Modeling Energy LED Light Consumption Based on an Artificial Intelligent Method Applied to Closed Plant Production System

Artificial lighting is a key factor in Closed Production Plant Systems (CPPS). A significant light-emitting diode (LED) technology attribute the emission of different wavelengths, called light recipes. Light recipes are typically configured continuous mode, but can also be pulsed mode to save energy. We propose two nonlinear models, i.e., genetic programing (GP) and feedforward artificial neural networks (FNNs) predict energy consumption CPPS. The generated models use following input variables: intensity, red component, blue green white component; operation modes: including frequency, duty cycle as well output. Spearman’s correlation was applied generate model with only representative inputs. Two datasets were applied. first (Test 1), 5700 samples similar ranges, used train evaluate, while second 2), included 160 total datapoints ranges. metrics that allowed quantitative evaluation model’s performance MAPE, MSE, MAE, SEE. Our implemented achieved an accuracy 96.1% for GP 98.99% FNNs model. this proposal or programmed part monitoring system CPPS which prioritize efficiency. provide further analysis savings due recipe on LED systems.