A Communication- and Memory-Aware Model for Load Balancing Tasks
Explore the source record for details and available documents.
Lifflander, Jonathan Josiah↗
SEARCH · Engineering Papers
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.
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.
17 WIND ENERGY↗
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
Bez, Jean Luca [Lawrence Berkeley National Laborat↗
Evaluation of Optimal Net Load Management in Microgrids Using Hardware-in-the-Loop Simulation: Preprint
This paper presents the performance evaluation of a net load management (NLM) engine that balances load and generation in an isolated community to power a critical facility after a grid interruption event (e.g., lost a large generation unit). The NLM engine is a central dispatch control system that provides high-speed cost-optimal coordination of a set of net loads (combination of generation and deferrable loads) connected to the same electrical network. The NLM algorithm cost-optimally dispatches the grid-following inverters and deferrable loads based on the demanded power and load priorities, and the grid-forming inverters use droop control to form system voltages and share active and reactive power. A controller-hardware-in-the-loop platform is developed to evaluate the control performance of the NLM algorithm. The experimental results indicate that the NLM engine can achieve the targeted system voltage and frequency and balance load and generation to serve the critical facility.
droop control↗
Evaluation of Optimal Net Load Management in Microgrids Using Hardware-in-the-Loop Simulation
This paper presents the performance evaluation of a net load management (NLM) engine that balances load and generation in an isolated community to power a critical facility after a grid interruption event (e.g., the loss of a large generation unit). This NLM engine is particularly important for microgrid systems because it provides a high-speed, cost-optimal control solution to coordinate grid-forming inverters and to dispatch grid-following inverters and deferrable loads in microgrid systems to enhance grid resilience and reliability. The NLM algorithm cost-optimally dispatches the grid-following inverters and deferrable loads based on the demanded power and load priorities, and the grid-forming inverters use droop control to form system voltages and share active and reactive power. A controller-hardware-in-the-loop platform is developed to evaluate the control performance of the NLM algorithm with two sequential contingency events of lost generation units. The experimental results indicate that the NLM engine can maintain system stability, achieve the targeted system voltage and frequency, and balance load and generation to serve the critical facility with improved system resilience and reliability.
grid-following inverter↗
Evaluation of Optimal Net Load Management in Microgrids Using Hardware-in-the-Loop Simulation
This presentation discusses the performance evaluation of a net load management (NLM) engine that balances load and generation in an isolated community to power a critical facility after a grid interruption event (e.g., the loss of a large generation unit). This NLM engine is particularly important for microgrid systems because it provides a high-speed, cost-optimal control solution to coordinate grid-forming inverters and to dispatch grid-following inverters and deferrable loads in microgrid systems to enhance grid resilience and reliability. The NLM algorithm cost-optimally dispatches the grid-following inverters and deferrable loads based on the demanded power and load priorities, and the grid-forming inverters use droop control to form system voltages and share active and reactive power. A controller-hardware-in-the-loop platform is developed to evaluate the control performance of the NLM algorithm with two sequential contingency events of lost generation units. The experimental results indicate that the NLM engine can maintain system stability, achieve the targeted system voltage and frequency, and balance load and generation to serve the critical facility with improved system resilience and reliability.
droop control↗
Scalability and Effectiveness of Smart Charge Management
The rise in electric vehicle (EV) adoption presents growing challenges for power grids, particularly from simultaneous residential charging, which can cause voltage fluctuations and increase feeder peak loads. Baltimore Gas and Electric (BGE), with support from the U.S. Department of Energy, initiated a pilot program to evaluate managed residential EV charging through Smart Charge Management (SCM). This study analyzes real-world charging behavior data from the pilot and feeder-level base loads from BGE to simulate residential charging scenarios through 2035 across the Washington, DC–Baltimore region. Grid impacts under unmanaged charging are compared to three SCM strategies: TOU-immediate, TOU-distributed, and Load Balancing. Results show that the magnitude of peak reduction is highly feeder-dependent. Some feeders achieve reductions of more than 40% at high enrollment levels, while others show improvements closer to 10–15%. This heterogeneity reflects differences in baseline feeder load shapes, EV penetration, and plug-in behavior across customers. Results also highlight trade-offs between shifting load away from peak periods and minimizing secondary demand peaks, offering practical insights for future utility program design.
