MQTT Protocol based Smart Greenhouse Environment Monitoring System using Machine Learning
G. Sai Teja1, P. Sathish2

1G. Sai Teja, Department of Electronics and Communication, CBIT, Hyderabad, India.
2P. Sathish Department of Electronics and Communication, CBIT, Hyderabad, India.
Manuscript received on June 21, 2020. | Revised Manuscript received on June 30, 2020. | Manuscript published on July 10, 2020. | PP: 278-285 | Volume-9 Issue-9, July 2020 | Retrieval Number: 100.1/ijitee.I7149079920 | DOI: 10.35940/ijitee.I7149.079920
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Internet of Things (IoT) allows connections among various devices using the internet with the ability to gather and exchange data. IoT has various connecting protocols like HTTPS, MQTT, CoAP, SMCP, etc. A lightweight protocol of all these protocols is the Message Queuing Telemetry Transport (MQTT) protocol. Agriculture is the backbone of India it plays a significant role in the growth of the economics of the country. The majority of the population in India focused on developing a good yield of the crop at their available space which is leading to the development of various greenhouse and smart farming methods. The technology developments will be enabling to design and develop a simple intelligent system for smart farming and maintaining the greenhouse environment. The proposed system is designed using an ARM Cortex processor with the other supporting peripherals for monitoring and constantly updating and controlling environmental parameter values to achieve optimal growth and yield of plants. In this paper, the proposed system consists of several sensors for measuring different parameters including temperature, humidity, soil moisture, air pressure, and fertilizer content. Further, the obtained data is sent to the cloud by using IoT based Thing Speak with the secured MQTT protocol to monitor the parameters. An efficient Machine Learning algorithm is developed to predict the parameters like soil moisture, fertilizer content sprayed and weather data i.e., humidity, and temperature. The accuracy obtained using Machine Learning algorithm i.e. Decision Tree method is 97%. 
Keywords: Machine Learning, MQTT, IoT, ARM, Thing Speak.
Scope of the Article: Machine Learning