Dynamic Differential Evolution algorithm with composite strategies and parameter values self-adaption

摘要

Dynamic Differential Evolution algorithm using composite mutation strategies and parameter values self-adaptation (COSADDE) was proposed to solve complex optimization problems. For mutation, a strategy candidate pool including three trial vector generation strategies is constructed where one strategy is chosen for each target vector in the current population with roulette. To increase convergence speed, the target vector will be replaced by the newborn competitive trial vector if the newborn competitive baby is better. The updated target vector then will be used immediately at the same generation. Control parameter values (F and CR) are gradually self-adapted by learning from their previous experiences in generating promising solutions. The experiments are conducted on 13 classic benchmark functions and the results show that COSADDE is better than, or at least comparable to other classic DE algorithms in terms of accuracy and convergence speed.