Resource allocation in pastoral dairy production systems: Evaluating exact and genetic algorithms approaches

The problem of food resources allocation to a heterogeneous dairy herd was studied in this paper. We focused on how to allocate available resources by grouping cows and their subsequent distribution in the field (pasture and/or feeding area). The main goal of this paper was to maximize either milk production or the margin over feeding cost for the entire dairy herd. The input of energy from different feed resources and the animal requirements of energy were considered. A mathematical model and a Genetic Algorithm (GA) were programmed. An experimental evaluation was performed in order to analyze the quality solution of the GA and to study how the resource allocation should be performed by interpreting the solutions' structure for both methods. The diversity of the solutions provided by the GA was also studied. The experimental evaluation showed that the gap values (milk production difference) between the GA and the Exact Method (EM) solutions were smaller than 2%. Also, when food resources were scarce, there was a great difference (almost a 50% difference for a herd of 1500 cows) between the GA and the EM solutions' structure. The results showed that values obtained by the GA were very close to the values obtained by the exact method, but generating different assignment structures, presenting a good diversity and a wider exploration of the solutions' space.