On the adaptation of the mutation scale factor in differential evolution

Differential evolution (DE) is a simple yet effective metaheuristic specially suited for real-parameter optimization. The most advanced DE variants take into account the feedback obtained in the self-optimization process to modify their internal parameters and components dynamically. In recent years, some controversies have arisen regarding the adaptive schemes that incorporate feedback from the search process to guide the adaptation of the mutation scale factor. Some researchers have claimed that no significant benefits are obtained with these kinds of schemes. However, other studies have shown that they are highly effective. In this paper, we show that there is a relationship between the effectiveness of these adaptive schemes and the balance between exploration and exploitation induced by the trial vector generation strategy considered. State-of-the-art adaptive schemes are not useful for the trial vector generation strategies with the highest levels of exploration, which in fact seems to be the reason behind the controversies of recent years.

[1]  Francisco Herrera,et al.  Editorial scalability of evolutionary algorithms and other metaheuristics for large-scale continuous optimization problems , 2011, Soft Comput..

[2]  Arthur C. Sanderson,et al.  JADE: Adaptive Differential Evolution With Optional External Archive , 2009, IEEE Transactions on Evolutionary Computation.

[3]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[4]  Qingfu Zhang,et al.  Differential Evolution With Composite Trial Vector Generation Strategies and Control Parameters , 2011, IEEE Transactions on Evolutionary Computation.

[5]  Karl-Dirk Kammeyer,et al.  Parameter Study for Differential Evolution Using a Power Allocation Problem Including Interference Cancellation , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[6]  Carlos A. Coello Coello,et al.  A comparative study of differential evolution variants for global optimization , 2006, GECCO.

[7]  Ville Tirronen,et al.  Recent advances in differential evolution: a survey and experimental analysis , 2010, Artificial Intelligence Review.

[8]  P. N. Suganthan,et al.  Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization , 2009, IEEE Transactions on Evolutionary Computation.

[9]  P. N. Suganthan,et al.  Differential Evolution: A Survey of the State-of-the-Art , 2011, IEEE Transactions on Evolutionary Computation.

[10]  Rainer Laur,et al.  Comparison of Adaptive Approaches for Differential Evolution , 2008, PPSN.

[11]  Janez Brest,et al.  Self-Adapting Control Parameters in Differential Evolution: A Comparative Study on Numerical Benchmark Problems , 2006, IEEE Transactions on Evolutionary Computation.

[12]  Hussein A. Abbass,et al.  The effect of a stochastic step length on the performance of the differential evolution algorithm , 2007, 2007 IEEE Congress on Evolutionary Computation.

[13]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[14]  Antonio LaTorre,et al.  A MOS-based dynamic memetic differential evolution algorithm for continuous optimization: a scalability test , 2011, Soft Comput..

[15]  Mehmet Fatih Tasgetiren,et al.  Differential evolution algorithm with ensemble of parameters and mutation strategies , 2011, Appl. Soft Comput..

[16]  Petr Bujok,et al.  Adaptive Variants of Differential Evolution: Towards Control-Parameter-Free Optimizers , 2013, Handbook of Optimization.