Evolutionary neighborhood discovery algorithm for agricultural routing planning in multiple fields

Abstract

In recent years, operations research in agriculture has improved the harvested yield, reduced the cost and time required for field operations, and maintained economic and environmental sustainability. The heuristics method, named Evolutionary neighborhood discovery algorithm (ENDA), is applied to minimize the inter-field and intra-field distance of the routing planning of machines in multiple agricultural fields. The problem is an extended version of the Agricultural Routing Planning (ARP) that takes into consideration the different capacity of the machines and multiple agricultural fields. This research also describes the mathematical model to represent the proposed problem formulated as an integer program. The experimental results show that ENDA successfully solves ARP instances, giving the best results and the fastest running time compared to those obtained by Genetic Algorithms and Tabu Search. The results also show that ENDA can save an average of 11.72% of the distance traveled by the machines outside the working path (when making maneuvers, going to or from the entrances and going from and returning to the Depot).