Deep Neural Network based Optimal Control of Greenhouses

TL;DR

This paper presents a two-level control system for greenhouses that uses deep neural networks trained via NMPC to enable real-time, efficient control despite complex nonlinear dynamics.

Contribution

The novel approach combines NMPC with deep neural networks to achieve real-time control of greenhouse environments, reducing computational complexity.

Findings

Effective control under real-time disturbances demonstrated in simulations

Deep neural networks successfully learned control policies from NMPC data

Reduced computational time compared to traditional NMPC methods

Abstract

Automatic control of greenhouse crop production is of great interest owing to the increasing energy and labor costs. In this work, we use two-level control, where the upper level generates suitable reference trajectories for states and control inputs based on day-ahead predictions. These references are tracked in the lower level using Nonlinear Model Predictive Control (NMPC). In order to apply NMPC, a model of the greenhouse dynamics is essential. However, the complex nature of the underlying model including discontinuities and nonlinearities results in intractable computational complexity and long sampling times. As a remedy, we employ NMPC as a data generator to learn the tracking control policy using deep neural networks. Then, the references are tracked using the trained Deep Neural Network (DNN) to reduce the computational burden. The efficiency of our approach under real-time disturbances is demonstrated by means of a simulation study.