Research On Resource Optimization Technology In Future Wireless Communication

With the development of communication technology,people's requirements for user's delay and energy efficiency are getting higher and higher.In order to reduce the user's delay and meet the indoor and outdoor data needs,in the future mobile communication network,a large number of small base stations(SBSs)will be arranged intensively,so as to shorten the physical distance between the transmitter and the receiver,and enhance the user's experience.Small base stations deployed by users are flexible in configuration,which can effectively reduce the cost of deployment and improve energy efficiency while reducing interference.In addition,the deployment of dense small base stations can also solve the problem of blind area coverage and realize the need for users to maintain seamless connections.The access of a large number of small base stations makes the research on resource optimization of base stations particularly important.Therefore,in this paper,based on convex optimization and deep learning theory,base station resources will be optimized in three aspects,the specific work can be summarized as follows:In the research of resource optimization of energy harvesting communication system,this paper first introduces the related research background,mainly the traditional energy harvesting communication system and the recently proposed energy borrowing communication system.Secondly,on the basis of the energy borrowing communication system,this paper proposes an energy despoiting communication system based on energy cooperation between base station and power grid,that is,base station can store surplus energy into power grid according to its transmission strategy to obtain energy interest.In the energy despoiting communication system,besides the base station can obtain energy gain,the power grid can further alleviate the power supply pressure during the peak period of power consumption,so as to achieve a win-win situation.In the research of resource optimization in wireless caching network,this paper first introduces the traditional wireless caching optimization model,which mainly includes optimizing the caching strategy of small base station only and jointly optimizing the caching strategy of small base station and the routing strategy of users.Secondly,based on traditional optimization problems,this paper proposes a wireless cache network with base station selection,so that base station selection is also included into the optimization scope.The simulation results show that the average user delay decreases compared with the random-selected cached small base stations.In the resource optimization of space modulation system,this paper first introduces the basic principles of traditional antenna selection algorithm and power allocation algorithm,and redefines the antenna selection problem and power allocation problem as a classification problem.Then a method based on support vector machine(SVM)for solving this problem is instrduced.Secondly,based on the theory of deep learning,a multi-layer perceptron(MLP)is designed to solve the classification problem of antenna selection and power allocation.Finally,the performance of the algorithm is verified by simulation.At last,the contribution of this paper is summarized and the future research directions are discussed.