Smart greenhouse control under harsh climate conditions based on data-driven robust model predictive control with principal component analysis and kernel density estimation

Abstract

Efficient greenhouse climate control under harsh climate conditions at locations such as Qatar is a challenge because of the high temperature and high relative humidity. This work presents an application of a data-driven robust model predictive control for intelligent control of greenhouse indoor climate in Qatar. The framework integrates dynamic control models of temperature, CO2 concentration level, and humidity of a greenhouse with a data-driven robust optimization framework that accurately and rigorously captures uncertainty in weather forecast error. A machine learning approach combining principal component analysis (PCA) with kernel density estimation (KDE) is adopted to construct data-driven uncertainty sets for temperature, solar radiation, and humidity from historical data. The optimal control inputs that minimize control costs and state violations are obtained by solving a data-driven robust optimization problem at each time step. The application of controlling a greenhouse growing tomatoes located in Doha, Qatar is presented. The results suggest that the proposed PCA and KDE-based data-driven robust model predictive control approach needs lower total control cost than rule-based control and other model predictive control to maintain the greenhouse climate for supporting crop production under harsh climate conditions.