.png){kind=icon}
返回
A Multi-Strategy Siberian Tiger Optimization Algorithm for Task Scheduling in Remote Sensing Data Batch Processing
.png){kind=icon}
OA
AI
DOI：10.3390/biomimetics9110678.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With advancements in integrated space-air-ground global observation capabilities, the volume of remote sensing data is experiencing exponential growth. Traditional computing models can no longer meet the task processing demands brought about by the vast amounts of remote sensing data. As an important means of processing remote sensing data, distributed cluster computing's task scheduling directly impacts the completion time and the efficiency of computing resource utilization. To enhance task processing efficiency and optimize the allocation of computing resources, this study proposes a Multi-Strategy Improved Siberian Tiger Optimization (MSSTO) algorithm based on the original Siberian Tiger Optimization (STO) algorithm. The MSSTO algorithm integrates the Tent chaotic map, the L & eacute;vy flight strategy, Cauchy mutation, and a learning strategy, showing significant advantages in convergence speed and global optimal solution search compared to the STO algorithm. By combining stochastic key encoding schemes and uniform allocation encoding schemes, taking the task scheduling of aerosol optical depth retrieval as a case study, the research results show that the MSSTO algorithm significantly shortens the completion time (21% shorter compared to the original STO algorithm and an average of 15% shorter compared to nine advanced algorithms, such as a particle swarm algorithm and a gray wolf algorithm). It demonstrates superior solution accuracy and convergence speed over various competing algorithms, achieving the optimal execution sequence and machine allocation scheme for task scheduling.
Keyword:
workflow
task scheduling
remote sensing data
Siberian Tiger Optimization
metaheuristic
optimal assignment
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
B
IF:
3.9
论文数:
3.2K
被引数:
5.1K
机构
暂无机构信息
引用论文
.png){kind=icon}
A Review on Swarm Intelligence and Evolutionary Algorithms for Solving Flexible Job Shop Scheduling Problems求解柔性作业车间调度问题的群体智能和进化算法综述OAAI
OAAI分享收藏分享收藏分享收藏Golden jackal optimization: A novel nature-inspired optimizer for engineering applicationsGolden jackal优化: 一种用于工程应用的新颖的自然启发优化器
PREAI
分享收藏分享收藏
查看更多内容