Abstract
Large-scale global optimization (LSGO) algorithms are crucially important to handle real-world problems. Recently, cooperative co-evolution (CC) algorithms have successfully been applied for solving many large-scale practical problems. Many applications have imbalanced subcomponents where the size of subcomponents and their contribution to the objective function value are different. CC algorithms often lose their efficiency on LSGO problems with the imbalanced subcomponents; since they do not consider the imbalance aspect of variables. In this paper, we propose a multilevel optimization framework based on variables effect (called MOFBVE) which optimizes several subcomponents of the most important variables at earlier stages of optimization procedure before optimizing the problem with the original search space at its last stage. Sensitivity analysis (SA) method determines how the variation in the outputs of the model can be influenced by the variation of its input parameters. MOFBVE computes the main effect of variables using an SA method, Morris screening, and then it employs the k-means clustering method to construct groups including variables with the similar effects on the fitness value. The constructed groups are sorted in the descending order based on their contribution on the fitness value and the top groups are selected as the levels of the important variables. MOFBVE can reduce the complexity of search space to work with a simplified model to achieve an efficient exploration. The performance of MOFBVE is benchmarked on the imbalanced LSGO problems, i.e., two individually modified CEC-2010 and the CEC-2013 LSGO benchmark functions. The simulated experiments confirmed that MOFBVE obtains a promising performance on the majority of the imbalanced LSGO test functions. Also, MOFBVE is compared with state-of-the-art CC algorithms; and the results show that it is better than or at least comparable to CC algorithms.
Similar content being viewed by others
References
Andrea S, Karen C, Marian Scott E et al (2000) Sensitivity analysis, vol 134. Wiley, New York
Andrea S, Marco R, Terry A, Francesca C, Jessica C, Debora G, Michaela S, Stefano T (2008) Global sensitivity analysis: the primer. Wiley, New York
Benjamin D, Dirk S, Carsten W (2013) When do evolutionary algorithms optimize separable functions in parallel? In: Proceedings of the twelfth workshop on Foundations of genetic algorithms XII, pp 51–64. ACM
Daniel M, Manuel L, Francisco H (2010) Ma-sw-chains: Memetic algorithm based on local search chains for large scale continuous global optimization. In: Evolutionary Computation (CEC), 2010 IEEE Congress on, IEEE, pp 1–8
Eman S, Daryl E, Ruhul S (2012a) Dependency identification technique for large scale optimization problems. In: Evolutionary Computation (CEC), 2012 IEEE Congress on, IEEE, pp 1–8
Eman S, Daryl E, Ruhul S (2012b) Using hybrid dependency identification with a memetic algorithm for large scale optimization problems. In: Simulated evolution and learning, Springer, pp 168–177
Francesca C, Jessica C, Andrea S (2007) An effective screening design for sensitivity analysis of large models. Environ Model Softw 22(10):1509–1518
Frank W (1945) Individual comparisons by ranking methods. Biometr Bull, pp 80–83
Frans Van den B, Andries PE (2004) A cooperative approach to particle swarm optimization. Evol Comput IEEE Trans 8(3):225–239
Hanning C, Yunlong Z, Kunyuan H, Xiaoxian H, Ben N (2008) Cooperative approaches to bacterial foraging optimization. In: Advanced intelligent computing theories and applications. with aspects of artificial intelligence, Springer, NY, pp 541–548
Hemant Kumar S, Tapabrata R (2010) Divide and conquer in coevolution: A difficult balancing act. In: Agent-based evolutionary search, Springer, pp 117–138
Herschel R, Ömer FA (1999) General foundations of high-dimensional model representations. J Math Chem 25(2–3):197–233
Hui W, Shahryar R, Zhijian W (2013) Parallel differential evolution with self-adapting control parameters and generalized opposition-based learning for solving high-dimensional optimization problems. J Parallel Distrib Comput 73(1):62–73
Jasbir A (2004) Introduction to optimum design. Academic Press, New York
Jinpeng L, Ke T (2013) Scaling up covariance matrix adaptation evolution strategy using cooperative coevolution. In: Intelligent data engineering and automated learning–IDEAL 2013, Springer, pp 350–357
Joaquín D, Salvador G, Daniel M, Francisco H (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1(1):3–18
Ke T, Xiaodong L, Ponnuthurai Nagaratnam S, Zhenyu Y, Thomas W (2010) Benchmark functions for the CEC’2010 special session and competition on large-scale global optimization. Technical report, Nature Inspired Computation and Applications Laboratory (NICAL),USTC, China. http://www.it-weise.de/documents/files/TLSYW2009BFFTCSSACOLSGO.pdf
Liang S, Shinichi Y, Xiaochun C, Yanchun L (2012) A cooperative particle swarm optimizer with statistical variable interdependence learning. Inf Sci 186(1):20–39
MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability., vol 1. California, pp 281–297
