Study On Improved Grey Wolf Optimizer And Its Application In Paramrter Estimation

Grey Wolf Optimizer is a new intelligent optimization algorithm,which is proposed in 2014,it is inspired by the social hierarchy and the hunting behavior of grey wolves.It has the advantages of simple structure,few parameters to be set and easy to implement in experimental coding.At present,it has been widely applied in many fields.However,the GWO algorithm has the disadvantages of low accuracy and slow convergence speed.This paper focuses on the improvement of GWO algorithm and the widening of its application scope.The main work is proposed three improved algorithms of SMIGWO?IGWO?CGWO,and estimated the parameters of the three models of Muskingum,Richards,GM(1,1),the details are as follows:(1)An improved grey wolf optimization algorithm based on simplex method(SMIGWO)is proposedIn order to solve the problem that grey wolf optimizer about the dependence on the initial population,chaotic Iterative sequence is used instead of random method to produce the initial population,which makes the position distribution of grey wolf more uniform.When the convergence factor is updated,the inverse incomplete function is introduced,which makes the algorithm achieve a balance in global search and local search,and the four operators of simplex method are used to deal with the gray wolf with poor position,which reduces the possibility of the algorithm falling into the local area.The improved algorithms of the three strategies are called SMIGWO algorithm.The experimental results on 10 test functions show that compared with the basic GWO,SquareGWO,NGWO,HGWO,PSO and BFA algorithms,the solution accuracy of SMIGWO algorithm is improved to a certain extent,and the convergence speed is faster.(2)Parameter estimation for Muskingum model based on the IGWO algorithm is proposedIn order to improve the computation accuracy of the Muskingum flood routing model,a new method of parameter estimation for Muskingum model based on the improved grey wolf optimizer(IGWO)is proposed and applied to the flood calculation in the south canal between Chenggouwan and Linqing River.The experimental results show that IGWO can effectively estimate the parameters of the Muskingum model.Compared with the other methods,IGWO has higher calculation accuracy and better optimization performance.(3)Parameter estimation for Richards model based on CGWO algorithm is proposedOn the basis of analyzing the insufficiency of grey wolf optimizer,an improved grey wolf optimization algorithm(CGWO)is proposed.The proposed algorithm adopts the convergence factor based on the variation of cosine law,and the weight based on the Euclidean distance of the step length is introduced.The simulation experimental results show that the CGWO algorithm has better optimization performance,and it's calculation accuracy is more higher.Finally,the prediction of the growth concentration of glutamic acid bacteria is taken as an example,and the parameters of the Richards model are estimated by CGWO algorithm.The root-mean-square error and the mean absolute error are used as evaluation indexes.Compared with the results of PSO algorithm,GA algorithm and VS-FOA algorithm,the CGWO algorithm can effectively estimate the parameters of the Richards model.(4)Forecasting natural gas consumption with a GM(1,1)model based on GWO algorithmIn order to improve the forecasting accuracy of GM(1,1)model,an improved GM(1,1)model based on grey wolf optimizer is proposed(GWOGM(1,1)).The proposed model uses GWO to optimize the development coefficient and grey control parameter of GM(1,1)model,minimizing the average relative percentage errors between the actual value and predicted value.The total natural gas consumption of household and total natural gas consumption in China from 2001 to 2013 are simulated,verified the validity of the GWOGM(1,1)model.Compared with the traditional GM(1,1)model and the Verhulst model,the prediction accuracy of the model is more higher.