Self-adaptive collective intelligence-based mutation operator for differential evolution algorithms

摘要: In conventional differential evolutionary (DE) algorithm, mutation operator has significant influence on generating new vectors by mixing existing target randomly selected from the current population. Recently, many operators, which usually employ best individual or some high-quality individuals chosen, have been proposed to improve searching capability. However, such designs may easily suffer premature convergence trapped local optima. To make a trade-off between exploration and exploitation capability, this paper proposes novel collective intelligence (CI)-based operator, is named as “current-to-sa-ci-best.” presented information of m linearly combined generate mutant vectors. Besides, designed an exponential-distributed random number could be self-adapted based successful records values alongside evolution. Moreover, applied any DE algorithm without destroying search capability adding greedy selection operator. verify its effectiveness, CI-based strategy, SaCI, was embedded into state-of-the-art variants 28 CEC2013 benchmark functions. Numerical results confirmed that SaCI beneficial DEs extent.