Predictive Control of Autonomous Greenhouses: A Data-Driven Approach

Abstract

In the past, many greenhouse control algorithms have been developed. However, the majority of these algorithms rely on an explicit parametric model description of the greenhouse. These models are often based on physical laws such as conservation of mass and energy and contain many parameters which should be identified. Due to the complex and nonlinear dynamics of greenhouses, these models might not be applicable to control greenhouses other than the ones for which these models have been designed and identified. Hence, in current horticultural practice these control algorithms are scarcely used. Therefore, the need rises for a control algorithm which does not rely on a parametric system representation but rather on input/output data of the greenhouse system, hereby establishing a way to control the system with unknown or unmodeled dynamics. A recently proposed algorithm, Data-Enabled Predictive Control (DeePC), is able to replace system identification, state estimation and future trajectory prediction by one single optimization framework. The algorithm exploits a non-parametric model constructed solely from input/output data of the system. In this work, we apply this algorithm in order to control the greenhouse climate. It is shown that in numerical simulation the DeePC algorithm is able to control the greenhouse climate while only relying on past input/output data. The algorithm is bench-marked against the Nonlinear Model Predictive (NMPC) algorithm in order to show the differences between a predictive control algorithm that has direct access to the nonlinear greenhouse simulation model and a purely data-driven predictive control algorithm. Both algorithms are compared based on reference tracking accuracy and computational time. Furthermore, it is shown in numerical simulation that the DeePC algorithm is able to cope with changing dynamics within the greenhouse system throughout the crop cycle.

Comparison of behavioral systems theory and conventional linear models for predicting building zone temperature in long-term in situ measurements

“…However, the computation of ARX is faster by orders of magnitude. [21] and [24] report similar ratios for the computation time comparing DeePC to conventional MPC. Furthermore, ARX has fewer tuning parameters.…”

“…However, these are not adaptive. Kerkhof [24] has conducted a simulation study on adaptive DeePC in a greenhouse. However, a very short prediction horizon of one hour is used.…”