Font Size: a A A

Application Research Of Flower Pollination Algorithm

Posted on:2018-05-09Degree:MasterType:Thesis
Country:ChinaCandidate:C Y ZhaoFull Text:PDF
GTID:2348330512487087Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
Plants flower pollination algorithm(FPA)is a novel meta-heuristic algorithm inspired by the pollination behavior of plant flowers in nature.The local search and global search process of the algorithm corresponding to the self-pollination and cross-pollination process respectively,and the strength of these two form of search balanced by stochastic disturbance.By the reason of its simple structure,brilliant search capability,strong robustness and easy to implement and other characteristics,at present,the flower pollination algorithm has been successfully applied by many scholars to solve various complex combinational optimization problems.While with the deepening of the study,at the same time the researchers found that it also has drawbacks,poor performance in optimization precision and easily being trapped into local optimum has greatly limited the range of application of the plants flower pollination algorithm.This paper aiming to conduct deep research to the flower pollination algorithm and overcome the shortcomings of FPA,and the improved algorithm is applied to some classic optimization problems.The main purpose is to expand its theory and application range.In summary,in this paper,the main work includes the following two aspects:(1)Improve the plants flower pollination algorithm by adopting the idea of complex-valued encoding scheme.The population diversity of pollen grains was increased.Therefore,this strategy enhance the global detection ability of the algorithm,avoid premature algorithm trapped in local optimum prematurely.At the same time,overcome the shortcoming of the lower searching precision,which comprehensively improves the performance of the traditional plants flower pollination algorithm.(2)A new algorithm named elite opposition-based flower pollination algorithm,which can improves the solution in precision,accelerates convergence speed and avoid premature phenomenon of the algorithm,was introduced.And in this section,the main purpose is solving system of nonlinear equations by using the elite opposition-based flower pollination algorithm.Results of experiment show that using the elite opposition-based flower pollination algorithm can solve nonlinear equations with improving the algorithm accuracy,speed up the convergence speed of the algorithm,and avoid appear premature phenomenon with high stability.
Keywords/Search Tags:Meta-heuristic algorithm, traditional plants flower pollination algorithm, elite opposition based learning, complex-valued encoding, nonlinear equations
PDF Full Text Request
Related items