Optimal Lighting Control in Greenhouses Using Bayesian Neural Networks for Sunlight Prediction

TL;DR

This paper presents a cost-effective greenhouse lighting control method using Bayesian Neural Networks for accurate sunlight prediction, significantly reducing electricity costs compared to traditional prediction and heuristic approaches.

Contribution

It introduces a novel BNN-based sunlight prediction model integrated into an optimal lighting control strategy for greenhouses, improving cost efficiency.

Findings

BNN model achieves high prediction accuracy (R^2=0.9971, RMSE=1.8%)

Cost reduction of 2.27% compared to Markov prediction

Cost reduction of 43.91% compared to heuristic method

Abstract

Controlling the environmental parameters, including light in greenhouses, increases the crop yield; however, the electricity cost of supplemental lighting can be high. Therefore, the importance of applying cost-effective lighting methods arises. In this paper, an optimal supplemental lighting control approach is developed considering a variational inference Bayesian Neural Network (BNN) model for sunlight prediction. The predictive model is validated through testing the model on the historical solar data of a site located at North Carolina ($R^{2}$=0.9971, RMSE=1.8%). The proposed lighting approach is shown to minimize electricity cost by considering the BNN-based sunlight prediction, plant light needs, and variable electricity pricing when solving the underlying optimization problem. For evaluation, the new strategy is compared to: 1) a Markov-based prediction method, which solves the same optimization problem, assuming a Markov model for sunlight prediction; 2) a heuristic method which aims to supply a fixed amount of light. Simulation studies are conducted to examine the electricity cost improvements of the BNN-based approach. The results show that the BNN-based approach reduces cost by (on average) 2.27% and 43.91% compared to the Markov prediction-based method and the heuristic method, respectively, throughout a year.