基于反射变异策略的自适应差分进化算法
|
摘要
针对差分进化算法易于陷入早熟收敛和局部搜索较慢的问题,提出了一种类似Nelder-Mead方法中的反射操作的变异策略,称为反射变异策略。不同于其他基本的差分策略,提出的变异策略具有明确的差分方向,具有更快的局部收敛速度。为了避免因差分方向的贪婪性而导致算法早熟的可能性增加,反射变异策略使用4个随机的个体完成一次变异操作。将基于反射变异策略的子代生成策略和自适应参数方法组合形成了基于反射变异策略的自适应差分进化算法(RMADE)。使用12个函数测试了RMADE的性能并与其他算法进行比较,结果表明RMADE具有较快的收敛速度和较好的全局探测能力,进而体现了反射变异策略的价值。
For the problems that differential evolution algorithm is prone to premature convergence and its local search is slower, a mutation strategy similar to Nelder-Mead method is proposed, which is called reflective mutation strategy.Different from other basic differential strategies, the proposed mutation strategy has a distinct difference direction and has a stronger local convergence speed. In order to avoid the possibility of premature increase due to the greedy of differential orientation, the reflection mutation strategy uses 4 random individuals to complete a mutation operation. An adaptive differential evolution algorithm(RMADE)based on the reflective mutation strategy is developed by combining the generation strategy and the adaptive parameter method based on the reflective mutation strategy. The performance of RMADE is tested by using 12 functions and compared with other algorithms. The results show that RMADE has faster convergence speed and better global detection capability, and reflects the value of reflective mutation strategy.
For the problems that differential evolution algorithm is prone to premature convergence and its local search is slower, a mutation strategy similar to Nelder-Mead method is proposed, which is called reflective mutation strategy.Different from other basic differential strategies, the proposed mutation strategy has a distinct difference direction and has a stronger local convergence speed. In order to avoid the possibility of premature increase due to the greedy of differential orientation, the reflection mutation strategy uses 4 random individuals to complete a mutation operation. An adaptive differential evolution algorithm(RMADE)based on the reflective mutation strategy is developed by combining the generation strategy and the adaptive parameter method based on the reflective mutation strategy. The performance of RMADE is tested by using 12 functions and compared with other algorithms. The results show that RMADE has faster convergence speed and better global detection capability, and reflects the value of reflective mutation strategy.
引文
[1]Storn R,Price K.Differential evolution:A simple and efficient heuristic for global optimization over continuous spaces[J].Journal of Global Optimization,1997,11(4):341-359.
[2]Ghosh A,Das S,Chowdhury A,et al.An improved differential evolution algorithm with fitness-based adaptation of the control parameters[J].Information Sciences,2011,181(18):3749-3765.
[3]张春美,陈杰,辛斌.参数适应性分布式差分进化算法[J].控制与决策,2014,29(4):701-706.
[4]张锦华,宋来锁,张元华,等.加权变异策略动态差分进化算法[J].计算机工程与应用,2017,53(4):156-162.
[5]Brest J,Greiner S,Boskovic B,et al.Self-adapting control parameters in differential evolution:A comparative study on numerical benchmark problems[J].IEEE Transactions on Evolutionary Computation,2006,10(6):646-657.
[6]Zhang J,Sanderson A C.JADE:Adaptive differential evolution with optional external archive[J].IEEE Transactions on Evolutionary Computation,2009,13(5):945-958.
[7]Tanabe R,Fukunaga A.Success-history based parameter adaptation for differential evolution[C]//IEEE Congress on Evolutionary Computation,2013:71-78.
[8]Wang Y,Cai Z,Zhang Q.Differential evolution with composite trial vector generation strategies and control parameters[J].IEEE Transactions on Evolutionary Computation,2011,15(1):55-66.
[9]Mallipeddi R,Suganthan P N,Pan Q K,et al.Differential evolution algorithm with ensemble of parameters and mutation strategies[J].Applied Soft Computing,2011,11(2):1679-1696.
[10]Wu G,Mallipeddi R,Suganthan P N,et al.Differential evolution with multi-population based ensemble of mutation strategies[J].Information Sciences,2016,329(C):329-345.
[11]Mohamed A W.An improved differential evolution algorithm with triangular mutation for global numerical optimization[J].Computers&Industrial Engineering,2015,85(C):359-375.
[12]Yi W,Gao L,Li X,et al.A new differential evolution algorithm with a hybrid mutation operator and selfadapting control parameters for global optimization problems[J].Applied Intelligence,2015,42(4):642-660.
[13]Yang M,Li C,Cai Z,et al.Differential evolution with auto-enhanced population diversity[J].IEEE Transactions on Cybernetics,2015,45(2):302.
