Optimal Schedule for Agricultural Machinery in Sequential Tasks Using a Multi-Population Co-Evolutionary Non-Dominant Neighbor Immune Algorithm

Considering the lack of the intelligent method of the agricultural machinery scheduling in sequential tasks, a multi-population co-evolutionary non-dominant neighbor immune algorithm (MCNNIA) is proposed to minimize the total distance travelled of all agricultural machineries and the total execution time for all tasks. We have constructed a novel antibody encoding method, and each antibody represents a scheduling scheme. Combining our collaborative evolutionary strategy of the population with non-dominant neighbor immune algorithm (NNIA), all the antibodies are divided into H populations to evolve separately and the inter-population competition and elite communication are introduced in the evolutionary process to enhance the diversity of antibodies and the search ability of the algorithm. Simulation results illustrate that the proposed algorithm has better performance in convergence and Pareto-optimal solutions spacing.