Max DM (1991) Factorial sampling plans for preliminary computational experiments. Technometrics 33(2):161–174
Mitchell AP, de Kenneth AD (1994) A cooperative coevolutionary approach to function optimization. In: Parallel problem solving from naturePPSN III, Springer, pp 249–257
Mitchell AP (1997) The design and analysis of a computational model of cooperative coevolution. PhD thesis, Citeseer
Mohammad Nabi O, Xiaodong L, Ke T (2015) Designing benchmark problems for large-scale continuous optimization. Inf Sci 316:419–436
Mohammad Nabi O, Xiaodong L, Xin Y (2011) Smart use of computational resources based on contribution for cooperative co-evolutionary algorithms. In: Proceedings of the 13th annual conference on genetic and evolutionary computation, ACM, pp 1115–1122
Mohammad Nabi O, Xiaodong L, Yi M, Xin Y (2014a) Cooperative co-evolution with differential grouping for large scale optimization. Evolutionary Computation, IEEE Transactions on 18(3): 378–393
Mohammad Nabi O, Yi M, Xiaodong L (2014b) Effective decomposition of large-scale separable continuous functions for cooperative co-evolutionary algorithms. In: Evolutionary computation (CEC), 2014 IEEE Congress on, IEEE, pp 1305–1312
Sedigheh M, Mohammad Ebrahim S, Shahryar R (2015) Metaheuristics in large-scale global continues optimization: a survey. Inf Sci 295:407–428
Sedigheh M, Mohammad Ebrahim S, Shahryar R (2014) Cooperative co-evolution with a new decomposition method for large-scale optimization. In: Evolutionary Computation (CEC), 2014 IEEE Congress on, IEEE, pp 1285–1292
Singiresu SR, Rao SS (2009) Engineering optimization: theory and practice. Wiley, New York
Wenxiang C, Thomas W, Zhenyu Y, Ke T (2010) Large-scale global optimization using cooperative coevolution with variable interaction learning. In: Parallel Problem Solving from Nature, PPSN XI, Springer, Heidelberg, pp 300–309
Xiaodong L, Ke T, Mohammad NO, Zhenyu Y, Kai Q (2013) Benchmark functions for the cec 2013 special session and competition on large-scale global optimization. Gene 7(33):8
Xiaodong L, Xin Y (2009) Tackling high dimensional nonseparable optimization problems by cooperatively coevolving particle swarms. In: Evolutionary computation, 2009. CEC’09. IEEE Congress on, pp 1546–1553. IEEE
Xiaodong L, Xin Y (2012) Cooperatively coevolving particle swarms for large scale optimization. Evol Comput IEEE Trans 16(2):210–224
Yoel T, Chi-Keong G (2010) Computational intelligence in expensive optimization problems, vol 2. Springer, New York
Yong L, Xin Y, Qiangfu Z, Tetsuya H (2001) Scaling up fast evolutionary programming with cooperative coevolution. In: Evolutionary Computation, 2001. Proceedings of the 2001 Congress on, IEEE. vol 2, pp 1101–1108
Yuanfang Ren, Yan Wu (2013) An efficient algorithm for high-dimensional function optimization. Soft Comput 17(6):995–1004
Zhao S-Z, Ponnuthurai Nagaratnam S, Swagatam D (2011) Self-adaptive differential evolution with multi-trajectory search for large-scale optimization. Soft Comput 15(11):2175–2185
Zhenyu Y, Ke T, Xin Y (2008a) Large scale evolutionary optimization using cooperative coevolution. Inf Sci 178(15):2985–2999
Zhenyu Y, Ke T, Xin Y (2008b) Multilevel cooperative coevolution for large scale optimization. In: Evolutionary computation, 2008. CEC 2008. IEEE World Congress on Computational Intelligence). IEEE Congress on, IEEE, pp 1663–1670
Zhenyu Y, Ke T, Xin Y (2008c) Self-adaptive differential evolution with neighborhood search. In: Evolutionary computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on, IEEE, pp 1110–1116
Acknowledgments
The authors would like to thank anonymous reviewers for their constructive comments.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Communicated by V. Loia.
Appendices
Appendix A
The the normal coefficient
Tables 22, 23, and 24 present the normal coefficient corresponding to nonseparable subcomponents in the modified normal CEC-2010 test functions.
Appendix B
The benchmark functions
-
CEC-2010 benchmark functions
Dimension: \(D = 1000\)
Group size: \(m = 50\)
\(x = (x_1, x_2, \dots , x_D)\): The candidate solution
\(o = (o_1, o_2, \dots , o_D)\): The (shifted) global optimum
\(z = x - o, z = (z_1, z_2, \dots , z_D)\): The shifted candidate solution
P: A random permutation of \({1, 2, \dots ,D}\)
-
CEC-2013 benchmark functions
Dimension: \(D = 1000\)
Group size: \(m = 50\)
\(x^\mathrm{opt}\) : The optimum decision vector
P: A random permutation of \({1, 2, \dots ,D}\)
\(T_\mathrm{osz}\): A transformation function to create smooth local irregularities.
\(T_\mathrm{asy}\): A transformation function to break the symmetry of the symmetric functions.
\(\lambda \): A D-dimensional diagonal matrix with the diagonal elements is used to create ill-conditioning.
R: An orthogonal rotation matrix which is used to rotate the fitness landscape randomly around various axes
m: The overlap size between subcomponents
Rights and permissions
About this article
Cite this article
Mahdavi, S., Rahnamayan, S. & Shiri, M.E. Multilevel framework for large-scale global optimization. Soft Comput 21, 4111–4140 (2017). https://doi.org/10.1007/s00500-016-2060-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-016-2060-y