This article explains how screen optimization functions within Crop Controller to enhance energy savings while maintaining an optimal greenhouse climate.

---

How the Algorithm Works   

The screen optimization module focuses on two key objectives:

1. Achieving the optimal climate by adjusting screen positions based on greenhouse conditions.
2. Saving energy through a predictable pattern that follows the growers’ strategy

The module determines the best moments to open and close screens using weather forecasts. These moments may vary daily based on predicted conditions.

Setting up screen settings: Getting started – screens

---

Aligning with Shading, Blackout & Gap Control

The goal of the screens module is to create an optimal climate while maximizing energy efficiency. When active, it sends optimal screen operation setpoints to the climate computer, ensuring seamless integration with other screen functions:

• Shading: During shading periods, Crop Controller allows the climate computer to manage screen operation. In case no energy saving is expected. Crop Controller will not interfere with the shading function of the climate computer
• Blackout: Crop Controller ensures blackout screens remain closed when necessary. However, we recommend configuring blackout functions directly in the climate computer, as these override all other settings.
• Gap Control: Crop Controller sends opening and closing setpoints at the ideal moments. The gap control function is left to the climate computer.

---

Learning from historical data

• The screen optimization module learns from historical greenhouse behaviour to better predict how the climate will evolve under different circumstances. It does this by analyzing past screen actions together with the influences configured in the climate computer. These influences—such as radiation thresholds, humidity limits, temperature targets, or wind‑based ventilation rules—shape how the climate computer controls the greenhouse. Crop Controller does not copy these influences; instead, it learns the climate dynamics that result from them.
• This learning process is especially important during transition moments, where climate responses are subtle and highly dependent on weather conditions. For example, around sunset, the system evaluates how quickly the temperature drops after the screens close and how this affects climate stability throughout the night. On cold days, it learns whether keeping the screen closed after sunrise helps retain enough energy to justify the temporary reduction in radiation.
• Each type of screen moment is modeled separately to ensure the right learnings are applied to each situation: shading during warm periods, irradiation screening before sunset, or daytime energy screening during cold spells. This allows the system to tailor decisions to the specific purpose of the screen action instead of treating all closed‑screen periods as equal.
• By learning from historical patterns and the resulting climate dynamics, the module continuously improves its predictions, enabling more accurate and energy‑efficient screen operation.

---