Intelligent multi-agent system for water reduction in automotive irrigation processes

Abstract

This paper deals with a multi-agent system (MAS) to automate the gathering and managing of information from potato crops in order to provide a precision irrigation system. The proposal and development of a novel MAS is presented based on different agent subsystems with specific objectives to meet the main objective of the global MAS. The proposed MAS has been developed on the Cloud Computing paradigm and is able to gather data from wireless sensor networks (WSNs) located in potato crops for knowledge discovery and decision making. According to the collected information as historical data by the MAS, it can make decision on an actuator set that modify the irrigation system by updating the areas of the crop with most irrigation needs. The use of these intelligent technologies in rural areas provides a considerable saving of resources and improves the efficiency and effectiveness of agricultural production systems. The architecture has been tested in an agricultural environment in order to optimize irrigation in a potato crop. The results showed a significant reduction in comparison to traditional automotive irrigation.