Network Selection Algorithm Of Heterogeneous Wireless Networks Based On Multiple Attribute Decision Making

With the rapid development of wireless communication technology,various endless wireless technologies have provided users with a heterogeneous network environment and ubiquitous access services.Under the trend of future network convergence,heterogeneous wireless networks and related technologies which is a promising research field,have attracted much attention of scholars at home and abroad.So,as one of its key technologies,network selection is naturally the focus of research.Based on the thinking of multiple attribute decision making,this paper studies the selection algorithm of heterogeneous wireless networks,and proposes two novel algorithms.The first one is to construct a fuzzy hierarchical structure based on intuition normal fuzzy numbers to obtain subjective weights of network attributes,combined with the coefficient of variation method to obtain objective weights,and then perform simple addition integration to obtain comprehensive weights of network attributes.The network ranking is performed by using the improved grey correlation analysis method.Simulation results show that the algorithm is consistent with other algorithms in the selection of candidate networks.The four types of services reduce the overall vertical switching rate by 25%,the performance has improved a lot.And the ping-pong effect is also effectively alleviated,thus can choose the most suitable network for the user to switch.The second algorithm relaxes the membership space of intuitionistic fuzzy numbers,constructs a fuzzy contrast matrix based on the Pythagorean fuzzy set theory to obtain the subjective weights of the network attributes,and uses the entropy weight method to obtain the objective weights of the attributes,then uses multiplication integration to obtain the comprehensive weights of the attributes.After that,the improved TOPSIS(Technique for Order Preference by Similarity to an Ideal Solution)method is used for network ranking where vertical distance is used to replace the European distance in the traditional TOPSIS method.Experiments show that the algorithm can effectively reduce the unnecessary switching rate of 8.5% under four different service types.And the optimal network selection is also consistent with other comparison algorithms,which can ensure that the selected network continues to provide services to users,thus meeting the expectations of the algorithm.