Length Scale-Based Differential Evolution

Differential Evolution (DE) has shown a superior performance for solving global continuous optimization problems. The crucial idea of DE is modifying the population of the candidate solutions toward the weighted differences of randomly selected candidate solutions. In this paper, we propose the length scale-based DE which utilizes the obtained information of a landscape analysis metric, the length scale metric, to enhance its own performance. Landscape analysis methods attempt to gain the properties of optimization problems. For two sample points, length scale metric calculates their objective function changes with respect to the distance between them. By computing length scale values of all possible pairs of candidate solutions, DE can employ the pairs of candidate solutions with the greater length scale values to calculate the difference vector in its mutation operator. The length scale-based DE is evaluated on CEC-2014 benchmark functions. Two dimensions, 50 and 100, are considered for benchmark functions. Simulation results confirm that the proposed algorithm obtains a promising performance on the majority of the benchmark functions on both dimensions.

[1]  Michael Affenzeller,et al.  A Comprehensive Survey on Fitness Landscape Analysis , 2012, Recent Advances in Intelligent Engineering Systems.

[2]  Ponnuthurai N. Suganthan,et al.  Self-adaptive differential evolution with multi-trajectory search for large-scale optimization , 2011, Soft Comput..

[3]  Phil Husbands,et al.  Fitness Landscapes and Evolvability , 2002, Evolutionary Computation.

[4]  Pascal Bouvry,et al.  Improving Classical and Decentralized Differential Evolution With New Mutation Operator and Population Topologies , 2011, IEEE Transactions on Evolutionary Computation.

[5]  Francisco J. Rodríguez,et al.  Role differentiation and malleable mating for differential evolution: an analysis on large-scale optimisation , 2011, Soft Comput..

[6]  Marcus Gallagher,et al.  Analysing and characterising optimization problems using length scale , 2017, Soft Comput..

[7]  Rammohan Mallipeddi.  Harmony Search Based Parameter Ensemble Adaptation for Differential Evolution , 2013, J. Appl. Math..

[8]  Marcus Gallagher,et al.  Length Scale for Characterising Continuous Optimization Problems , 2012, PPSN.

[9]  Bart Naudts,et al.  A comparison of predictive measures of problem difficulty in evolutionary algorithms , 2000, IEEE Trans. Evol. Comput..

[10]  Nirmala Sharma,et al.  Exponential Scale-Factor based Differential Evolution Algorithm , 2017, 2017 International Conference on Computer, Communications and Electronics (Comptelix).

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

[12]  Andries Petrus Engelbrecht,et al.  A survey of techniques for characterising fitness landscapes and some possible ways forward , 2013, Inf. Sci..

[13]  L. Darrell Whitley,et al.  The dispersion metric and the CMA evolution strategy , 2006, GECCO.

[14]  Adam Kiczko,et al.  Differential Evolution algorithm with Separated Groups for multi-dimensional optimization problems , 2012, Eur. J. Oper. Res..

[15]  Shahryar Rahnamayan,et al.  Enhanced Differential Evolution using center-based sampling , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

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

[17]  Marcus Gallagher,et al.  Sampling Techniques and Distance Metrics in High Dimensional Continuous Landscape Analysis: Limitations and Improvements , 2014, IEEE Transactions on Evolutionary Computation.

[18]  Amit Konar,et al.  Two improved differential evolution schemes for faster global search , 2005, GECCO '05.

[19]  Meie Shen,et al.  A Differential Evolution Algorithm With Dual Populations for Solving Periodic Railway Timetable Scheduling Problem , 2013, IEEE Transactions on Evolutionary Computation.

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

[21]  G. Uludag,et al.  Fitness landscape analysis of differential evolution algorithms , 2009, 2009 Fifth International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control.

[22]  Ville Tirronen,et al.  Shuffle or update parallel differential evolution for large-scale optimization , 2011, Soft Comput..

[23]  Richard J. Duro,et al.  Evolutionary algorithm characterization in real parameter optimization problems , 2013, Appl. Soft Comput..

[24]  Ponnuthurai Nagaratnam Suganthan,et al.  Problem Definitions and Evaluation Criteria for the CEC 2014 Special Session and Competition on Single Objective Real-Parameter Numerical Optimization , 2014 .

[25]  Ville Tirronen,et al.  Scale factor inheritance mechanism in distributed differential evolution , 2009, Soft Comput..

[26]  A. Kai Qin,et al.  Self-adaptive differential evolution algorithm for numerical optimization , 2005, 2005 IEEE Congress on Evolutionary Computation.

[27]  Amit Konar,et al.  Differential Evolution Using a Neighborhood-Based Mutation Operator , 2009, IEEE Transactions on Evolutionary Computation.

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

[29]  Hendrik Richter,et al.  Fitness Landscapes: From Evolutionary Biology to Evolutionary Computation , 2014 .

[30]  Jason Teo,et al.  Exploring dynamic self-adaptive populations in differential evolution , 2006, Soft Comput..

[31]  Jouni Lampinen,et al.  A Trigonometric Mutation Operation to Differential Evolution , 2003, J. Glob. Optim..

[32]  M.M.A. Salama,et al.  Opposition-Based Differential Evolution , 2008, IEEE Transactions on Evolutionary Computation.

[33]  Saman K. Halgamuge,et al.  On the selection of fitness landscape analysis metrics for continuous optimization problems , 2014, 7th International Conference on Information and Automation for Sustainability.

[34]  Ming Yang,et al.  Differential Evolution With Auto-Enhanced Population Diversity , 2015, IEEE Transactions on Cybernetics.

[35]  J. Krug,et al.  Empirical fitness landscapes and the predictability of evolution , 2014, Nature Reviews Genetics.

[36]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[37]  Athanasios V. Vasilakos,et al.  Teaching and learning best Differential Evoltuion with self adaptation for real parameter optimization , 2013, 2013 IEEE Congress on Evolutionary Computation.