A Knowledge Guided Multi-Population Evolutionary Algorithm for Dynamic Workflow Scheduling Problem

Jingyuan XU, Jiajian YANG, Peiru LI, Ziming WANG, Changwu HUANG, Xin YAO

Research output: Other Conference ContributionsConference Paper (other)Other Conference Paperpeer-review

Abstract

The workflow scheduling problem is a fundamental task in cloud computing. This paper addresses the challenge of workflow scheduling in dynamic and uncertain cloud environments, where computing resources may become inaccessible due to hardware or software failures. To tackle this challenge, we propose a novel algorithm called the Order Feature Guided Multi-Population (OFGMP) algorithm for dynamic workflow scheduling in cloud environments. The OFGMP algorithm utilizes a multi-population evolutionary framework, incorporating a knowledge-guided reproduction operator that leverages the order feature of solutions, as well as repair mechanisms to adapt to changing environmental conditions. Extensive experiments are conducted to validate the algorithm’s performance against existing dynamic scheduling approaches. The experimental results demonstrate the superiority of our proposed method over others on a number of test cases.
Original languageEnglish
Pages21-28
Number of pages8
DOIs
Publication statusPublished - 2024
Event2024 IEEE Conference on Artificial Intelligence (CAI) - Singapore, Singapore
Duration: 25 Jun 202427 Jun 2024

Conference

Conference2024 IEEE Conference on Artificial Intelligence (CAI)
Period25/06/2427/06/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • Cloud Computing
  • Evolutionary Algorithm
  • Multi-objective Optimization
  • Workflow Scheduling Problem

Fingerprint

Dive into the research topics of 'A Knowledge Guided Multi-Population Evolutionary Algorithm for Dynamic Workflow Scheduling Problem'. Together they form a unique fingerprint.

Cite this