Electric vehicle↗
Toucan: A performance portable, scalable implementation of the DECA algorithm
In the field of additive manufacturing (AM), cellular automata (CA) is extensively used to simulate microstructural evolution during solidification. However, while traditional CA approaches are relatively fast, they still require a substantial number of time steps, are limited to moderate volumes, and are relatively difficult to improve through parallelism due to the highly localized nature of the solidification front. Here, to address these issues of time to solution and load balancing, we introduce Toucan, a parallel, performance-portable, and scalable code written in C++ with the Kokkos library that leverages the discrete event inspired cellular automata (DECA) algorithm to perform parallel-in-time (PinT) grain growth simulations. Toucan effectively mitigates load balancing issues by distributing the computational workload more evenly across processors, enhancing scalability and efficiency. We conduct both strong and weak scaling studies on up to 64 GPUs on the Frontier supercomputer, demonstrating that Toucan significantly outperforms the current state-of-the-art, time-stepped CA code, ExaCA, on both single and multi-GPU simulations. Even in AM-specific weak scaling scenarios, Toucan maintains near-ideal scaling, in contrast to the linear increase observed with ExaCA due to the moving laser raster pattern. This study highlights Toucan’s potential to transform microstructural simulations in AM by radically improving both efficiency and scalability over existing methods.
36 MATERIALS SCIENCE↗
OCTOKV: An Agile Network-Based Key-Value Storage System with Robust Load Orchestration
In this paper, we propose OctoKV, an innovative network-based key-value storage system. OctoKV addresses the repetitive address translation overhead associated with traditional key-value stores running on file systems on the client side. To mitigate this overhead, we implemented the key-value store on the server side using NVMe-oF and a user-level NVMe driver. In particular, we employed fine-grained resource monitoring and load balancing based on heuristics to optimize I/O performance. OctoKV is deployed on a Linux cluster with Intel SPDK. The extensive evaluation shows that OctoKV achieves lower I/O response times in comparison to traditional approaches where key-value stores run on the client side. Also, the proposed load balancing strategies efficiently enhance I/O response times by equally distributing the workload from overloaded cores to other cores.
Khan, Awais↗
A Sparse Distributed Gigascale Resolution Material Point Method
In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.
97 MATHEMATICS AND COMPUTING↗
T-FSM: A Scalable Distributed Task-Based System for Frequent Subgraph Pattern Mining from a Big Graph
Finding frequent subgraph patterns in a big graph is an important problem with many applications such as classifying chemical compounds and building indexes to speed up graph queries. Since this problem is NP-hard, some recent parallel and distributed systems have been developed to accelerate the mining. However, they often have a huge memory cost, very long running time, suboptimal load balancing, poor scale-out capability, and possibly inaccurate results. In this article, we propose an efficient system called T-FSM for parallel mining of frequent subgraph patterns in a big graph. T-FSM supports a new anti-monotonic frequentness measure called Fraction-Score, which is more accurate than the widely used MNI measure. The execution engine of T-FSM supports both intra-machine parallelism and inter-machine parallelism. For intra-machine parallelism, T-FSM adopts a novel task-based execution model to ensure high multithreading concurrency, bounded memory consumption, and effective load balancing. For inter-machine parallelism, T-FSM ensures good scale-out performance with a lightweight pattern rebalancing approach that reduces workload skewness of pattern evaluations among machines. To avoid recomputing the contexts for migrated patterns, we design a novel context cache table to support concurrent and asynchronous requesting and caching of remote context data, which can timely evict and garbage collect used pattern contexts that are no longer needed to keep memory consumption bounded. Extensive experiments show that T-FSM is orders of magnitude faster than existing state-of-the-art parallel systems (more than 10×, 51×, 131×, 55× speedup over ScaleMine, DistGraph, Pangolin and Peregrine, respectively) and distributed systems (more than 42× and 88× over ScaleMine and DistGraph, respectively) for frequent subgraph pattern mining, and it scales out satisfactorily to 512 CPU cores on the Polaris supercomputer at Argonne National Laboratory.
