How to achieve precise and coordinated control of greenhouse microclimate factors under strong coupling and nonlinear conditions remains a key challenge in protected agriculture. To address this issue, this study integrates intelligent control and multi-objective optimization to regulate greenhouse temperature and humidity in a coordinated manner. A mechanistic model of a Venlo-type greenhouse was first developed in Matlab R2022a. Then, three control methods, namely LQR, MPC, and NMPC, were compared, and NMPC showed the best performance. Finally, NSGA-II was introduced to optimize the objective function weights of NMPC, further improving the control results. Compared with NMPC alone, the optimized method reduced the RMSE and MAE by 0.3366 and 0.0812 for temperature control, and by 0.2192 and 0.6853 for humidity control, respectively. The proposed method improves the precision and coordination of greenhouse environmental control and provides support for efficient greenhouse production. Ultimately, this study offers a promising technical paradigm for transitioning traditional greenhouse management towards highly autonomous and sustainable precision agriculture.

Persistent low temperatures in autumn and winter have a huge impact on crops, and greenhouses rely on solar radiation and heating equipment to meet the required indoor temperature. But the energy cost of frequent operation of the actuators is exceptionally high. The relationship between greenhouse environmental control accuracy and energy consumption is one of the key issues faced in greenhouse research. In this study, a non-linear model predictive control method with an improved objective function was proposed. The improved objective function used tolerance intervals and boundary constraints to optimize the objective evaluation. The nonlinear model predictive control (NMPC) controller design was based on the wavelet neural network (WNN) data-driven model and applied the interior point method to solve the optimal solution of the objective function control, thus balancing the contradiction between energy consumption and control precision. The simulation results showed that the improved NMPC method reduced energy consumption by 21.02% and 9.54% compared with the model predictive control and regular NMPC, which proved the method achieved good results in a low-temperature environment. This research can provide an important reference for the field as it offers a more efficient approach to managing greenhouse climates, potentially leading to substantial energy savings and enhanced sustainability in agricultural practices.