Use of multi-agent systems and the Internet of Things to monitor the environment of commercial broiler poultry houses through specific air enthalpy

Abstract

The intensive production system for broilers requires the availability of an environment (aviary) that promotes an artificial microclimate that favors both animal well-being and productive performance; therefore, monitoring this environment is critical for production success, especially in tropical countries. This criticality opens up a range of research opportunities for monitoring because of the currently available technologies, especially in the areas of the Internet of Things and Expert Systems. Thus, this study presents a proposal for the environmental monitoring of an aviary using an Internet of Things technological apparatus combined with multi-agent systems to monitor climatic variables with the guidance of thermal comfort indicators. The experiment took place in a Cobb broiler aviary located in the countryside of the State of São Paulo, Brazil. With this objective in mind, the production period of Cobb broilers was analyzed through the construction of an Internet of Things system to collect air temperature, relative humidity, and atmospheric pressure variables combined with a data transfer mechanism for cloud recording. These variables were then analyzed by computational agents using the Java programming language with the Jade framework, which generated animal comfort indicators. The results showed that real-time monitoring of environmental variables is possible with the combination of the Internet of Things with agents that can determine animal comfort conditions according to the specific enthalpy of the air through the orchestration of a deliberative agent and with the participation of several reactive agents.