Multi-objective optimization of greenhouse light environment based on NSGA-II algorithm

It is important to study the optimization and control of greenhouse light environment for improving the production efficiency and economic benefit of greenhouse crops. However, the current optimization methods of greenhouse light environment are mainly to meet the needs of crop photosynthesis, ignoring the cost of energy consumption in the process of light supplement. Therefore, this paper establishes a multi-objective optimization model for optimizing two indices, including the photosynthetic rate of crop and the cost of energy consumption. Meanwhile, aiming at the problem that it is difficult to accurately measure the photosynthetic rate of crop online, an improved least squares support vector machine (LSSVM) is used to establish a soft sensing model of crop photosynthetic rate, which can accurately predict the photosynthetic rate, and the model is introduced into the optimization model. On this basis, a fast elitist non-dominated sorting genetic algorithm (NSGA-II) is used to solve the multi-objective optimization model, and the experimental results show the effectiveness of the model and optimization algorithm.