Improved metaheuristic optimization algorithm applied to hydrogen fuel cell and photovoltaic cell parameter extraction

En Jui Liu, Yi Hsuan Hung, Che Wun Hong

Research output: Contribution to journalArticlepeer-review

Abstract

As carriers of green energy, proton exchange membrane fuel cells (PEMFCs) and photovoltaic (PV) cells are complex and nonlinear multivariate systems. For simulation analysis, optimization control, efficacy prediction, and fault diagnosis, it is crucial to rapidly and accurately establish reliability modules and extract parameters from the system modules. This study employed three types of particle swarm optimization (PSO) algorithms to find the optimal parameters of two energy models by minimizing the sum squared errors (SSE) and roots mean squared errors (RMSE). The three algorithms are inertia weight PSO, constriction PSO, and momentum PSO. The obtained calculation results of these three algorithms were compared with those obtained using algorithms from other relevant studies. This study revealed that the use of momentum PSO enables rapid convergence (under 30 convergence times) and the most accurate modeling and yields the most stable parameter extraction (SSE of PEMFC is 2.0656, RMSE of PV cells is 8.839 × 10−4 ). In summary, momentum PSO is the algorithm that is most suitable for system parameter identification with multiple dimensions and complex modules.

Original languageEnglish
Article number619
JournalEnergies
Volume14
Issue number3
DOIs
Publication statusPublished - 2021 Feb 1

Keywords

  • Metaheuristic optimization algorithm
  • Particle swarm algorithm
  • Photovoltaic cell
  • Proton exchange membrane fuel cell

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Fuel Technology
  • Energy Engineering and Power Technology
  • Energy (miscellaneous)
  • Control and Optimization
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Improved metaheuristic optimization algorithm applied to hydrogen fuel cell and photovoltaic cell parameter extraction'. Together they form a unique fingerprint.

Cite this