Abstract

In this paper, we present the development and evaluation of a smart indoor farming prototype designed for precision agriculture. The system integrates multiple environmental sensors, including temperature, humidity, light and CO₂ sensors, with real-time monitoring and control via Raspberry Pi and Microsoft Azure IoT Hub. A four-dimensional logistic growth model was implemented to simulate and predict plant growth dynamics across biomass, plant height, leaf area and chlorophyll content. Experimental trials were conducted using adaptive lighting and nutrient control strategies across three treatment groups. Results show a clear enhancement in photosynthetic efficiency, as indicated by a progressive increase in SPAD values from 31.2 to 35.4 over eight weeks. The system effectively responded to environmental changes, demonstrating the feasibility and performance of IoT-based smart agriculture platforms. This work contributes a scalable and sustainable framework for integrating hardware, data analytics and AIdriven growth optimization in controlled agricultural environments.

Keywords:Indoor Farming; IoT-Based agriculture; Smart greenhouse; Light intensity control; Azure IoT hub; Raspberry Pi