An efficient renewable hybridization based on hydrogen storage for peak demand reduction: A rule-based energy control and optimization using machine learning techniques

The present study proposes and thoroughly examines a novel approach for the effective hybridization of solar and wind sources based on hydrogen storage to increase grid stability and lower peak load. The parabolic trough collector, vanadium chloride thermochemical cycle, hydrogen storage tank, alkaline fuel cells, thermal energy storage, and absorption chiller make up the suggested smart system. Additionally, the proposed system includes a wind turbine to power the electrolyzer unit and minimize the size of the solar system. A rule-based control technique establishes an intelligent two-way connection with energy networks to compensate for the energy expenses throughout the year. The transient system simulation (TRNSYS) tool and the engineering equation solver program are used to conduct a comprehensive techno-economic-environmental assessment of a Swedish residential building. A four-objective optimization utilizing MATLAB based on the grey wolf algorithm coupled with an artificial neural network is used to determine the best trade-off between the indicators. According to the results, the primary energy saving, carbon dioxide reduction rate, overall cost, and purchased energy are 80.6 %, 219 %, 14.8 $/h, and 24.9 MWh at optimal conditions. From the scatter distribution, it can be concluded that fuel cell voltage and collector length should be maintained at their lowest domain and the electrode area is an ineffective parameter. The suggested renewable-driven smart system can provide for the building's needs for 70 % of the year and sell excess production to the local energy network, making it a feasible alternative. Solar energy is far less effective in storing hydrogen over the winter than wind energy, demonstrating the benefits of combining renewable energy sources to fulfill demand. By lowering CO₂ emissions by 61,758 kg, it is predicted that the recommended smart renewable system might save 7719 $ in environmental costs, equivalent to 6.9 ha of new reforestation.