Indoor Farming: Comparative Study Based on Internet of Things –A Fuzzy SWARA-TODIM Approach

Abstract

Introduction: Indoor farming has emerged as a sustainable solution to meet the increasing demand for fresh produce while minimizing environmental impact.

This study aims to optimize a sustainable integrated vertical farming (SIVF) system by integrating some indoor farming methods in a complex multi-criteria decision-making challenge.

Objectives: Develop an artificial intelligence approach for monitoring and analyzing data from automated indoor farming systems.

The optimized SIVF system was designed with AI sensors to create a modern agriculture.

Methods: This study integrates SWARA and TODIM methods to address the MCDM problem with unknown weights.

The proposed method was solved in two processes: PyCuFN and PyFN environments for conduct a comparative study based on a real life MCDM problem.

Results: The results show a significant reduction in water consumption and energy usage in the optimized indoor farming system.

The comparison between two processes reveals minimal impact on the overall decision values and rank orders, indicating the robustness of the proposed method.

Conclusions: The study demonstrates the effectiveness of the SWARA-TODIM method and AI sensors in optimizing the SIVF system. The proposed method's ability to be solved in different environments adds to its flexibility and applicability in various contexts.