Amazing technological breakthrough possible @S-Logix pro@slogix.in

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • pro@slogix.in
  • +91- 81240 01111

Social List

Chaotic-nondominated-sorting Owl Search Algorithm for Energy-aware Multi-Workflow Scheduling in Hybrid Clouds - 2022

Research Area:  Cloud Computing

Abstract:

Since a single private cloud cannot satisfy the increasing computing requirements for executing multiple workflows simultaneously, hybrid clouds are preferred to do so. However, multi-workflow scheduling is challenging as users may request various workflows with different quality of service (QoS) requirements. This work proposes a Chaotic-non-dominated-sorting Owl Search Algorithm (COSA) by combining an Owl Search Algorithm (OSA) with a Non-dominated Sorting Genetic Algorithm II (NSGA-II) to do so with makespan, cost and energy consumption minimized for each workflow given deadline and budget constraints. First, a hierarchical evolving mechanism is designed to update the better half and worse half of population by NSGA-II and OSA, respectively to guarantee a good trade-off between exploration and exploitation. Second, a chaotic sequence is introduced to adaptively adjust OSAs step size during population evolution for better exploration. Third, we adopt a chaotic operator for searching around the resulting non-dominated solutions to improve COSAs local search ability. Experiments are conducted to compare COSA with four state-of-the-art ones. The results demonstrate that it outperforms them in terms of diversity preservation, convergence towards a true Pareto front and the number of non-dominated solutions. In particular, it can find at least 19% more NDS than its peers.

Author(s) Name:  Huifang Li; Guanghao Xu; Danjing Wang; Mengchu Zhou; Yan Yuan; Ahmed Alabdulwahab

Journal name:  IEEE Transactions on Sustainable Computing

Conferrence name:  

Publisher name:  IEEE

DOI:  10.1109/TSUSC.2022.3144357

Volume Information:  Page(s): 1 - 1