Multi-step Optimization of Biogeography-based Optimization
The information analysis and processing are difficult research areas.Traditional algorithms perform poorly, especially for the multi dimensional, time-varying and nonlinear systems.In this paper we present multi-step optimization methods for the standard Biogeography-based Optimization (BBO) algorithm.The optimization methods include recalculating the fitness function and reordering the habitats after migration and before mutation.The optimized BBO algorithm, only mutates the worst parts, and removes the undesirable information.So the maximum mutation rate may be larger than the standard BBO algorithm.At the same time, exploring more appropriate migration model so as to accelerate the exchange of information and improve the convergence rate.Running on benchmark functions many times, the simulation results prove that the optimal algorithm has achieved the expected effects.The optimized algorithm and more appropriate migration model can help to accelerate the optimization speed and to avoid premature.So this new algorithm has a strong ability to process information.
intelligence algorithms nonlinear systems BBO information
ZHU Chao PEI Lun XU Tingting JIN Dingshou
Wuhan University of Technology, Wuhan 430070, China Huazhong University of Science and Technology, Wuhan 430074, China
国际会议
武汉
英文
239-243
2016-10-21（万方平台首次上网日期，不代表论文的发表时间）