Dynamic multi-objective optimization of a solar-based combined cooling, heating, and power (CCHP) system based on the data-driven model

• A solar CHP system has been analyzed dynamically over a year. • Using Data-driven model to Dynamic Multi-objective Optimization. • Using MLM to reduce the modeling time from 12 h to 10 s. • Generating data for neural network training to model CCHP systems. • The system has been optimized in three various scenarios. Solar-based Combined Cooling, Heating, and Power (CCHP) systems represent a promising pathway toward sustainable energy generation, but they often involve high capital investment and complex operational behavior. Therefore, optimizing their performance is essential to ensure both energy efficiency and economic viability. Moreover, the inherently dynamic nature of solar energy and the time-dependent behavior of these systems necessitate dynamic optimization approaches that can capture real-world variability. In this study, a dynamic simulation is conducted over a full year, and a data-driven modeling framework based on artificial neural networks is developed to significantly reduce computational time while preserving the system’s dynamic characteristics. The trained models are incorporated into a multi-objective optimization process using the Non-dominated sorting genetic algorithm II (NSGA-II algorithm), targeting energy efficiency and net present value. Results show that the proposed approach enables rapid and reliable optimization of solar CCHP systems and supports their practical deployment under realistic, time-varying condition. In the case study, the maximum annual energy efficiency and net present value (NPV) achieved through single-objective optimization were 51.09% and 5.68 million USD, respectively. Under two-objective optimization, the system achieved an annual efficiency of 43.27% and an NPV of 4.94 million USD. Owing to its minimal computational burden, the proposed framework can be readily employed by system designers to gain valuable insights into identifying the most efficient and economically viable configurations of solar Combined Cooling, Heating, and Power (CCHP) systems.