Research On Resource Management Method Of Wireless Communication Network Based On UAV-assisted

With the explosive growth of smart terminals and multimedia applications,human society has gradually become more dependent on information networks in daily life,industrial production,economic development and social management,and traditional cellular networks are therefore facing the problems of spectrum shortage and increasing energy consumption.UAV communication and Device-to-Device(D2D)communications can utilize the existing spectrum resources and infrastructure of cellular networks,and are considered as an effective way to improve spectrum efficiency and reduce the increasing energy consumption while guaranteeing the quality of service(Qo S)of users.Therefore,this paper investigates the resource allocation problem for UAV-assisted D2 D communication and proposes different resource allocation strategies to address the optimal energy efficiency and bandwidth efficiency in two different application scenarios.In the UAV-assisted Energy Harvesting D2 D cellular network scenario,an energy efficiency optimization algorithm is proposed to address the energy efficiency problem while guaranteeing user Qo S.First,with the goal of maximizing user energy efficiency in the network,considering the constraints of user communication mode,spectrum allocation,transmission power,satisfaction of quality of service and energy state,the optimization problem is modeled as a mixed integer nonlinear programming problem.Then,the energy efficiency optimization problem is transformed into a Markov Decision Process(MDP)for solution.Next,an algorithm combining Deep Deterministic Policy Gradient(DDPG)with Long Short-Term Memory network(LSTM)is proposed.The algorithm uses DDPG to find the optimal strategy,and uses LSTM network to extract state features from the original continuous state to improve the convergence speed of the algorithm.Finally,in order to ensure effective exploration,this paper adds Gaussian noise to the actor network.The simulation results show that the proposed algorithm is superior to the traditional deep deterministic policy gradient algorithm and Deep Q-Network(DQN)algorithm in terms of energy efficiency and convergence.In the UAV-assisted Cellular Vehicle to Everything communication scenario,multiple flexible UAVs are deployed as the aerial Base Station to assist terrestrial Base Station for providing service to vehicular users with the objective of maximizing the bandwidth efficiency while concurrently guaranteeing the transmission rate and the low latency by adopting Network Slicing.Due to the uncertainty of the stochastic environment in the scenario,the optimization problem is modeled as a stochastic game,which is an extension of game theory to Markov Decision Process like environments for the case of multiple adaptive agents are involved to compete goals simultaneously.Nevertheless,the dynamic nature of both UAVs and vehicles pose the difficulty of perceiving and interacting with the unknown environment.Based on this,an LSTM network is used to extract the features of the observed data and learn the correlation between previous and recent observations to approximate the optimal policy.Simulation results show that the proposed scheme has better bandwidth efficiency compared to traditional DQN and DDPG algorithms with guaranteed Qo S for vehicular users.