Institut for Forretningsudvikling og Teknologi

Implementation of APSO and Improved APSO on Non-Cascaded and Cascaded Short Term Hydrothermal Scheduling

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

DOI

  • Muhammad Salman Fakhar, University of Engineering and Technology Lahore
  • ,
  • Syed Abdul Rahman Kashif, University of Engineering and Technology Lahore
  • ,
  • Sheroze Liaquat, National University of Computer and Emerging Sciences, Lahore
  • ,
  • Akhtar Rasool, Sharif College of Engineering and Technology
  • ,
  • Sanjeevikumar Padmanaban
  • Muhammad Ahmad Iqbal, University of Engineering and Technology Lahore
  • ,
  • Muhammad Anas Baig, University of Engineering and Technology Lahore
  • ,
  • Baseem Khan, Hawassa University

Short-term hydrothermal scheduling (STHTS) is a highly non-linear, multi-model, non-convex, and multi-dimensional optimization problem that has been worked upon for about 5 decades. Many research articles have been published in solving different test cases of STHTS problem, while establishing the superiority of one type of optimization algorithm over the type, in finding the near global best solution of these complex problems. This paper presents the implementation of an improved version of a variant of the Particle Swarm Optimization algorithm (PSO), known as Accelerated Particle Swarm Optimization (APSO) on three benchmark test cases of STHTS problems. The adaptive and variable nature of the local and global search coefficients for the proposed APSO significantly improve its performance in obtaining the optimal solution for the STHTS test cases. Two of these cases are non-cascaded cases of STHTS problem (NCSTHTS) and one case is cascaded case of STHTS problem (CSTHTS). The results are compared with the results of the previous implementations of the other algorithms as presented in the literature. Due to the stochastic nature of the meta-heuristic algorithms, the parametric and non-parametric statistical tests have been implemented to establish the superiority of results of one type of algorithm over the results of the other type of algorithms.

OriginalsprogEngelsk
TidsskriftIEEE Access
Vol/bind9
Sider (fra-til)77784-77797
Antal sider14
ISSN2169-3536
DOI
StatusUdgivet - 2021

Bibliografisk note

Publisher Copyright:
CCBY

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Se relationer på Aarhus Universitet Citationsformater

ID: 218776310