Imperialist Competitive Algorithm with Independence and Constrained Assimilation
Ivars Dzalbs, Tatiana Kalganova, Ian Dear · 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA) · 2020
This work proposes an improved Imperialist Competitive Algorithm (ICA) based algorithm for solving constrained combinatorial problems, called ICA with Independence and Constrained Assimilation (ICAwICA). The proposed algorithm introduces the concept of colony independence - a free will to choose between classic ICA assimilation to the empire's imperialist or any other imperialist in the population. Furthermore, a constrained assimilation process has been implemented that combines classical ICA assimilation and revolution operators, while maintaining population diversity. In order to evaluate the performance and generalisation aspects of the proposed approach, two different kinds of combinatorial benchmark problems were selected - subset selection and routing, Multiple Knapsack Problem (MKP) and Multiple Depot Vehicle Routing Problem (MDVRP), respectively. The algorithm showed definite improvement over classic ICA and outperformed most of the competition on both types of problems across multiple instances, indicating the generic, universal nature of the ICAwICA. Moreover, it ranked 2ndamong the recently published algorithms that are customised to the specific problem with the use of problem-specific operators, while the proposed algorithm had no such operators.