Development and Implementation of an IoT-Enabled Optimal and Predictive Lighting Control Strategy in Greenhouses

Area of Science:

• Agricultural Engineering
• Horticultural Science
• Smart Agriculture

Background:

• Increasing global population necessitates enhanced food production, driving agricultural innovation.
• Internet of Things (IoT) adoption in agriculture addresses challenges in conventional farming.
• Controlling greenhouse environmental parameters, like light, is crucial for crop yield, but supplemental lighting incurs high electricity costs.

Purpose of the Study:

• To develop and implement an optimal supplemental lighting approach for greenhouses using IoT technology.
• To minimize electricity costs associated with supplemental lighting in greenhouse cultivation.
• To evaluate the effectiveness of the proposed lighting strategy on crop growth and cost-efficiency.

Main Methods:

• Developed an IoT-based optimal supplemental lighting system.
• Integrated Markov-based sunlight prediction, plant light requirements, and variable electricity pricing.
• Conducted two experimental studies on "Green Towers" lettuce (Lactuca sativa) in a research greenhouse during winter and spring.
• Compared the proposed strategy against a heuristic lighting method.

Main Results:

• The proposed optimal lighting approach reduced electricity costs by 4.16% in winter and 33.85% in spring compared to the heuristic method.
• Statistical analysis (paired t-test) indicated no significant difference in crop growth parameters between the two lighting methods.
• The strategy effectively balanced electricity cost reduction with consistent plant development.

Conclusions:

• The developed IoT-based optimal supplemental lighting approach is a cost-effective solution for greenhouse cultivation.
• This method successfully reduces energy expenditure without compromising lettuce growth.
• The findings support the integration of smart technologies for sustainable and economical agricultural practices.