An Improved Gradient-Based Optimization Algorithm for Solving Complex Optimization Problems

Saleh Masoud Abdallah Altbawi, Saifulnizam Bin Abdul Khalid, Ahmad Safawi Bin Mokhtar, Hussain Shareef, Nusrat Husain, Ashraf Yahya, Syed Aqeel Haider, Lubna Moin, Rayan Hamza Alsisi

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, an improved gradient-based optimizer (IGBO) is proposed with the target of improving the performance and accuracy of the algorithm for solving complex optimization and engineering problems. The proposed IGBO has the added features of adjusting the best solution by adding inertia weight, fast convergence rate with modified parameters, as well as avoiding the local optima using a novel functional operator (G). These features make it feasible for solving the majority of the nonlinear optimization problems which is quite hard to achieve with the original version of GBO. The effectiveness and scalability of IGBO are evaluated using well-known benchmark functions. Moreover, the performance of the proposed algorithm is statistically analyzed using ANOVA analysis, and Holm–Bonferroni test. In addition, IGBO was assessed by solving well-known real-world problems. The results of benchmark functions show that the IGBO is very competitive, and superior compared to its competitors in finding the optimal solutions with high convergence and coverage. The results of the studied real optimization problems prove the superiority of the proposed algorithm in solving real optimization problems with difficult and indefinite search domains.

Original languageEnglish
Article number498
JournalProcesses
Volume11
Issue number2
DOIs
Publication statusPublished - Feb 2023

Keywords

  • engineering optimization problems
  • gradient-based optimizer
  • improve gradient-based optimizer
  • inertia
  • metaheuristic
  • operator

ASJC Scopus subject areas

  • Bioengineering
  • Chemical Engineering (miscellaneous)
  • Process Chemistry and Technology

Fingerprint

Dive into the research topics of 'An Improved Gradient-Based Optimization Algorithm for Solving Complex Optimization Problems'. Together they form a unique fingerprint.

Cite this