信息工程与人工智能学院知识库

Differential evolution (DE) is a stochastic search algorithm which has shown a good performance in many optimization problems. Due to the randomness of the DE, it easily gets stuck when solving complex optimization problems. To enhance the performance of DE, this paper proposes a novel DE variant called self-adaptive DE with quantum behaviors (SAQDE). The new approach employs two strategies including quantumbehaved mutation scheme and adaptive crossover rate. Compared with the classical DE, SAQDE eliminates the scale factor. Experimental studies on ten well-known numerical optimization problems show that SAQDE outperforms the classical DE and three other similar algorithms in terms of the solution accuracy and convergence rate. © 2012 ISSN 1881-803X.