communication-intensive codes. Topology adaptation is complicated by irregular node allocation shapes and holes due to dedicated input/output nodes or hardware failure. In the context of the popular molecular dynamics program NAMD, we present methods for mapping a periodic 3-D grid of fixed-size spatial decomposition domains to 3-D Cray Gemini and 5-D IBM Blue Gene/Q toroidal networks to enable hundred-million atom full machine simulations, and to similarly partition node allocations into compact domains for smaller simulations using multiple copy algorithms. Additional enabling techniques are discussed and performance is reported for NCSA Blue Waters, ORNL Titan, ANL Mira, TACC Stampede, and NERSC Edison.

Computer Science↗

Utility functions and resource management in an oversubscribed heterogeneous computing environment

We model an oversubscribed heterogeneous computing system where tasks arrive dynamically and a scheduler maps the tasks to machines for execution. The environment and workloads are based on those being investigated by the Extreme Scale Systems Center at Oak Ridge National Laboratory. Utility functions that are designed based on specifications from the system owner and users are used to create a metric for the performance of resource allocation heuristics. Each task has a time-varying utility (importance) that the enterprise will earn based on when the task successfully completes execution. We design multiple heuristics, which include a technique to drop low utility-earning tasks, to maximize the total utility that can be earned by completing tasks. The heuristics are evaluated using simulation experiments with two levels of oversubscription. The results show the benefit of having fast heuristics that account for the importance of a task and the heterogeneity of the environment when making allocation decisions in an oversubscribed environment. Furthermore, the ability to drop low utility-earning tasks allow the heuristics to tolerate the high oversubscription as well as earn significant utility.

97 MATHEMATICS AND COMPUTING↗

A Transactive Network Template for Decentralized Coordination of Electricity Provision and Value

Transactive energy systems facilitate and plan for an allocation of electricity based on distributed, value-based negotiations. They are currently extending the usage of market-based principles and transactions from wholesale electricity markets where they exist today downward into distribution systems. While many interesting transactive energy systems have been proposed, few fully decentralize price discovery and price-responsive control. Even fewer plan for extensibility that will be needed for the ultimate growth of transactive networks and for the inclusion of additional and new objectives and new flexible, responsive assets. This paper introduces a transactive network template from which an agent may be configured at its network node to negotiate for electricity with other neighboring network agents, manage a set of locally-owned supply and demand assets, and induce local power balance through price discovery. A set of base object classes defines the template and may be extended. Three important basic computational responsibilities are allocated among the base object classes—scheduling, balancing, and network coordination. These several basic classes and responsibilities may be used to represent the perspective of large and small devices and regions anywhere in the electric power grid because they are based on the self-similarity of these objects and responsibilities. Agents in a transactive network are not at all unique in these basic responsibilities. So far, these following dynamic values have been addressed by extension of the base classes: energy value, demand charges, transport losses, and impacts of distributed renewable resources. The template is designed to be further extended to address and monetize still other valuable objectives.

Transactive, Transactive network, Transactive netw↗

Techno-Economic Analysis of Data-Driven and Transactive Approaches for Resilience Enhancement

As extreme weather events lead to more frequent power outages, understanding and enhancing grid resilience is critical to mitigating economic losses and non-energy impacts from service disruptions. Here, this study introduces a novel techno-economic analysis framework for evaluating resilience enhancement mechanisms. The framework combines grid response modeling with a co-simulation approach and valuation methodology to provide a comprehensive assessment. We apply this framework to a realistic case study of the Texas grid during Winter Storm Uri in February 2021. Two advanced resilience strategies are analyzed: a data-driven rolling outage mechanism and a transactive energy (TE) based allocation scheme. The rolling outage scheme selectively serves customers based on real-time curtailment needs, while the TE scheme allows customers to trade energy allocations according to their preferences. Our findings show that both the rolling outage and TE schemes significantly outperform conventional methods (i.e. controlled outages) by reducing the amount of energy not supplied to customers by 41% and 64%, respectively. These approaches also enhance flexibility and customer satisfaction, while improving energy utilization for greater resilience. Additionally, they maintain thermal comfort about 3.5 times better and substantially lower customer risk exposure. A key contribution of this study is addressing both utility and customer perspectives while considering both energy and non-energy impacts. The techno-economic analysis indicates that implementing these resilience enhancement strategies would incur an additional 1.1Bto1.6B in utility costs but has the potential to avoid 17.3Bto18B of customer losses as compared to existing solutions, thereby underscoring the value of investing in advanced resilience, as it provides significant societal benefits to customers.

42 ENGINEERING↗

Adaptive Protection of Scientific Backbone Networks Using Machine Learning

In this article, we propose a new protection scheme for backbone networks to guarantee high service availability. The presented scheme does not require any reconfiguration immediately after the failure (i.e., it is proactive). At the same time, it does not require any reserved backup network resources either. To achieve these seemingly contradictory goals, we utilize the recent advancements in Machine Learning (ML) to implement a network intelligence that periodically re-allocates the unused capacity as protection bandwidth to meet the service availability requirements of each connection. Our goal is achieved by two components (1) predicting the traffic for the next period on each link, and (2) intelligently selecting the best fit dedicated protection scheme for the next period depending on the estimated unused (spare) bandwidth and the previous service availability violations. Note that re-allocating protection bandwidth affects neither the operational connections nor the current best practice of operators to over-provision network bandwidth to support elephant flows. Finally, we provide a case study on the real traffic from Energy Sciences Network (ESnet), a high-speed, international scientific backbone network. The key benefit of our framework is that adaptively utilizing the over-provisioned bandwidth for spare capacity is sufficient to improve the availability from three-nines to five-nines (in ESnet for the 30 examined connections). The drawback is negligible bandwidth limitations; the user perceives a minor and very temporal bandwidth limitation in less than 0.1% of the time.

42 ENGINEERING↗

Rapid Calculation of Max-Min Fair Rates for Multi-Commodity Flows in Fat-Tree Networks

Max-min fairness is often used in the performance modeling of interconnection networks. Existing methods to compute max-min fair rates for multi-commodity flows have high complexity and are computationally infeasible for large networks. In this paper, we show that by considering topological features, this problem can be solved efficiently for the fat-tree topology that is widely used in data centers and high performance compute clusters. Several efficient new algorithms are developed for this problem, including a parallel algorithm that can take advantage of multi-core and shared-memory architectures. Using these algorithms, we demonstrate that it is possible to find the max-min fair rate allocation for multi-commodity flows in fat-tree networks that support tens of thousands of nodes. We evaluate the run-time performance of the proposed algorithms and show improvement in orders of magnitude over the previously best known method. Finally, we further demonstrate a new application of max-min fair rate allocation that is only computationally feasible using our new algorithms.

97 MATHEMATICS AND COMPUTING↗

Dual pricing algorithm in ISO markets

The challenge to create efficient market clearing prices in centralized day-ahead electricity markets arises from inherent non-convexities in unit commitment problems. When this aspect is ignored, marginal prices may result in economic losses to market participants who are part of the welfare maximizing solution. In this essay, we present an axiomatic approach to efficient prices and cost allocation for a revenue neutral and non-confiscatory day-ahead market. Current cost allocation practices do not adequately attribute costs based on transparent cost causation criteria. Instead we propose an ex post multi-part pricing scheme, which we refer to as the Dual Pricing Algorithm. Lastly, our approach can be incorporated into current dayahead markets without altering the market equilibrium.

97 MATHEMATICS AND COMPUTING↗

A Real-Time Greedy-Index Dispatching Policy for using PEVs to Provide Frequency Regulation Service

This article presents a real-time greedy-index dispatching policy (GIDP) for using plug-in electric vehicles (PEVs) to provide frequency regulation services. A new service cost allocation mechanism is proposed to award PEVs based on the amount of service they provided, while considering compensations for delayed-charging and reduction of battery lifetime due to participation of the service. The GIDP transforms the optimal dispatch problem from a high-dimensional space into a one-dimensional space while preserving the solution optimality. When solving the transformed problem in real-time, the global optimality of the GIDP solution can be guaranteed by mathematically proved “indexability”. Because the GIDP index can be calculated upon the PEV’s arrival and used for the entire decision making process till its departure, the computational burden is minimized and the complexity of the aggregator dispatch process is significantly reduced. Finally, simulation results are used to evaluate the proposed GIDP, and to demonstrate the potential profitability from providing frequency regulation service by using PEVs.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

