Search NASA⌕ Search

SEARCH · Search NASA

Results for “Dynamic scheduling”

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 109 records · Page 6

A dynamic control approach for energy-efficient production scheduling on a single machine under time-varying electricity pricing

This paper proposes a dynamic control algorithm to enable an energy-aware single machine scheduling under the time-varying electricity pricing policy, in which price rates remain fixed day-to-day over the season. The key issue is to assign a set of jobs to available time periods where different electricity prices are assigned, while considering requested due dates of jobs so as to minimize total penalty costs for earliness and tardiness of jobs and total energy consumption costs, simultaneously. As the first contribution of this study, we develop a new mixed integer nonlinear programming (MINLP) model that aims at determining job arrival times and resulting earliness and tardiness of jobs and energy consumption costs for machine idle and normal processing. Second, an efficient heuristic approach based on continuous-time variable control models and algorithm is developed. The proposed heuristic adaptively changes job arrival times and due dates, which finally determine production sequence over the time periods of different electricity prices, machine turn-off, and machine idle with minimum energy consumption costs and just-in-time (JIT) penalty. Energy and JIT performance of the proposed approach is examined using real energy and machining parameters of a HAAS machine and compared to those of the metaheuristic approach. For relatively large size data groups, the proposed approach incurs about higher energy consumption costs on average, which are offset by up to lower JIT costs, resulting in lower total costs on average compared to the metaheuristic approach. Further, the proposed time-scaled heuristic algorithm yields extremely short computational time, which enables production managers to flexibly select proper production strategies and to implement them for different production environments.

42 ENGINEERING↗

Sky Survey Scheduling Using Reinforcement Learning

Modern cosmic sky surveys (e.g., CMB S4, DES, LSST) collect a complex diversity of astronomical objects. Each of class objects presents different requirements for observation time and sensitivity. For determining the best sequence of exposures for mapping the sky systematically, conventional scheduling methods do not optimize the use of survey time and resources. Dynamic Sky survey scheduling is an np-hard problem that has been therefore treated primarily with heuristic methods. We present an alternative scheduling method based on reinforcement learning (RL) that aims to optimize the use of telescope resources for scheduling sky surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

Exploiting Vector and Multicore Parallelsim for Recursive, Data- and Task-Parallel Programs

Modern hardware contains parallel execution resources that are well-suited for data-parallelism-vector units-and task parallelism-multicores. However, most work on parallel scheduling focuses on one type of hardware or the other. In this work, we present a scheduling framework that allows for a unified treatment of task- and data-parallelism. Our key insight is an abstraction, task blocks, that uniformly handles data-parallel iterations and task-parallel tasks, allowing them to be scheduled on vector units or executed independently as multicores. Our framework allows us to define schedulers that can dynamically select between executing task- blocks on vector units or multicores. We show that these schedulers are asymptotically optimal, and deliver the maximum amount of parallelism available in computation trees. To evaluate our schedulers, we develop program transformations that can convert mixed data- and task-parallel pro- grams into task block-based programs. Using a prototype instantiation of our scheduling framework, we show that, on an 8-core system, we can simultaneously exploit vector and multicore parallelism to achieve 14×-108× speedup over sequential baselines.

Ren, Bin↗

Adaptations in Electronic Structure Calculations in Heterogeneous Environments

Modern quantum chemistry deals with electronic structure calculations of unprecedented complexity and accuracy. They demand full power of high-performance computing and must be in tune with the given architecture for superior e ciency. To make such applications resourceaware, it is desirable to enable their static and dynamic adaptations using some external software (middleware), which may monitor both system availability and application needs, rather than mix science with system-related calls inside the application. The present work investigates scienti c application interlinking with middleware based on the example of the computational chemistry package GAMESS and middleware NICAN. The existing synchronous model is limited by the possible delays due to the middleware processing time under the sustainable runtime system conditions. Proposed asynchronous and hybrid models aim at overcoming this limitation. When linked with NICAN, the fragment molecular orbital (FMO) method is capable of adapting statically and dynamically its fragment scheduling policy based on the computing platform conditions. Signi cant execution time and throughput gains have been obtained due to such static adaptations when the compute nodes have very di erent core counts. Dynamic adaptations are based on the main memory availability at run time. NICAN prompts FMO to postpone scheduling certain fragments, if there is not enough memory for their immediate execution. Hence, FMO may be able to complete the calculations whereas without such adaptations it aborts.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Identification and Online Updating of Dynamic Models for Demand Response of an Industrial Air Separation Unit

