Local ensemble surrogate assisted crowding differential evolution

Chen Jin, A. Kai Qin, Ke Tang

Abstract: Differential evolution (DE) is a powerful population-based stochastic optimization algorithm. Although its efficacy has been witnessed in various applications, the performance of DE is usually challenged when the computational budget is decreased and/or the search landscape's complexity is increased. To address these issues, we propose a new local ensemble surrogate assisted crowding DE (LES-CDE) algorithm, which consists of multiple local surrogate models built upon the historical search information accumulated in diverse overlapped local regions of the search space. In LES-CDE, an ensemble of several adjacent local surrogates is utilized to guide the creation of promising trial vectors. To maintain the local nature of each surrogate model, LES-CDE uses the replacement scheme of crowding DE (CDE) to update the population which also serves as model landmarks. We test LES-CDE under varying parameters and compare them with CDE on 15 numerical test problems taken from CEC 2015 single-objective real-parameter optimization testbed. Results from our experiments demonstrate the superiority of LES-CDE over CDE in a statistically significant manner.