Optimal 6E design of an integrated solar energy-driven polygeneration and CO2 capture system: A machine learning approach

Renewable energy-driven decentralized polygeneration systems herald great potential in tackling climate change issues and promoting sustainable development. In this light, study introduces a new machine learning-based multi-objective optimization approach of an integrated solar CO2 capture system for meeting greenhouse’s power, freshwater, demands. The solar-assisted comprises 486-kW gas turbine, two steam turbines, organic Rankine cycles, humidification-dehumidification desalination unit to recover waste heat while producing post-combustion unit. proposed is mathematically modelled evaluated via dynamic simulation implemented MATLAB software. Moreover, sensitivity analysis conducted identify the most influential decision variables on performance. strategy combines Genetic Programming (GP) Artificial Neural Networks (ANN) minimize total costs, environmental impacts, economic emergy rates whilst maximizing exergy efficiency freshwater production. Finally, performance further investigated through comprehensive Energy, Exergy, Exergoeconomic, Exergoenvironmental, Emergoeconomic, Emergoenvironmental (6E) analyses. three-objective reduces monthly rate by 11.4%, 34.31% 6.38%, respectively. Furthermore, reductions up 56.81%, 50.19% 77.07%, respectively, are obtained previous indicators four-objective model. Hence, methodology represents valuable tool decision-makers implementing more cost-effective environment-friendly systems.