The electromagnetic transient simulation acceleration algorithm based on delay mitigation of dynamic critical paths

Q2 Energy
Qi Guo, Yuanhong Lu, Jie Zhang, Jingyue Zhang, Libin Huang, Haiping Guo, Tianyu Guo, Liang Tu
{"title":"The electromagnetic transient simulation acceleration algorithm based on delay mitigation of dynamic critical paths","authors":"Qi Guo,&nbsp;Yuanhong Lu,&nbsp;Jie Zhang,&nbsp;Jingyue Zhang,&nbsp;Libin Huang,&nbsp;Haiping Guo,&nbsp;Tianyu Guo,&nbsp;Liang Tu","doi":"10.1186/s42162-025-00516-6","DOIUrl":null,"url":null,"abstract":"<div><p>The task scheduling problem based on directed acyclic graphs (DAGs) has been proven to be NP-complete in general cases or under certain restrictions. In this paper, building upon existing scheduling algorithms, we introduce a static task scheduling algorithm based on directed acyclic graphs. By incorporating the proportion of task transmission delay as a guiding metric in the optimization process, processors can be prioritized for tasks with high latency, thereby improving computational efficiency. We first validate the theoretical feasibility of the algorithm using a theoretical case study and illustrate the algorithmic effectiveness using two real case studies, direct current (DC) model and alternating current (AC) model respectively. The research indicates that the scheduling algorithm proposed in this paper achieves an average scheduling length improvement of over 1.2% compared to the Heterogeneous Earliest-Finish-Time algorithm (HEFT) in topologies with high latency tasks. Additionally, the experiments show that the HEFT algorithm consumes 39.85us and the EMT-DM algorithm consumes 38.29us during simulation using DC, and the HEFT algorithm consumes 31.23us and the EMT-DM algorithm consumes 26.51us during simulation using AC, both of which are improved compared to the HEFT algorithm.</p></div>","PeriodicalId":538,"journal":{"name":"Energy Informatics","volume":"8 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://energyinformatics.springeropen.com/counter/pdf/10.1186/s42162-025-00516-6","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy Informatics","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1186/s42162-025-00516-6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Energy","Score":null,"Total":0}
引用次数: 0

Abstract

The task scheduling problem based on directed acyclic graphs (DAGs) has been proven to be NP-complete in general cases or under certain restrictions. In this paper, building upon existing scheduling algorithms, we introduce a static task scheduling algorithm based on directed acyclic graphs. By incorporating the proportion of task transmission delay as a guiding metric in the optimization process, processors can be prioritized for tasks with high latency, thereby improving computational efficiency. We first validate the theoretical feasibility of the algorithm using a theoretical case study and illustrate the algorithmic effectiveness using two real case studies, direct current (DC) model and alternating current (AC) model respectively. The research indicates that the scheduling algorithm proposed in this paper achieves an average scheduling length improvement of over 1.2% compared to the Heterogeneous Earliest-Finish-Time algorithm (HEFT) in topologies with high latency tasks. Additionally, the experiments show that the HEFT algorithm consumes 39.85us and the EMT-DM algorithm consumes 38.29us during simulation using DC, and the HEFT algorithm consumes 31.23us and the EMT-DM algorithm consumes 26.51us during simulation using AC, both of which are improved compared to the HEFT algorithm.

基于动态关键路径延迟缓解的电磁瞬态仿真加速算法
基于有向无环图(dag)的任务调度问题在一般情况下或在一定条件下是np完全的。本文在现有调度算法的基础上,提出了一种基于有向无环图的静态任务调度算法。通过将任务传输延迟的比例作为优化过程的指导指标,可以对高延迟的任务进行处理器优先级排序,从而提高计算效率。我们首先通过理论案例研究验证了算法的理论可行性,并分别通过直流(DC)模型和交流(AC)模型两个实际案例研究说明了算法的有效性。研究表明,与异构最早完成时间算法(HEFT)相比,本文提出的调度算法在具有高延迟任务的拓扑中平均调度长度提高了1.2%以上。此外,实验表明,在直流仿真中,HEFT算法的功耗为39.85us, EMT-DM算法的功耗为38.29us;在交流仿真中,HEFT算法的功耗为31.23us, EMT-DM算法的功耗为26.51us,均比HEFT算法有所提高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Energy Informatics
Energy Informatics Computer Science-Computer Networks and Communications
CiteScore
5.50
自引率
0.00%
发文量
34
审稿时长
5 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信