Strategic Conflict Resolution Based on Cooperative Co-evolution Algorithm

Abstract:
In this paper, we design a cooperative co-evolutionary algorithm based on dynamic grouping (CCDG) to solve the large-scale optimization problem of 4D-Trajectory strategic conflict resolution (4DTCR). A dynamic grouping strategy based on aircraft conflict and random grouping strategies is proposed. The grouping strategy based on aircraft conflict can make full use of prior domain knowledge and maximize the mutual influence of flights into a group to improve the conflict resolution efficiency. An improved fast genetic algorithm (GA) is used in the group to evolve, and the group cooperates through a collaborative selection mechanism. Using 600 flights during peak hours of China air route network for example verification, the proposed algorithm is compared with the traditional genetic algorithm and the cooperative co-evolution algorithm based on random grouping strategy (CCRG). Experimental results show that the CCDG has better optimization effects, can effectively resolve conflicts between aircrafts and produce smaller delays and altitude adjustments, and the algorithm has a faster convergence speed.