New hybrid photovoltaic-fuel cell system for green hydrogen and power production: performance optimization assisted with Gaussian process regression method

This paper endeavors to utilize the numerical modeling method to evaluate the energy, economic, and environmental performances of a new hybrid PV-FC system for green hydrogen and electricity production. The proposed system consists of photovoltaic panels, fuel cells, an electrolyzer, a converter, and a hydrogen storage tank. A robust techno-enviro-economic (3E) analysis is conducted through comprehensive modeling for the system components using MATLAB/Simulink?. In this validated model, the essential parameters have been calculated: PV plant power, area and efficiency, electrolyzer efficiency, flow rate and power, stack power, area and efficiency, total LCOE of the integrated components, and CO2 emission reduction. Moreover, the NSGA-II coupled with TOPSIS decision-making approach and Gaussian Process Regression machine learning method with selection kernel function are also utilized as a novel inclusion for the prediction and optimization of the 3E performances of this hybrid system. To obtain a multidimensional view of the optimization, six key decision variables of total stack power, fossil fuel-based generator energy, total CO2 emissions coming from hydrogen production, total FC system voltage, module area, and number of PV modules have been adopted. The optimization problem encompasses maximizing the total fuel cell stack power and carbon emission reduction, while simultaneously minimizing the total stack area and levelized cost of energy. The simulation outcomes reveal that the stack can reach its maximum output power of 350 kW when operating temperatures are between 40 ?C and 55 ?C and there are more than 380 cells in the stack. Also, the LCOE was found to be less than $2/kWh for solar radiation above 250 W/m2 and PV outputs reaching 100 W. Further, Increasing FCs from 10 to 400 reduces CO2 emissions by roughly 13% at 100 ?C. Ultimately, the optimal configuration of the system yields stack power of 1589 kW, a total stack area of 269.9 m2, and total CO2 emission reduction of 1268 tonCO2, respectively.