文献类型：期刊文献

英文题名：Biogeography-based optimization in noisy environments

作者：Ma, Haiping[1,2];Fei, Minrui[2];Simon, Dan[3];Chen, Zixiang[1]

机构：[1]Shaoxing Univ, Dept Elect Engn, Shaoxing, Zhejiang, Peoples R China;[2]Shanghai Univ, Shanghai Key Lab Power Stn Automat Technol, Sch Mechatron Engn & Automat, Shanghai, Peoples R China;[3]Cleveland State Univ, Dept Elect & Comp Engn, Cleveland, OH 44115 USA

年份：2015

卷号：37

期号：2

起止页码：190

外文期刊名：TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL

收录：SCI-EXPANDED(收录号：WOS:000349317600005)、、EI(收录号：20150500478944)、Scopus(收录号：2-s2.0-84921847989)、WOS

基金：This material is based upon work supported by the National Science Foundation under grant number 0826124, the National Natural Science Foundation of China under grant numbers 61305078, 61074032 and 61179041 and the Shaoxing City Public Technology Applied Research Project under grant number 2013B70004.

语种：英文

外文关键词：Biogeography-based optimization; evolutionary algorithm; Kalman filter; noisy optimization; re-sampling

外文摘要：Biogeography-based optimization (BBO) is a new evolutionary optimization algorithm that is based on the science of biogeography. In this paper, BBO is applied to the optimization of problems in which the fitness function is corrupted by random noise. Noise interferes with the BBO immigration rate and emigration rate, and adversely affects optimization performance. We analyse the effect of noise on BBO using a Markov model. We also incorporate re-sampling in BBO, which samples the fitness of each candidate solution several times and calculates the average to alleviate the effects of noise. BBO performance on noisy benchmark functions is compared with particle swarm optimization (PSO), differential evolution (DE), self-adaptive DE (SaDE) and PSO with constriction (CPSO). The results show that SaDE performs best and BBO performs second best. In addition, BBO with re-sampling is compared with Kalman filter-based BBO (KBBO). The results show that BBO with re-sampling achieves almost the same performance as KBBO but consumes less computational time.