This paper studies a modification of the imperialist competitive algorithm to solve constrained optimization problems with hybrid methods. The imperialist competitive algorithm is a kind of evolutionary algorithm based on the colonial competition mechanism of imperialism, which is a type of social heuristic optimization algorithm. However, this algorithm needs to be modified because of some problems, including the decreasing number of empires, which leads to easily falling into a local optimum, and a lack of information exchange among countries leading to the search ability being insufficiently strong.To solve these problems and improve the search ability of the algorithm, a newly improved imperialist competitive algorithm with hybrid methods is proposed based on the imperialist competitive algorithm in this paper. In this algorithm, a crossover mechanism is introduced as the empire interaction to boost the information exchange among countries. Two groups of combinatorial operators are constructed in the process of empire assimilation and revolution to improve the algorithm's global and local search ability. Moreover, a step of empire splitting is added based on the imperialist competitive algorithm in which the number of empires is decreased rapidly by empire competition in imperialist competitive algorithm, which leads to a decrease in the population diversity. Then, the proposed algorithm is tested on 12 benchmark functions and 4 engineering problems, and the constraints are addressed by Deb's rules. The results obtained by the proposed algorithm are compared with those of algorithms that have obtained good results in recent years, and it is shown that the proposed method obtains promising and comparable results on the constrained optimization benchmarks in terms of the solution quality and robustness.INDEX TERMS Constrained optimization problems, Hybrid methods, Imperialist competitive algorithm.
This paper proposes a modification of the imperialist competitive algorithm to solve multi-objective optimization problems with hybrid methods (MOHMICA) based on a modification of the imperialist competitive algorithm with hybrid methods (HMICA). The rationale for this is that there is an obvious disadvantage of HMICA in that it can only solve single-objective optimization problems but cannot solve multi-objective optimization problems. In order to adapt to the characteristics of multi-objective optimization problems, this paper improves the establishment of the initial empires and colony allocation mechanism and empire competition in HMICA, and introduces an external archiving strategy. A total of 12 benchmark functions are calculated, including 10 bi-objective and 2 tri-objective benchmarks. Four metrics are used to verify the quality of MOHMICA. Then, a new comprehensive evaluation method is proposed, called “radar map method”, which could comprehensively evaluate the convergence and distribution performance of multi-objective optimization algorithm. It can be seen from the four coordinate axes of the radar maps that this is a symmetrical evaluation method. For this evaluation method, the larger the radar map area is, the better the calculation result of the algorithm. Using this new evaluation method, the algorithm proposed in this paper is compared with seven other high-quality algorithms. The radar map area of MOHMICA is at least 14.06% larger than that of other algorithms. Therefore, it is proven that MOHMICA has advantages as a whole.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.