Optimal techno-economic and thermo-electrical design for a phase change material enhanced renewable energy driven polygeneration unit using a machine learning assisted lattice Boltzmann method

A polygeneration system, in which electricity, heating, cooling, hydrogen, and water are produced, is equipped with PCM for higher technical and economic performance at the same time. The best specifications of PCM, including type and thickness are found based on a multi-objective optimization. Five technical objectives are considered. They are the amount of production of each of the products. On the other hand, levelized cost of energy (LCOE) and payback period (PBP) are the representative of economic side in the multi-objective opti-mization. For lower computation time and cost, an artificial neural network (ANN) has been employed to calculate the amount of heat transfer between solar system (PV and solar collector) and PCM. The created ANN is developed using data generated by lattice Boltzmann method (LBM). It has been then validated and applied for conducting the multi-objective optimization based on techno-economic and thermo-electrical viewpoints, as mentioned. The results have shown that by application of the multi-objective optimization, 16.4, 12.7, 8.4, 10.3, and 9.5% more electricity, heating, cooling, hydrogen, and water production compared to the reference con-dition (system without PCM) are achieved, respectively. Moreover, LCOE is improved by 11.4%, while the corresponding value for PBP is 13.7%.