Demand-response operation of air separation units requires frequent changes in production rate(s), and scheduling calculations must explicitly consider process dynamics to ensure feasibility of the solutions. To this end, scale-bridging models (SBMs) approximate the scheduling-relevant dynamics of a process and its controller in a low-order representation. In contrast to previous works that have employed nonlinear SBMs, this paper proposes linear SBMs, developed using time-series analysis, to facilitate online scheduling computations. Using a year-long industrial dataset, we nd that compact linear SBMs are suitable approximations over typical scheduling horizons, but that their accuracies are unpredictable over time. We introduce a strategy for online updating of the SBMs, based on Kalman ltering schemes for online parameter estimation. The approach greatly improves the accuracy of SBM predictions and will enable the use of linear SBM-based demand-response scheduling in the future.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Emerging Technologies for Improved Plug Load Management Systems: Learning Behavior Algorithms and Automatic and Dynamic Load Detection

Plug loads are responsible for a significant portion of the energy consumed in commercial buildings, yet their distributed and ever-changing nature makes them one of the most challenging building end uses to manage. Plug load management systems exist today that utilize smart plugs to meter and control devices at the outlet level, however, their uptake has been relatively slow in part due to the significant labor required for installation and maintenance. Learning behavior algorithms and automatic and dynamic load detection have been identified as two technology areas that could accelerate the adoption of plug load management systems by reducing these labor demands and providing additional energy efficiency and non-energy benefits. Learning behavior algorithms learn occupant behavior and adjust plug load management systems accordingly, allowing for the automatic creation of optimized control schedules. Automatic and dynamic load detection allows a plug load management system to identify devices as they are plugged in to a building and keeps the system up to date as devices are moved throughout a building. In this paper, we present our findings with respect to the current state of these two technologies based on a review of existing research and patents, as well as a series of interviews with companies working in the plug load space. We have found that, as of now, no commercialized solutions exist for these plug load technologies and that more work is needed to bring them to market. In addition, we summarize our findings related to the technology challenges, market barriers, drivers, and opportunities for these technologies moving forward.

30 DIRECT ENERGY CONVERSION↗

Optimizing CMS build infrastructure via Apache Mesos

The Offline Software of the CMS Experiment at the Large Hadron Collider (LHC) at CERN consists of 6M lines of in-house code, developed over a decade by nearly 1000 physicists, as well as a comparable amount of general use open-source code. A critical ingredient to the success of the construction and early operation of the WLCG was the convergence, around the year 2000, on the use of a homogeneous environment of commodity x86-64 processors and Linux.Apache Mesos is a cluster manager that provides efficient resource isolation and sharing across distributed applications, or frameworks. It can run Hadoop, Jenkins, Spark, Aurora, and other applications on a dynamically shared pool of nodes. Lastly, we present how we migrated our continuous integration system to schedule jobs on a relatively small Apache Mesos enabled cluster and how this resulted in better resource usage, higher peak performance and lower latency thanks to the dynamic scheduling capabilities of Mesos.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Going deeper and wider in neural architectures improves their accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need to change to less de- sired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far beyond the GPU DRAM capacity. SuperNeurons features 3 memory optimizations, Liveness Analysis, Unified Tensor Pool, and Cost-Aware Recomputation; together they effectively reduce the network-wide peak memory usage down to the maximal memory usage among layers. We also address the performance issues in these memory-saving techniques. Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance. Evaluations against Caffe, Torch, MXNet and TensorFlow have demonstrated that SuperNeurons trains at least 3.2432 deeper network than current ones with the leading performance. Particularly, SuperNeurons can train ResNet2500 that has 104 basic network layers on a 12GB K40c.

