This paper proposes a Q-learning-based task allocation approach for wireless coded distributedcomputing systems with heterogeneous worker nodes. Task allocation in such systems is challenging due to the heterogeneity...
详细信息
Innovation and technological advancements have enabled energy production to meet growing energy demands. The challenge, however, is to achieve this goal without generating significant greenhouse gas emissions. Leverag...
详细信息
ISBN:
(数字)9780784485248
ISBN:
(纸本)9780784485248
Innovation and technological advancements have enabled energy production to meet growing energy demands. The challenge, however, is to achieve this goal without generating significant greenhouse gas emissions. Leveraging electric vehicles (EVs) as a distributed power storage solution for solar PV-powered energy presents an opportunity to significantly reduce the carbon footprint of energy generation. This paper explores the potential of vehicle-to-grid (V2G) technology to reduce greenhouse gas emissions by utilizing solar-generated energy stored in EV batteries. This study presents the findings of a case study that evaluates the economic feasibility of integrating a single-family household with a V2G capable system. As a result of examining the findings of the case study, a better understanding of the feasibility and advantages of V2G technology can be gained, as well as its potential as an alternative to traditional energy storage systems.
Agent-Based Modeling and Simulation (ABMS) has been increasingly applied in various research fields, thanks to the capability of these models to describe fine-grained realworld behavior and to the ease of interpretati...
详细信息
The primary targets for improving efficiency for large-scale matrix factorization are reducing synchronization, addressing the overlap in communication and computation, and improving load balance. In recent years, til...
详细信息
ISBN:
(纸本)9798400708893
The primary targets for improving efficiency for large-scale matrix factorization are reducing synchronization, addressing the overlap in communication and computation, and improving load balance. In recent years, tiled algorithms with task parallelism in multicore shared memory systems have become well-established as efficient methods for conducting fine-grained computations on smaller tiles. Moreover, they provide flexible execution orders for a runtime system in many situations. However, traditional hybrid programs with MPI and OpenMP for distributed memory systems use a fork-join model for multi-threads in each process, which leads to thread-parallelcomputing tasks interchange with sequential communication tasks. In this paper, we incorporate task parallelism and low-rank approximation into a hybrid task-based Cholesky factorization in a distributed environment and propose some low-rank variants. We evaluate the performance of our programs on both full-rank inputs and low-rank inputs and report the pros and cons of the proposed programs.
Understanding and optimizing the parallel training strategies in the training of large-scale Deep Neural Network (DNN) models is crucial to enhance training efficiency. Existing works tried to demonstrate the layer-le...
详细信息
Understanding and optimizing the parallel training strategies in the training of large-scale Deep Neural Network (DNN) models is crucial to enhance training efficiency. Existing works tried to demonstrate the layer-level information of the computational graph to support parallel training strategy selection. Whereas, the overall parallel execution logic is rarely considered by previous methods. In this paper, we proposed a novel visual analytics approach for parallel training strategies, demonstrating the execution logic of the distributedcomputing from up to bottom via explaining communication operators. Specifically, a computation-communication bipartite construction algorithm is designed for the computational graph visualization. Furthermore, a system is developed to help users easily access the proposed approach and explore the parallel training strategies interactively. With empirical evaluation through a quantitative user study and a qualitative expert interview, the practicality and superiority of the proposed approach is verified.& COPY;2023 Elsevier Ltd. All rights reserved.
In the distribution substation, edge computing can optimize the allocation and utilization of overall distributed resources, which is essential for ensuring efficient energy utilization and stable operation of the pow...
详细信息
Challenges like network latency, bandwidth limitations, and varied node resources are encountered by distributed databases in edge computing environments. This paper examines a distributed database synchronization mec...
详细信息
A Voltage Source Inverter (VSI) is widely used to interface distributed generating sources to AC grid. In a grid connected VSI, the active and reactive powers injected to the grid are controlled. The control dynamics ...
详细信息
Task-based execution frameworks, such as parallel programming libraries, computational workflow systems, and function-as-a-service platforms, enable the composition of distinct tasks into a single, unified application...
详细信息
ISBN:
(纸本)9798350365627;9798350365610
Task-based execution frameworks, such as parallel programming libraries, computational workflow systems, and function-as-a-service platforms, enable the composition of distinct tasks into a single, unified application designed to achieve a computational goal and abstract the parallel and distributed execution of those tasks on arbitrary hardware. Research into these task executors has accelerated as computational sciences increasingly need to take advantage of parallel compute and/or heterogeneous hardware. However, the lack of evaluation standards makes it challenging to compare and contrast novel systems against existing implementations. Here, we introduce TAPS, the Task Performance Suite, to support continued research in distributed task executor frameworks. TAPS provides (1) a unified, modular interface for writing and evaluating applications using arbitrary execution frameworks and data management systems and (2) an initial set of reference synthetic and real-world science applications. We discuss how the design of TAPS supports the reliable evaluation of frameworks and demonstrate TAPS through a survey of benchmarks using the provided reference applications.
distributed, parallel, and gridcomputing are all used in a kind of computing known as cloud computing. It serves as a flexible, affordable, and tried-and-true online delivery platform for IT services marketed to busi...
详细信息
暂无评论