97 MATHEMATICS AND COMPUTING↗
ESnet/JLab FPGA Accelerated Transport
To increase the science rate for high data rates/volumes, Thomas Jefferson National Accelerator Facility (JLab) has partnered with Energy Sciences Network (ESnet) to define an edge to data center traffic shaping / steering transport capability featuring data event aware network shaping and forwarding. The keystone of this ESnet+JLab FPGA Accelerated Transport (EJFAT) is the joint development of an AI/ML directed dynamic compute work Load Balancer (LB) of UDP streamed data. The LB is a suite consisting of a Field Programmable Gate Array (FPGA) executing the dynamically configurable, low fixed latency LB data plane featuring real-time packet redirection and high throughput, and a control plane running on the FPGA host computer that monitors network and compute farm telemetry in order to make dynamic AI/ML guided decisions for destination compute host redirection/load balancing and destination resource provisioning. The LB provides for three-tier horizontal scaling across LB suites, core compute hosts, and CPUs within a host. The LB effectively provides seamless integration of edge/core computing to support direct experimental data processing for immediate use by JLab science programs and others such as the EIC as well as data centers of the future requiring high throughput and low latency for both hot and cooled data for both running experiment data acquisition systems and data center use cases.
97 MATHEMATICS AND COMPUTING↗
Performance Analysis of Speculative Parallel Adaptive Local Timestepping for Conservation Laws
Stable simulation of conservation laws, such as those used to model fluid dynamics and plasma physics applications, requires the satisfaction of the so-called Courant-Friedrichs-Lewy condition. By allowing regions of the mesh to advance with different timesteps that locally satisfy this stability constraint, significant work reduction can be attained when compared to a time integration scheme using a single timestep size. However, parallelizing this algorithm presents considerable difficulty. Since the stability condition depends on the state of the system, dependencies become dynamic and potentially non-local. In this article, we present an adaptive local timestepping algorithm using an optimistic (Timewarp-based) parallel discrete event simulation. We introduce waiting heuristics to limit misspeculation and a semi-static load balancing scheme to eliminate load imbalance as parts of the mesh require finer or coarser timesteps. Last, we outline an interface for separating the physics of the specific conservation law from the temporal integration allowing for productive adoption of our proposed algorithm. We present a misspeculation study for three conservation laws, demonstrating both the productivity of the local timestepping API, for which 74% of the lines of code are reused across different conservation laws, and the robustness of the waiting heuristics—at most 1.5% of element updates are rolled back. Our performance studies demonstrate up to a 2.8× speedup versus a baseline unoptimized local timestepping approach, a 4x improvement in per-node throughput compared to an MPI parallelization of synchronous timestepping, and scalability up to 3,072 cores on NERSC’s Cori Haswell partition.
97 MATHEMATICS AND COMPUTING↗
Scaling Demand Flexibility: Building on 30 Years of Energy Efficiency Success
With electricity consumption across the United States (US) and Canada anticipated to grow, energy efficiency program administrators have a key role to play in helping to ensure energy affordability and reliability in support of the broader economic systems utilities and grid support. Connected, demand side load balancing solutions, such as load shifting heating, ventilation and air conditioning (HVAC) systems and managed charging for electric vehicles (EVs), can dynamically manage energy, allowing for more volumetric electricity consumption without incurring the expense of upgraded transmission and distribution capabilities. When combined, or aggregated, many small loads can be managed to have meaningful impact on energy demand on the grid. Utilities and their partners have an opportunity to leverage decades of experience and the infrastructure needed to assess, design, implement, and measure programs to scale up the adoption of equipment with built-in load flexibility capabilities. Current efforts among a wide variety of electricity system service providers, utilities, standards agencies, regulators, national labs and private industry stakeholders aim to identify common standards, metrics, and methodologies for valuing grid services offered by demand side equipment. By combining those efforts with decades of proven energy efficiency resources, utilities are poised to effectuate a scaling up of equipment with energy management capabilities installed in homes and businesses across the US and Canada. This paper will provide an overview of how utilities are approaching this era of load growth and new peak demands across the United States and Canada. It will highlight the specific strategies that program administrators are employing to advance market transformation for grid-enabled products and devices that have the greatest potential to reduce energy use and increase load flexibility.
