Imperialist competition algorithm with quasi-opposition-based learning for function optimization and engineering design problems

Imperialist competitive algorithm (ICA) is an efficient meta-heuristic algorithm by simulating the competitive behaviour among imperialist countries. However, it still suffers from slow convergence and deficiency in exploration. To address these issues, an improved ICA is proposed by combining ICA with a quasi-opposition-based learning (QOBL) strategy, which is named QOBL-ICA. The improvements include two aspects. First, the QOBL strategy is adopted to generate a population of fitter individuals. Second, a QOBL-assisted assimilation strategy is proposed to enhance the exploration ability of ICA. As a result, the proposed QOBL-ICA has more powerful exploration ability than ICA as well as faster convergence speed. The effectiveness of the proposed QOBL-ICA is verified by testing on 20 benchmark functions and 3 engineering design problems. Experimental results show that the performance of QOBL-ICA is superior to most state-of-the-art meta-heuristic algorithms in terms of global optimum reached and convergence speed.