Self-organizing multi-agent collaborative decision-making system

Abstract

In the context of smart agriculture, the use of self-organizing computing systems becomes essential for optimizing monitoring and control processes. This study proposes a decision-making system based on a multi-agent architecture, capable of collecting, analyzing, and managing real-time data using technologies such as the Internet of Things (IoT) and edge computing. The system is designed to autonomously adapt to the dynamic conditions of the agricultural environment by integrating nature-inspired computing algorithms, such as swarm intelligence and cellular computing. By leveraging genetic algorithms and Pareto optimization, the system identifies optimal solutions for resource management and productivity enhancement. This approach enables early anomaly detection and real-time adjustment of operational strategies to reduce water, fertilizer, and energy consumption. The experimental results demonstrate the efficiency and reliability of the proposed system, highlighting the advantages of using self-organizing computing systems in the context of smart agriculture.