Grant, Peter↗
Advancing Grid Resilience through Smart Charge Management: Findings from Maryland’s Pilot
This report presents research findings from a four-year Smart Charge Management (SCM) pilot program conducted by Maryland’s largest electric utilities—Baltimore Gas and Electric (BGE), Potomac Electric Power Company (Pepco), and Delmarva Power & Light (DPL)—to evaluate strategies for optimizing electric vehicle (EV) charging loads and enhancing grid stability. Supported by the U.S. Department of Energy (DOE), Argonne National Laboratory collaborated with all project partners and examined the effectiveness of Time-of-Use (TOU) and Load Balancing (LB) strategies in managing peak demand, deferring costly infrastructure upgrades, and reducing grid constraints at the feeder level. Using charging data from over 4,600 EV drivers, the study analyzed SCM’s impact on the distribution systems of BGE and Pepco, which consists of over 2000 feeders. Unlike prior research that focused on system-wide trends or synthetic feeders, this analysis offers granular, feeder-level insights based on real-world operational data. It highlights how transformer density, load profiles, and infrastructure constraints influence smart charging performance. Results show feeder-level conditions play a crucial role in SCM effectiveness, with most feeders benefiting more from LB, while TOU-based SCM may be sufficient for others. By 2035, LB reduced peak charging loads by 27% on average, compared to 23% under TOU-based SCM, though some feeders saw reductions exceeding 35%, while others experienced minimal impact. Feeders with higher transformer utilization and limited capacity benefited more from LB, which more effectively distributed charging demand during off-peak hours. Beyond reducing grid constraints, SCM offers long-term operational and financial benefits. By shifting EV charging demand strategically, utilities can optimize asset utilization, delay infrastructure investments, and enhance grid performance. In terms of infrastructure upgrade deferrals, at the feeder level, LB consistently reduced peak charging loads and resulting infrastructure upgrade costs, particularly in high EV enrollment areas, decreasing the number of overloaded transformers by up to 35%, while TOU-based SCM achieved 20-30% reductions depending on feeder characteristics. At the system level, LB has the potential to defer total upgrade costs by $\$$186 million for BGE, compared to $\$$159 million under TOU-based SCM. For Pepco, TOU-based SCM performed slightly better, deferring upgrade costs by $\$$30 million, compared to $\$$29 million under LB. Section 4.5 reviews some of the system differences between BGE and Pepco. However, as EV adoption scales, TOU-based SCM will introduce secondary peak charging loads, reinforcing the need for more advanced, adaptive SCM approaches to prevent new grid challenges. As EV adoption continues to grow, feeder-level managed charging strategies will be essential for mitigating grid stress, improving infrastructure efficiency, and maintaining energy affordability for consumers. This report provides critical insights for utilities, Public Utility Commissions (PUCs), and state agencies on the role of feeder-specific smart charging in infrastructure planning, policy development, and grid modernization. The findings underscore the importance of tailored, data-driven SCM solutions that align with local grid conditions, ensuring a resilient, cost-effective transition to increasing EV adoption while safeguarding distribution system performance.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Assessing the performance of global thermostat adjustment in commercial buildings for load shifting demand response
Abstract Efficiently leveraging new sources of flexibility is critical to mitigating load balancing challenges posed by variable renewable resources. The thermal inertia of commercial buildings allows us to shift their power consumption on minute to hourly timescales to provide demand response to the grid while maintaining occupant comfort. Global thermostat adjustment (GTA) provides a readily available and scalable approach for implementing load shifting demand response using commercial heating, ventilation, and air conditioning (HVAC) systems, since it leverages the inherent sophistication of modern building automation systems. However, there is an incomplete understanding of GTA’s performance for this purpose and its impact on building systems and occupant comfort. In this paper, we explore the performance of GTA by analyzing results from nearly nine hundred experiments on eight university campus buildings in Michigan and North Carolina. Using GTA, we manipulate each building’s thermostat setpoints causing the building to shift its power consumption with respect to its baseline. We quantify the magnitude of HVAC power response, energy use of HVAC subsystems, and impact on occupant comfort. Finally, we connect our experimental results with power system operation using an optimization model that coordinates GTA actions across a large collection of grid-interactive efficient buildings (GEBs) to reduce high ramp rates on the grid and mitigate renewable energy curtailment. Overall, our work finds that the impacts on HVAC subsystems are often complex, and may result in additional energy being consumed by fans and terminal reheat. These effects must be considered when using GTA for load shifting. Additionally, we demonstrate that occupant comfort, as assessed by indoor temperature and humidity, can be maintained during GTA events. From a societal perspective, our modeling work finds that the additional renewable energy that can be integrated through the use of GTA strategies eclipses any additional energy consumed by buildings.
