Optimal Data-Driven Modelling of a Microbial Fuel Cell

Microbial fuel cells (MFCs) are biocells that use microorganisms as biocatalysts to break down organic matter and convert chemical energy into electrical energy. Presently, the application of MFCs alternative sources is limited by their low power attribute. Optimization very important harness optimum In this study, we develop optimal data-driven models for a typical MFC synthesized from polymethylmethacrylate two graphite plates using machine learning algorithms including support vector regression (SVR), artificial neural networks (ANNs), Gaussian process (GPR), ensemble learners. Power density output voltage were modeled different datasets; first dataset has current anolyte concentration features, while second considers oxygen demand features. Hyperparameter optimization was carried out on each considered learning-based Bayesian optimization, grid search, random search arrive at best possible MFC. A model derived having 99% accuracy testing set evaluations.