Asistente electrónico de agricultura hidropónica aplicando Machine Learning

Abstract

This research paper details the implementation of an electronic assistant for hydroponic agriculture applying machine learning. The assistant was implemented in the Puerto Arturo Sector an NFT (Nutrient Film Technique) system; The wizard allows you to control the ranges of pH, Total Dissolved Solids (TDS) and Electrical Conductivity of the nutrient solution of the hydroponic system with a command issued by the "K Nearby Neighbors" algorithm configured on a cloud server, in order to provide constant and precise control of nutrient solution rates for leafy vegetable crops. The assistant has two electronic boards with Wi-Fi that connect to the local area network of the greenhouse to send and receive the necessary data for the supervision and control of the nutrient solution of the NFT system. The assistant uses the MQTT (Message Queue Telemetry Transport) protocol that allows communication between the electronic boards, facilitates the creation of a server in the cloud and allows the configuration of the machine learning algorithm to use it as a command for the assistant's actuators. In addition, it has a mobile and web interface that allows monitoring the data and selecting the type of control of the nutrient solution, on the other hand, the assistant sends alerts when the monitoring ranges change to atypical values and restricts the activation of the dosing pumps of the NFT system.