Keskar, Aditya (ORCID:0000000244617980)↗
A GPU-based compressible combustion solver for applications exhibiting disparate space and time scales
High-speed chemically active flows pose significant computational challenges due to their disparate space and time scales, with stiff chemistry often dominating simulation time. While modern scientific computing programs achieve exascale performance by leveraging graphics processing units (GPUs), existing GPU-based compressible combustion solvers face critical limitations in memory management, load balancing, and handling the highly localized nature of chemical reactions. To this end, we present a high-performance compressible reacting flow solver built on the AMReX framework and optimized for multi-GPU settings. Here, our approach addresses three GPU performance bottlenecks: memory access patterns through column-major storage optimization, computational workload variability via a bulk-sparse integration strategy for chemical kinetics, and multi-GPU load distribution for adaptive mesh refinement applications. The solver adapts existing matrix-based chemical kinetics formulations to multi-grid contexts. Using representative combustion applications, including 2D and 3D detonations and a 3D jet-in-crossflow configuration, we demonstrate 1.4–5× performance improvements over initial implementations on an in-house cluster of NVIDIA H100 GPUs, and near-ideal weak scaling on the Frontier supercomputer (Oak Ridge Leadership Computing Facility) with up to 1024 AMD Instinct MI250X GPUs. Roofline analysis reveals substantial improvements in arithmetic intensity for both convection (∼ 10 ×) and chemistry (∼ 4 ×) routines, confirming efficient utilization of GPU memory bandwidth and computational resources.
42 ENGINEERING↗
Efficient Parallelization of Irregular Applications on GPU Architectures
With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with the computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to coarse-grained kernel and inefficient parallelism; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. Targeting these challenges, this dissertation proposes multiple optimizations to accelerate two real-world applications: many-body correlation functions to simulate nuclear physics in a large-scale scientific system; the other is the eALS-based matrix factorization recommendation system. To accelerate the calculations of many-body correlation functions, this dissertation presents three frameworks in GPU memory management and multi-GPU scheduling. Firstly, an optimized systematic GPU memory management framework, MemHC, utilizes a series of new memory reduction designs in GPU memory allocation, CPU/GPU communications, and GPU memory oversubscription. Secondly, an enhanced multi-GPU scheduling framework, MICCO, particularly by taking both data dimension (e.g., data reuse and data eviction) and computation dimension into account. MICCO designs a heuristic scheduling algorithm and a machine learning-based regression model to generate the optimal settings of a proposed new concept to manage the trade-off. Thirdly, a locality-aware multi-GPU scheduling framework. This scheduler leverages pipeline batch generation with a looking-ahead strategy by building local dependency graphs for memory transfer reduction and better data reuse, achieving up to 79.92% memory cost reduction and 1.67x speedup. To parallelize the eALS-based recommendation system, this dissertation proposes an efficient CPU/GPU heterogeneous recommendation system, HEALS. HEALS employs newly designed architecture-adaptive data formats to achieve load balance and good data locality on CPU and GPU. To mitigate the data dependence, HEALS presents a CPU/GPU collaboration model for both task parallelism and data parallelism with multiple kernel computation optimizations. In summary, this dissertation efficiently accelerates two typical irregular applications on GPUs by building four frameworks, including CPU/GPU collaboration, GPU memory management, and multi-GPU scheduling.
Wang, Qihan↗