Wang, Linnan↗

Community Microgrid Scheduling Considering Network Operational Constraints and Building Thermal Dynamics

Here, this paper proposes a Mixed Integer Conic Programming (MICP) model for community microgrids considering the network operational constraints and building thermal dynamics. The proposed optimization model optimizes not only the operating cost, including fuel cost, purchasing cost, battery degradation cost, voluntary load shedding cost and the cost associated with customer discomfort due to room temperature deviation from the set point, but also several performance indices, including voltage deviation, network power loss and power factor at the Point of Common Coupling (PCC). In particular, the detailed thermal dynamic model of buildings is integrated into the distribution optimal power flow (D-OPF) model for the optimal operation of community microgrids. The heating, ventilation and air-conditioning (HVAC) systems can be scheduled intelligently to reduce the electricity cost while maintaining the indoor temperature in the comfort range set by customers. Numerical simulation results show the effectiveness of the proposed model and significant saving in electricity cost could be achieved with network operational constraints satisfied.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A data-driven linear formulation of the optimal demand response scheduling problem for an industrial air separation unit

Demand response (DR) has become a key element in balancing the power grid as the contribution of time-varying renewable power generation increases. Chemical plants are appealing candidates for DR programs as they offer large, concentrated and flexible loads. DR participation calls for frequent production rate changes over time scales that overlap with the dominant dynamics of the plant. Production scheduling should therefore consider the process dynamics explicitly. Here we present a data-driven approach for modelling the scheduling-relevant dynamics based on historical closed-loop operating data using autoregressive with extra inputs (ARX) models. We introduce a new, linear scheduling problem formulation based on the ARX representation, and demonstrate its implementation on an industrial air separation unit.

42 ENGINEERING↗

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↗

Transferable Reinforcement Learning for Smart Homes: Preprint

To harness the great amount of untapped resources at the demand side, smart home technology plays a vital role in solving the "last mile" problem in smart grid. Reinforcement learning (RL), which has demonstrated an outstanding performance in solving many sequential decision-making problems, can be a great candidate to be used in smart home control. For instance, many studies have started investigating the load scheduling problem under dynamic pricing scheme. Based on those, this study aims at providing an affordable solution to encourage a higher smart home adoption rate. Specifically, we investigate combining transfer learning (TL) with RL to reduce the training cost of an optimal RL control policy. Given an optimal policy for a benchmark home, TL can jump-start the RL training of a policy for a new home, which has different appliances and user preferences. Simulation results show that by leveraging TL, RL training converges faster and requires much less computing time for new homes that are similar to the benchmark home. In all, this study proposes a cost-effective approach for training RL control policies for homes at scale, which ultimately reduces the controller's implementation costs, increases the adoption rate of RL controllers, and makes more homes grid-interactive.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION,↗

Notes from the Unit Commitment Linear Programming Project

The Unit Commitment Problem (UCP) is a computational bottleneck in electrical grid optimization. The problem bears a close resemblance to a similar problem in High Performance Computing: the Dynamic Volt age/Frequency Scheduling (DVFS) problem. In my earlier work I successfully tranformed the DVFS into a closely related problem amenable to a linear programming solution and was thus able to schedule problem instances several orders of magnitude larger than any that had been at tempted before. This technical report details my unsuccessful efforts to derive a similar transformation for the UCP. The problem proved impossible not because generators were either on or off, but because the state of an earlier timeslice constrains the states of latter timeslices in ways that cannot be sufficiently well approximated for useful solutions.

