A Machine Learning Method on a Tiny Hardware for Monitoring and Controlling a Hydroponic System

The implementation of artificial intelligence on very tiny chips plays an important role in the future of IoT. Generally, these chips do not conduct artificial intelligence operations locally. They just send collected data to a cloud, where artificial intelligence is located to make the decisions. This leads to time lag and intense dependency of the system on the internet connection that making it unsuitable for systems required immediate action. In a hydroponic system, it is required to control the speed of a pump immediately to control the pH level. But there are many challenges to design the intelligent system using low-powered chips that have low computational power. Therefore, achieving high AI accuracy is very difficult for them. Additionally, the tiny devices need to communicate with the user to conduct IoT operations. To overcome these challenges, in this research a hydroponic system was designed to incorporate an ESP32 chip-based microcontroller with sensors and actuators attached to it to conduct AI on edge and IoT tasks simultaneously. A dedicated android app was implemented to monitor and control the system remotely via IoT. The results show that the predicted pump speed just falls behind the expected speed by an average of 2.94%. The overall designed system is stable and reliable. Komatsuna plants were grown in a hydroponic system and the yield was compared with the plants grown in standard potting compost. The hydroponic system was monitored by the proposed method to produce a higher yield compared to the potting compost.