The discovery of population interaction with a power law distribution in brain storm optimization

Brain storm optimization (BSO) is a novel evolutionary algorithm which originates from the human brainstorming process. The successful applications of BSO on various problems demonstrate its validity and efficiency. To theoretically analyze the performance of algorithm from the viewpoint of population evolution, the population interaction network (PIN) is used to construct the relationship among individuals in BSO. Four experiments in different dimensions, parameters, combinatorial parameter settings and related algorithms are implemented, respectively. The experimental results indicate the frequency of average degree of BSO meets a power law distribution in the functions with low dimension, which shows the best performance of algorithm among three kinds of dimensions. The parameters of BSO are investigated to find the influence of the population interaction with the power law distribution on the performance of algorithm, and respective parameter can change the relationship among individuals. In addition, the mutual effect among parameters is analyzed to find the best combinatorial result to significantly enhance the performance of BSO. The contrast among BSO, DE and PSO demonstrates a power law distribution is more effective for boosting the population interaction to enhance the performance of algorithm.

[1]  Genichi Taguchi.  Computer-Based Robust Engineering : Essentials for DFSS , 2010 .

[2]  Yuhui Shi,et al.  Solution clustering analysis in brain storm optimization algorithm , 2013, 2013 IEEE Symposium on Swarm Intelligence (SIS).

[3]  Yuhui Shi,et al.  Advanced discussion mechanism-based brain storm optimization algorithm , 2015, Soft Comput..

[4]  V. Latora,et al.  Complex networks: Structure and dynamics , 2006 .

[5]  Francisco Herrera,et al.  A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms , 2011, Swarm Evol. Comput..

[6]  Zhiping Lin,et al.  Extreme Learning Machines on High Dimensional and Large Data Applications: A Survey , 2015 .

[7]  Ruhul A. Sarker,et al.  The Self-Organization of Interaction Networks for Nature-Inspired Optimization , 2008, IEEE Transactions on Evolutionary Computation.

[8]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[9]  Jun Zhang,et al.  Parameter investigation in brain storm optimization , 2013, 2013 IEEE Symposium on Swarm Intelligence (SIS).

[10]  Yuhui Shi,et al.  Brain Storm Optimization Algorithm with Modified Step-Size and Individual Generation , 2012, ICSI.

[11]  José Neves,et al.  The fully informed particle swarm: simpler, maybe better , 2004, IEEE Transactions on Evolutionary Computation.

[12]  Bo Yang,et al.  Random Grouping Brain Storm Optimization Algorithm with a New Dynamically Changing Step Size , 2016, ICSI.

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

[14]  Hisao Ishibuchi,et al.  Implementation of cellular genetic algorithms with two neighborhood structures for single-objective and multi-objective optimization , 2011, Soft Comput..

[15]  Chenggong Zhang,et al.  Scale-free fully informed particle swarm optimization algorithm , 2011, Inf. Sci..

[16]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[17]  Junfeng Chen,et al.  Brain storm optimization algorithm: a review , 2016, Artificial Intelligence Review.

[18]  R. J. Bell,et al.  Properties of Vitreous Silica: Analysis of Random Network Models , 1966, Nature.

[19]  Xin Yao,et al.  Evolutionary programming made faster , 1999, IEEE Trans. Evol. Comput..

[20]  Yuhui Shi,et al.  Brain storm optimization algorithms with k-medians clustering algorithms , 2015, 2015 Seventh International Conference on Advanced Computational Intelligence (ICACI).

[21]  Jie Qi,et al.  The emergence of scaling laws search dynamics in a particle swarm optimization , 2013 .

[22]  Jing J. Liang,et al.  Problem Definitions and Evaluation Criteria for the CEC 2005 Special Session on Real-Parameter Optimization , 2005 .

[23]  Yuhui Shi,et al.  Brain storm optimization with chaotic operation , 2015, 2015 Seventh International Conference on Advanced Computational Intelligence (ICACI).

[24]  Yuhui Shi,et al.  Brain Storm Optimization Algorithm , 2011, ICSI.

[25]  Martin Middendorf,et al.  A hierarchical particle swarm optimizer and its adaptive variant , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[26]  Albert-László Barabási,et al.  Scale-Free Networks: A Decade and Beyond , 2009, Science.

[27]  Yuhui Shi,et al.  Hybrid brain storm optimisation and simulated annealing algorithm for continuous optimisation problems , 2016, Int. J. Bio Inspired Comput..

[28]  Yuhui Shi,et al.  An Improved Brain Storm Optimization with Differential Evolution Strategy for Applications of ANNs , 2015 .

[29]  Jiujun Cheng,et al.  Understanding differential evolution: A Poisson law derived from population interaction network , 2017, J. Comput. Sci..

[30]  M. Newman.  Analysis of weighted networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.