97 MATHEMATICS AND COMPUTING↗

Sienna Modeling Framework [Slides]

NREL's Sienna modeling framework effectively builds, solves, and analyzes the scheduling problems and dynamic simulations of quasi-static infrastructure systems. It uses a modular framework to answer different questions about future energy systems, fundamentally advancing the nation's ability to model individual and integrated infrastructure systems at a range of spatial and temporal scales. This presentation will include NREL power grid researcher Clayton Barrows.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Formulation and Comparison of Two Real-Time Predictive Gear Shift Algorithms for Connected/Automated Heavy-Duty Vehicles

Our work investigates the problem of predictive gear scheduling for fuel consumption minimization in connected/automated heavy trucks. The literature highlights the fuel economy benefits of such predictive scheduling, but there is a need to optimize such scheduling online, in real time. To address this need, we begin by using dynamic programming (DP) to schedule gear shifting offline, in a manner that achieves a globally optimal Pareto tradeoff between the conflicting objectives of minimizing fuel consumption and shift frequency. The computational cost of DP is unfavorable for online implementation, but we present two algorithms addressing this issue. Both algorithms rely on the fact that in the Pareto limit where fuel consumption minimization is the sole objective, DP furnishes a simple static shift map . Our first algorithm trains a recurrent neural network to prune the shift schedule generated by this map. The second algorithm performs this pruning in a direct manner tailored to reduce the schedule's rain flow count. We simulate these algorithms for different drive cycles. Both algorithms achieve a reasonable tradeoff between fuel consumption and gear shift frequency. Yet, the rain flow count algorithm is both more effective in approaching the DP-based Pareto front and more computationally efficient.

33 ADVANCED PROPULSION SYSTEMS↗

Dynamic force and stability prediction for milling using feed rate scheduling software and time-domain simulation

This paper describes: 1) the use of feed rate scheduling software to predict the radial depth of cut variation for three-axis milling toolpaths and; 2) the use of the radial depth profile in a time-domain simulation to predict dynamic cutting forces. The time-domain simulation, which also includes the tool tip frequency response functions and force model (which relates the cutting force components to the chip geometry) as inputs, enables dynamic force profiles to be predicted and parameter combinations that cause chatter to be identified. A ramp geometry is selected that provides constantly varying radial depth and force predictions are completed at multiple axial depths for comparison to measured forces. Both stable and unstable (chatter) milling conditions were observed with good agreement between time-domain simulation and measurement results. The value of combining the feed rate scheduling software and time-domain simulation is demonstrated.

42 ENGINEERING↗

Mathematical and Numerical Aspects of the Adaptive Fast Multipole Poisson-Boltzmann Solver

This paper summarizes the mathematical and numerical theories and computational elements of the adaptive fast multipole Poisson-Boltzmann (AFMPB) solver. We introduce and discuss the following components in order: the Poisson-Boltzmann model, boundary integral equation reformulation, surface mesh generation, the nodepatch discretization approach, Krylov iterative methods, the new version of fast multipole methods (FMMs), and a dynamic prioritization technique for scheduling parallel operations. For each component, we also remark on feasible approaches for further improvements in efficiency, accuracy and applicability of the AFMPB solver to large-scale long-time molecular dynamics simulations. Lastly, the potential of the solver is demonstrated with preliminary numerical results.

97 MATHEMATICS AND COMPUTING↗

Optimizing human activity patterns using global sensitivity analysis

Implementing realistic activity patterns for a population is crucial for modeling, for example, disease spread, supply and demand, and disaster response. Using the dynamic activity simulation engine, DASim, we generate schedules for a population that capture regular (e.g., working, eating, and sleeping) and irregular activities (e.g., shopping or going to the doctor). We use the sample entropy (SampEn) statistic to quantify a schedule’s regularity for a population. We show how to tune an activity’s regularity by adjusting SampEn, thereby making it possible to realistically design activities when creating a schedule. The tuning process sets up a computationally intractable high-dimensional optimization problem. To reduce the computational demand, we use Bayesian Gaussian process regression to compute global sensitivity indices and identify the parameters that have the greatest effect on the variance of SampEn. Here we use the harmony search (HS) global optimization algorithm to locate global optima. Our results show that HS combined with global sensitivity analysis can efficiently tune the SampEn statistic with few search iterations. We demonstrate how global sensitivity analysis can guide statistical emulation and global optimization algorithms to efficiently tune activities and generate realistic activity patterns. Finally, though our tuning methods are applied to dynamic activity schedule generation, they are general and represent a significant step in the direction of automated tuning and optimization of high-dimensional computer simulations.

97 MATHEMATICS AND COMPUTING↗