Enhancing Greenhouse Efficiency with IoT and Reinforcement Learning
Author Information
Author(s): Platero-Horcajadas Manuel, Pardo-Pina Sofia, Cámara-Zapata José-María, Brenes-Carranza José-Antonio, Ferrández-Pastor Francisco-Javier
Primary Institution: University of Alicante
Hypothesis
Can integrating IoT and reinforcement learning optimize climate control in greenhouses?
Conclusion
The integration of IoT and reinforcement learning technologies effectively manages and optimizes greenhouse operations, leading to significant energy savings and improved temperature control.
Supporting Evidence
- The integration of IoT and RL technologies enhances operational efficiency in greenhouses.
- Energy savings of up to 45% were observed during cooling processes.
- RL-based control maintained desired temperature ranges more effectively than traditional methods.
- The study validates the practical implementation of RL models in real-world greenhouse settings.
Takeaway
This study shows that using smart technology can help greenhouses grow plants better while saving energy and reducing the need for constant human help.
Methodology
The study used a Q-learning algorithm to optimize greenhouse climate control based on real-time data from IoT sensors.
Limitations
The study may not account for all environmental variables affecting greenhouse performance.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website