[14]Teo J.Differential evolution with self-adaptive populations[M]//Knowledge-Based Intelligent Information and Engineering Systems.Berlin Heidelberg:Springer,2005:1284-1290.
[15]Brest J,Mau?ec M S.Population size reduction for the differential evolution algorithm[J].Applied Intelligence,2008,29(3):228-247.
[16]Tasoulis D K,Plagianakos V P,Vrahatis M N.Clustering in evolutionary algorithms to efficiently compute simultaneously local and global minima[C]//IEEE Congress on Evolutionary Computation,2005:1847-1854.
[17]Epitropakis M G,Plagianakos V P,Vrahatis M N.Balancing the exploration and exploitation capabilities of the differential evolution algorithm[C]//IEEE Congress on Evolutionary Computation,2008:2686-2693.
[18]Peng F,Tang K,Chen G,et al.Multi-start JADE with knowledge transfer for numerical optimization[C]//IEEE Congress on Evolutionary Computation,2009:1889-1895.
[19]李牧东,赵辉,翁兴伟,等.基于最优高斯随机游走和个体筛选策略的差分进化算法[J].控制与决策,2016,31(8):1379-1386.
[20]Yao Xin,Lin Guangming,Liu Yong.Evolutionary programming made faster[J].IEEE Transactions on Evolutionary Computation,1999,3(2):82-102.
[2]Ghosh A,Das S,Chowdhury A,et al.An improved differential evolution algorithm with fitness-based adaptation of the control parameters[J].Information Sciences,2011,181(18):3749-3765.
[3]张春美,陈杰,辛斌.参数适应性分布式差分进化算法[J].控制与决策,2014,29(4):701-706.
[4]张锦华,宋来锁,张元华,等.加权变异策略动态差分进化算法[J].计算机工程与应用,2017,53(4):156-162.
[5]Brest J,Greiner S,Boskovic B,et al.Self-adapting control parameters in differential evolution:A comparative study on numerical benchmark problems[J].IEEE Transactions on Evolutionary Computation,2006,10(6):646-657.
[6]Zhang J,Sanderson A C.JADE:Adaptive differential evolution with optional external archive[J].IEEE Transactions on Evolutionary Computation,2009,13(5):945-958.
[7]Tanabe R,Fukunaga A.Success-history based parameter adaptation for differential evolution[C]//IEEE Congress on Evolutionary Computation,2013:71-78.
[8]Wang Y,Cai Z,Zhang Q.Differential evolution with composite trial vector generation strategies and control parameters[J].IEEE Transactions on Evolutionary Computation,2011,15(1):55-66.
[9]Mallipeddi R,Suganthan P N,Pan Q K,et al.Differential evolution algorithm with ensemble of parameters and mutation strategies[J].Applied Soft Computing,2011,11(2):1679-1696.
[10]Wu G,Mallipeddi R,Suganthan P N,et al.Differential evolution with multi-population based ensemble of mutation strategies[J].Information Sciences,2016,329(C):329-345.
[11]Mohamed A W.An improved differential evolution algorithm with triangular mutation for global numerical optimization[J].Computers&Industrial Engineering,2015,85(C):359-375.
[12]Yi W,Gao L,Li X,et al.A new differential evolution algorithm with a hybrid mutation operator and selfadapting control parameters for global optimization problems[J].Applied Intelligence,2015,42(4):642-660.
[13]Yang M,Li C,Cai Z,et al.Differential evolution with auto-enhanced population diversity[J].IEEE Transactions on Cybernetics,2015,45(2):302.
[14]Teo J.Differential evolution with self-adaptive populations[M]//Knowledge-Based Intelligent Information and Engineering Systems.Berlin Heidelberg:Springer,2005:1284-1290.
[15]Brest J,Mau?ec M S.Population size reduction for the differential evolution algorithm[J].Applied Intelligence,2008,29(3):228-247.
[16]Tasoulis D K,Plagianakos V P,Vrahatis M N.Clustering in evolutionary algorithms to efficiently compute simultaneously local and global minima[C]//IEEE Congress on Evolutionary Computation,2005:1847-1854.
[17]Epitropakis M G,Plagianakos V P,Vrahatis M N.Balancing the exploration and exploitation capabilities of the differential evolution algorithm[C]//IEEE Congress on Evolutionary Computation,2008:2686-2693.
[18]Peng F,Tang K,Chen G,et al.Multi-start JADE with knowledge transfer for numerical optimization[C]//IEEE Congress on Evolutionary Computation,2009:1889-1895.
[19]李牧东,赵辉,翁兴伟,等.基于最优高斯随机游走和个体筛选策略的差分进化算法[J].控制与决策,2016,31(8):1379-1386.
[20]Yao Xin,Lin Guangming,Liu Yong.Evolutionary programming made faster[J].IEEE Transactions on Evolutionary Computation,1999,3(2):82-102.