Estimating and tuning adaptive action plans for the control of smart interconnected poultry condominiums

The systematic choice, update, and implementation of periodic () action plans define the feed conversion rate () in poultry farming, an acceptable measure for successful production. Appropriate plans provide tailored resources, allowing broilers to grow within the so-called comfort zone, without waste or lack of resources. Although the implementation of an action plan is automatic, its configuration depends on a specialist, which result in variable . In this article, the specialist’s perception is reproduced, to some extent, by computational intelligence. By combining deep learning and genetic algorithms, we show how action plans can adapt their performance over the time, based on previous well succeeded plans. We also implement a network infrastructure to replicate our method over distributed poultry houses, for their smart and interconnected control. A supervision system is provided as interface to users. Experiments using real data suggest an improvement of 5% on the performance of the most productive specialist, staying close to the optimal .