Minimizing Electricity Cost through Smart Lighting Control for Indoor Plant Factories

TL;DR

This paper presents a smart lighting control system for indoor lettuce farming that uses plant growth modeling and genetic algorithms to optimize lighting schedules, significantly reducing electricity costs and improving crop growth.

Contribution

It introduces a novel optimization approach combining plant growth modeling and genetic algorithms for energy-efficient lighting control in smart farming.

Findings

Achieved 40-52% energy cost savings in simulations.

Up to 6% increase in lettuce leaf area.

Demonstrated effectiveness of genetic algorithms for scheduling.

Abstract

Smart plant factories incorporate sensing technology, actuators and control algorithms to automate processes, reducing the cost of production while improving crop yield many times over that of traditional farms. This paper investigates the growth of lettuce (Lactuca Sativa) in a smart farming setup when exposed to red and blue light-emitting diode (LED) horticulture lighting. An image segmentation method based on K-means clustering is used to identify the size of the plant at each stage of growth, and the growth of the plant modelled in a feed forward network. Finally, an optimization algorithm based on the plant growth model is proposed to find the optimal lighting schedule for growing lettuce with respect to dynamic electricity pricing. Genetic algorithm was utilized to find solutions to the optimization problem. When compared to a baseline in a simulation setting, the schedules proposed by the genetic algorithm can achieved between 40-52% savings in energy costs, and up to a 6% increase in leaf area.