Research On Cognitive Heterogeneous Network Selection Algorithm In High-speed Railway Environment

With the direction of intelligence,digitization,and informationization development of high-speed railways,the demand for wireless communication services has continued to expand,the Heterogeneous wireless networks with a variety of access networks coexisting have become the development trend of the future railway mobile communication network architecture.However,the existing railway mobile communication system GSM-R belongs to digital narrowband mobile communication technology.The system has only 2 × 4MHz bandwidth,the service carrying capacity is limited,and adjacent frequency bands of GSM-R have been occupied,so it is difficult to increase the system capacity of GSM-R,even the next-generation railway mobile communication system LTE-R,will not be able to carry the applications of high-data-rate services of the future high-speed railway,and not be able to meet the demand for passenger broadband access services.The shortage of railway communication wireless spectrum resources will become more serious.Cognitive radio(CR)technology provides a feasible solution to solve the problem of spectrum shortage: combining the principles of security and stability of railway mobile communication systems,the key services(such as train control and dispatch communication)is carried by GSM-R/LTE-R,and high volume data communication services,which are related to high-speed rail service quality,but not related to railway transportation security.When the carrying capacity of the private network is exceeded,the cognitive users will select a reasonable network to achieve effective resource allocation,according to the perceived available spectrum holes.In the network selection process,how to quickly and effectively find idle spectrum that meets user needs in different time periods in different regions,so as to maximize user satisfaction,which is the key research topic in the field of wireless communications.Based on intelligent optimization decision algorithms,this dissertation studies the selection of cognitive heterogeneous networks in the high-speed rail communication environment.The main work and innovations are as follows:(1)Research on network selection algorithm in high-speed railway communication environment.The main problems of HSR users in the network selection process are analyzed and summarized: Firstly,the different service types have different requirements and satisfactions with the same network attribute value due to the diversity of user services;Secondly,many heterogeneous network selection algorithms have been proposed,most of them mainly focuses on the current access decision when the network attribute has not changed,and it does not consider the influence of the dynamic change of the network attribute after selecting the target network on the mobile user,the network reward function and the handover decision condition;Thirdly,the growing types of services and user requirements place higher demands on the response time of network access and the accuracy of access decisions.A single intelligent optimization algorithm cannot be satisfied.(2)Research on optimization of cognitive heterogeneous network selection algorithm.Aiming at the network selection problem of HSR users in the cognitive heterogeneous network environment,a network selection optimization algorithm based on the Markov decision process(MDP)is proposed.Considering the different types of service requirements,the MDP model and its reward function are constructed based on the quality of service(QoS)attribute parameters of the mobile users,and the network attribute weights are calculated by using the analytic hierarchy process(AHP).The network handoff decision condition is designed according to the different types of user services and the time-varying characteristics of the network,and the MDP model is solved by using the genetic algorithm and simulated annealing(GA-SA),thus,users can seamlessly switch to the network with the best long-term expected reward value.(3)Cognitive heterogeneous network selection algorithm simulation research.This dissertation use MATLAB simulation software to analysis and compare the performance among the algorithm in this dissertation and similar algorithms mentioned in other dissertations.The results show that: this proposed algorithm has good convergence performance,and can guarantee that users with different service types will obtain satisfactory expected total reward values and have low numbers of network handoffs.