A Data-Driven Pivot-Point-Based Time-Series Feeder Load Disaggregation Method

The load profile at a feeder-head is usually known to utility engineers while the nodal load profiles are not. However, the nodal load profiles are increasingly important for conducting time-series analysis in distribution systems. Therefore, in this paper, we present a pivot-point based, two-stage feeder load disaggregation algorithm using smart meter data. The two stages are load profile selection (LPS) and load profile allocation (LPA). In the LPS stage, a random load profile selection process is first executed to meet the load diversity requirement. Then, a few pairs of pivot points are selected as the matching targets. After that, a matching algorithm will run repetitively to select one load profile at a time for matching the reference load profile at the pivot points. In the LPA stage, the LPS selected load profiles are allocated to each load node on the feeder considering distribution transformer loading limits, load composition, and square-footage. The proposed method is validated using actual data collected in a North Carolina service area. Finally, simulation results show that the proposed method can generate a unique load shape for each load node while match the shape of their aggregated profile with the actual feeder head load profile.

42 ENGINEERING↗

Self-Organizing Map-Based Resilience Quantification and Resilient Control of Distribution Systems Under Extreme Events

Due to climate change, extreme weather events are occurring more frequently and with increasing impact. This trend poses a significant challenge for distribution system operators (DSO) to ensure that there is uninterrupted power supply to critical loads in their networks. To embed resilience into DSO's decision-making, resilience needs to be first quantified and then integrated into the system-level optimization. Therefore, this paper first develops a novel self-organizing map (SOM) based method (called SomRes) to quantify the time-varying resilience index of a system that can leverage the powerful classification property of SOMs and removes some of the disadvantages of subjective weight assignment methods. Using SomRes, a resilient resource allocation and operational dispatch algorithm is further developed to enhance system resilience against extreme events by considering the SomRes resilience index directly as the feedback. Here, the proposed resilience quantification approach is benchmarked with a state-of-the-art approach and the efficacy of the proposed resilient dispatch algorithm is demonstrated through several deterministic and statistical case studies on the IEEE 123-bus distribution system. Simulation studies show that the proposed SomRes quantification method is an appropriate indicator of system resilience, and the resilient resource allocation and dispatch strategy can significantly reduce critical load shedding under varying event propagation scenarios.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Growth strategies and threshold responses to water deficit modulate effects of warming on tree seedlings from forest to alpine

Predictions of upslope range shifts for tree species with warming are based on assumptions of moisture stress at lower elevation limits and low-temperature stress at high-elevation limits. However, recent studies have shown that warming can reduce tree seedling establishment across the entire gradient from subalpine forest to alpine via moisture limitation. Warming effects also vary with species, potentially resulting in community shifts in high-elevation forests. We examined the growth and physiology underlying effects of warming on seedling demographic patterns. We evaluated dry mass (DM), root length, allocation above- and below-ground, and relative growth rate (RGR) of whole seedlings, and their ability to avoid or endure water stress via water-use efficiency and resisting turgor loss, for Pinus flexilis , Picea engelmannii and Pinus contorta seeded below, at and above tree line in experimentally warmed, watered and control plots in the Rocky Mountains, USA. We expected that growth and allocation responses to warming would relate to moisture status and that variation in drought tolerance traits would explain species differences in survival rates. Across treatments and elevations, seedlings of all species had weak turgor-loss resistance, and growth was marginal with negative RGR in the first growth phase (-0.01 to -0.04 g g -1 day -1 ). Growth was correlated with soil moisture, particularly in the relatively small-seeded P. contorta and P. engelmannii . Pinus flexilis , known to have the highest survivorship, attained the greatest DM and longest root but was also the slowest growing and most water-use efficient. This was likely due to its greater reliance on seed reserves. Seedlings developed 15% less total DM, 25% less root DM and 11% shorter roots in heated compared with unheated plots. Higher temperatures slightly increased DM, root length and RGR where soils were wettest, but more strongly decreased these variables under drier conditions. Synthesis. The surprising heat inhibition of tree seedling establishment at the cold edge of forests appears to have a physiological basis: newly germinated seedlings have poor moisture stress tolerance, which appears related to marginal initial growth and heavy reliance on seed reserves. Variation in these attributes among tree species at tree line helps explain their different climate responses.

54 ENVIRONMENTAL SCIENCES↗