Biological invasion-inspired migration in distributed evolutionary algorithms

被引:37
作者
De Falco, I. [1 ]
Della Cioppa, A. [2 ]
Maisto, D. [1 ]
Scafuri, U. [1 ]
Tarantino, E. [1 ]
机构
[1] Natl Res Council Italy, Inst High Performance Comp & Networking, I-80131 Naples, Italy
[2] Univ Salerno, DIEII, Nat Computat Lab, I-84084 Fisciano, SA, Italy
关键词
Massive migration; Biological invasion; Distributed evolutionary algorithm; DIFFERENTIAL EVOLUTION; STATISTICAL COMPARISONS; SELECTION PRESSURE; OPTIMIZATION; INTELLIGENCE; CLASSIFIERS; DESIGN; MODELS; TESTS;
D O I
10.1016/j.ins.2012.04.027
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Migration strategy plays an important role in designing effective distributed evolutionary algorithms. In this work, a novel migration model inspired to the phenomenon known as biological invasion is devised. The migration strategy is implemented through a multistage process involving invading subpopulations and their competition with native individuals. Such a general approach is used within a stepping-stone parallel model adopting Differential Evolution as the local algorithm. The resulting distributed algorithm is evaluated on a wide set of classical test functions against a large number of sequential and other distributed versions of Differential Evolution available in literature. The findings show that, in most of the cases, the proposed algorithm is able to achieve better performance in terms of both solution quality and convergence rate. (C) 2012 Elsevier Inc. All rights reserved.
引用
收藏
页码:50 / 65
页数:16
相关论文
共 56 条
[1]   Parallelism and evolutionary algorithms [J].
Alba, E ;
Tomassini, M .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (05) :443-462
[2]  
Alba E, 2005, IEEE C EVOL COMPUTAT, P214
[3]  
[Anonymous], P IEEE INT C SYST MA
[4]  
[Anonymous], LECT NOTES COMPUTER
[5]  
[Anonymous], COMPLETE REFERENCE M
[6]  
[Anonymous], OPTIMIZATION ITS APP
[7]  
[Anonymous], FDN GENETIC ALGORITH
[8]  
[Anonymous], 1966, Artificial_Intelligence_Through_Simulated Evolution
[9]  
[Anonymous], STAT INFERENCE COMPU
[10]  
[Anonymous], P NATO ADV RES WORKS