Performance Analyses of Differential Evolution Algorithm Based on Dynamic Fitness Landscape

Performance Analyses of Differential Evolution Algorithm Based on Dynamic Fitness Landscape

Kangshun Li (South China Agricultural University, Guangzhou, China), Zhuozhi Liang (South China Agricultural University, Guangzhou, China), Shuling Yang (South China University of Technology, Guangzhou, China), Zhangxing Chen (University of Calgary, Calgary, Canada), Hui Wang (South China Agricultural University, Guangzhou, China) and Zhiyi Lin (Guangdong University of Technology, Guangzhou, China)
DOI: 10.4018/IJCINI.2019010104
OnDemand PDF Download:
No Current Special Offers


Dynamic fitness landscape analyses contain different metrics to attempt to analyze optimization problems. In this article, some of dynamic fitness landscape metrics are selected to discuss differential evolution (DE) algorithm properties and performance. Based on traditional differential evolution algorithm, benchmark functions and dynamic fitness landscape measures such as fitness distance correlation for calculating the distance to the nearest global optimum, ruggedness based on entropy, dynamic severity for estimating dynamic properties, a fitness cloud for getting a visual rendering of evolvability and a gradient for analyzing micro changes of benchmark functions in differential evolution algorithm, the authors obtain useful results and try to apply effective data, figures and graphs to analyze the performance differential evolution algorithm and make conclusions. Those metrics have great value and more details as DE performance.
Article Preview

Recently, fitness landscape is used in many aspects such as search-based software testing problems (Aleti, Moser & Grunske, 2016) producing approximate solutions of a combinatorial optimization problem through climbing combinatorial fitness landscapes (Basseur & Ffon, 2015). Different evolutionary algorithms are improved from different aspects based on traditional algorithms in order to attain better performance including faster convergence speed, fewer parameters, less running time and so on. But here, we are not going to focus on how to improve or propose new algorithms. On the contrary, we are going to employ fitness landscape analysis to study the performance of differential evolution algorithm in many ways. The concept of fitness landscape has been adopted widely in recent years in many fields. (Bolshakov, Pitzer, & Affenzeller, 2011)) considered applying fitness landscape analysis in simulation optimization for meta-optimization purposes and new insights are obtained in the field of fitness landscapes analysis for stochastic problems. (Malan & Engelbrecht, 2013b) proposed using ruggedness, funnels and gradients in the fitness landscapes analyzed and evaluated the performance and the effect of traditional particle swarm optimization (PSO). According to experimental results, these three metrics have valued as part-predictors of PSO performance on unknown problems if used in conjunction with measures approximating other features that have been linked to problem difficulty for PSOs. Meanwhile, they investigated whether a link can be found between problem characteristics and algorithm performance for PSOs. But there are not new insights to show algorithm performance clearly.

Complete Article List

Search this Journal:
Volume 16: 1 Issue (2022)
Volume 15: 4 Issues (2021)
Volume 14: 4 Issues (2020)
Volume 13: 4 Issues (2019)
Volume 12: 4 Issues (2018)
Volume 11: 4 Issues (2017)
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing