OPTIMALITY IN AGRICULTURE: GENERATING OPTIMAL STRUCTURE OF CULTURES WITHIN A FARM USING GENETIC ALGORITHMS

Optimization in agriculture can have various forms, depending on its various processes or the market evolution. It can be financial or product-based and can lead to minimization, if related to costs, or maximization, related to profit. In this paper we will present a method of determining an optimal...

Full description

Saved in:
Bibliographic Details
Main Authors: Victor TIȚA, Doru Anastasiu POPESCU, Nicolae BOLD
Format: Article
Language:English
Published: University of Agricultural Sciences and Veterinary Medicine, Bucharest 2017-01-01
Series:Scientific Papers Series : Management, Economic Engineering in Agriculture and Rural Development
Online Access:https://managementjournal.usamv.ro/pdf/vol.17_2/Art51.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Optimization in agriculture can have various forms, depending on its various processes or the market evolution. It can be financial or product-based and can lead to minimization, if related to costs, or maximization, related to profit. In this paper we will present a method of determining an optimal repartition of an agricultural surface for a number of cultures based on a genetic algorithm in order for the profit to be maxim. The model takes into consideration several requirements related to cultures selling price, obtained production, direct costs and costs related to human workforce. The genetic algorithm uses basic structures (chromosomes, genes) and operations (mutation, crossover) to generate a repartition. In this case, the chromosomes are defined as the surface itself, a gene within a chromosome being the surface for a specific culture. The length of the chromosome is equal to the number of cultures desired to be cultivated. The operations are basic and will be described in the paper. The fitness function is defined as the difference between the incomes and the costs, thus the profit. The results will be then compared to the results obtained by the traditional method that uses linear programming.
ISSN:2284-7995
2285-3952