SEARCH · Search NASA
Results for “Load Balancing”
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.
Integrating DARMA into EMPIRE for AMT-Based Particle Load Balancing.
Abstract not provided.
Integrating DARMA into EMPIRE for AMT-Based Particle Load Balancing.
Abstract not provided.
Load Balancing Eager K-truss on GPU and CPU via Fine-Grained Parallelism.
Abstract not provided.
Partitioning and Load-Balancing for Parallel Scientific Computing.
Abstract not provided.
The Zoltan Toolkits: Parallel Partitioning Load Balancing Coloring and Ordering.
Abstract not provided.
Clustering as a Load-Balancing Method to Speed Up PDES in ns-3.
Abstract not provided.
Integrating DARMA into EMPIRE for AMT-Based Particle Load Balancing.
Abstract not provided.
Balancing Load in More Ways than One
Explore the source record for details and available documents.
A Communication- and Memory-Aware Model for Load Balancing Tasks
Explore the source record for details and available documents.
Load Control for Frequency Response - A Literature Review
As electricity grids employ greater fractions of renewable energy, which introduce additional variability and uncertainty in the net load, balancing electrical load and generation becomes more challenging. This paper reviews the literature documenting physical simulations and real systems that employ load control (LC) for frequency response and other grid services, which balance net load on the grid and prevent unwanted frequency excursions. Apart from academic and simulation studies, few sources exist on large-scale laboratory hardware testing or actual real-world systems that employ LC for frequency response, and we review them here. Four types of systems that we consider are: 1) Laboratory-based LC experiments, 2) Isolated microgrids that employ LC, 3) Larger grids that employ LC and 4) vehicle-to-grid (V2G) technology, using electric vehicles (EVs). In general, these systems have successfully used LC to meet their objectives, which are often keeping grid frequency within a required band. However, LC struggled to balance grid frequency in an isolated system powered by a single wind turbine, and V2G technology requires refinement in communication and control to provide optimal regulation that adheres to industry standards. As LC grows in the energy industry, we have three main recommendations: 1) encouraging system operators who use LC to publish system characteristics and lessons learned; 2) transitioning more LC theoretical/simulated systems to physical experiments, and physical experiments to real-world pilot systems; 3) demonstrating load control to support isolated, high-wind-contribution systems.
Loads as a Resource: Frequency Responsive Demand
Current power grid operation predominantly relies on scheduling and regulating generation resources to supply loads and balance load changes. Due to the inherent intermittency of renewable energy, more flexible and fast ramping capacity is required to compensate for the uncertainty and variability introduced by renewable energy resources. With the advancement of information technologies, power system end-use loads are becoming more agile and can participate in provision of balancing energy and other grid services. The use of demand response can greatly reduce the required generation reserve in a clean and environmentally friendly way. In this report, a new frequency responsive load (FRL) controller was proposed based on the GFA controller, which can respond to both over and under-frequency events. A supervisory control was introduced to coordinate the autonomous response from FRLs in order to overcome the issues of excessive system response due to high penetration of FRLs. The effectiveness of the proposed FRL controller was demonstrated by large-scale simulation studies on the WECC system. Specifically, the FRLs were deployed in the WECC system at different penetration levels to analyze the performance of the proposed strategy both with and without supervisory level control. While both methods have their own advantages, the case without supervisory control could lead to system-wide instability depending on the size of the contingency and the number of FRLs deployed in the system. In addition, the voltage impacts of this controller on distribution system were also carefully investigated. Finally, a preliminary measurement and verification approach was also developed.
DISTRI: Distributed Multi-Facility HPC Simulator (DISTRI) v2.1
DISTRI is an advanced network simulator designed for multi-facility computational infrastructures with agentic behavior. It simulates HPC facilities where computational resources act as autonomous agents, making intelligent decisions about job scheduling, load balancing, and resource allocation. The simulator focuses on developing and testing decentralized algorithms that promote resilience and efficiency in multi-facility environments. Key Features: - Agentic Resource Behavior: Processors and DTNs act as autonomous agents with decision-making capabilities - Pheromone-Based Load Balancing: Decentralized load balancing inspired by ant colony optimization - Dual Topology Support: Mesh (normal operations) and Dumbell (network testing) topologies - Comprehensive TCP Simulation: Realistic TCP implementations with multiple congestion control algorithms - Failure Resilience Testing: Processor failure simulation with automatic job reassignment - Extensive Visualization: Detailed performance analysis and metrics collection - Research-Ready: Designed for algorithm development and benchmarking
Optimal Load Control via Frequency Measurement and Neighborhood Area Communication
We propose a decentralized optimal load control scheme that provides contingency reserve in the presence of sudden generation drop. The scheme takes advantage of flexibility of frequency responsive loads and neighborhood area communication to solve an optimal load control problem that balances load and generation while minimizing end-use disutility of participating in load control. Local frequency measurements enable individual loads to estimate the total mismatch between load and generation. Neighborhood area communication helps mitigate effects of inconsistencies in the local estimates due to frequency measurement noise. Case studies show that the proposed scheme can balance load with generation and restore the frequency within seconds of time after a generation drop, even when the loads use a highly simplified power system model in their algorithms. We also investigate tradeoffs between the amount of communication and the performance of the proposed scheme through simulation-based experiments.
Collaborating CPU and GPU for large-scale high-order CFD simulations with complex grids on the TianHe-1A supercomputer
Programming and optimizing complex, real-world CFD codes on current many-core accelerated HPC systems is very challenging, especially when collaborating CPUs and accelerators to fully tap the potential of heterogeneous systems. In this paper, with a tri-level hybrid and heterogeneous programming model using MPI + OpenMP + CUDA, we port and optimize our high-order multi-block structured CFD software HOSTA on the GPU-accelerated TianHe-1A supercomputer. HOSTA adopts two self-developed high-order compact definite difference schemes WCNS and HDCS that can simulate flows with complex geometries. We present a dual-level parallelization scheme for efficient multi-block computation on GPUs and perform particular kernel optimizations for high-order CFD schemes. The GPU-only approach achieves a speedup of about 1.3 when comparing one Tesla M2050 GPU with two Xeon X5670 CPUs. To achieve a greater speedup, we collaborate CPU and GPU for HOSTA instead of using a naive GPU-only approach. We present a novel scheme to balance the loads between the store-poor GPU and the store-rich CPU. Taking CPU and GPU load balance into account, we improve the maximum simulation problem size per TianHe-1A node for HOSTA by 2.3×, meanwhile the collaborative approach can improve the performance by around 45% compared to the GPU-only approach. Further, to scale HOSTA on TianHe-1A, we propose a gather/scatter optimization to minimize PCI-e data transfer times for ghost and singularity data of 3D grid blocks, and overlap the collaborative computation and communication as far as possible using some advanced CUDA and MPI features. Scalability tests show that HOSTA can achieve a parallel efficiency of above 60% on 1024 TianHe-1A nodes. With our method, we have successfully simulated an EET high-lift airfoil configuration containing 800M cells and China's large civil airplane configuration containing 150M cells. To our best knowledge, those are the largest-scale CPU–GPU collaborative simulations that solve realistic CFD problems with both complex configurations and high-order schemes.