On-demand farming services with shared agricultural machinery

Abstract

Nowadays, rural households and even governments are faced with increasing yields with limited resources, and the extensive use of agricultural machinery is one of the most efficient methods for that. Agricultural machinery usually charges high prices, and it is economically impractical for small-scale farmers to afford them. The shared agricultural machinery (SAM) is racing ahead full throttle in the market. Rural households submit a usage request and their requirements of operations and time, and the company would provide on-demand farming services for them. This thesis proposes a framework to investigate how to provide on-demand farming services with shared agricultural machinery, from selecting and dispatching SAMs to assigning operators to SAMs.

The first study investigates the optimal selection and maintenance strategy for operational usage of SAMs. A dynamic joint optimization model is developed to formulate such a strategy design problem, considering repeated selections and inspection and maintenance over the planning period. The units of SAMs operational-use reliability upon selection and their reliability after selection in the storage are analyzed, which are the foundation of our optimization problem. The applicability of the proposed optimization problem is numerically verified.

The second study develops a novel two-step dispatching framework for shared agricultural machinery. In the first step, a model-based spatiotemporal clustering approach is developed to cluster farmlands according to their location, time windows, and crop strain. The shortest route within each cluster of farmlands is also determined. In the second step, shared agricultural machines are routed across the clusters to minimize the dispatching costs. These two steps are formulated as Mixed Integer Linear Programming models, and a threestep heuristic is proposed to solve these problems. The computational results demonstrate the efficiency, effectiveness, and practical value of the developed approach. The decreasing number of working agricultural machines would result in a longer traveling distance. Longer time windows and higher working efficiency could reduce the number of working agricultural machines and dispatching costs but increase the traveling distances.

The third study proposes a methodology for operator assignment with shared agricultural machinery scheduling simultaneously. A mixed integer linear programming model is proposed to formulate our problem with the objective of minimizing the total working time and costs by determining the combinations of harvesters and operators and the routes of harvesters. Valid inequalities are derived for tightening the lower bounds after LP relaxation, which enables quickly solving problems of realistic size with near-optimal solutions. The corresponding heuristic algorithms are also developed. Computational studies are conducted to demonstrate the effectiveness and efficiency of our solution methodology and obtain managerial insights. Compared with the assigning-first routing-second approach, our joint decision-making method could reduce both working time and costs. Hiring more operators is not better than training employed ones to reduce the total working time and costs.