Research On Key Technologies Of Spectrum Resource Management For Heterogeneous Cellular Network In Smart Grid

With the development of smart grid,the installation of grid user-side devices has increased dramatically,which in turn has led to the rapid growth of grid data transmission.How to efficiently transmit these massive data is an important issue in smart grid.Through deploying small-size base stations and medium-size base stations and UAV base stations in traditional macro base station networks,heterogeneous cellular networks can effectively improve data transmission rates and network capacity.However,considering spectrum resource scarcity in the current situation,how to manage the existing wireless network spectrum resources to improve the communication quality and guarantee the quality of service requirements for grid userside devices is important.Based on exploring the channel allocation methods for smart grid heterogeneous cellular networks,this dissertation investigates the joint power allocation and trajectory design algorithms to improve the network performance and guarantee the quality of service for grid user-side devices.The main contributions of this dissertation are organized as follows:1.Heterogeneous networks can equalize traffic loads and cut down the cost of deploying cells.Thus,it is regarded to be the significant technique of the nextgeneration communication networks.Due to the non-convexity nature of the channel allocation problem in heterogeneous networks,it is difficult to design an optimal approach for allocating channels.To ensure the user quality of service as well as the long-term total network utility,this article proposes a new method through utilizing multi-agent reinforcement learning.Moreover,for the purpose of solving computational complexity problem caused by the large action space,deep reinforcement learning is put forward to learn optimal policy.A nearly-optimal solution with high efficiency and rapid convergence speed could be obtained by this learning method.Simulation results reveal that this new method has the best performance than other methods.2.Unmanned aerial vehicle(UAV)is regarded as an effective technology in future wireless networks.However,due to the non-convexity feature of joint power allocation and trajectory design(JPATD)issue,it is challenging to attain the optimal joint policy in multi-UAV networks.In this dissertation,a multi-agent deep reinforcement learningbased approach is presented to achieve the maximum long-term network utility while satisfying the user equipments’ quality of service requirements.Moreover,considering that the utility of each UAV is determined based on the network environment and other UAVs’ actions,the JPATD problem is modeled as a stochastic game.Due to the high computational complexity caused by the continuous action space and large state space,a multi-agent deep deterministic policy gradient method is proposed to obtain the optimal policy for the JPATD issue.Numerical results indicate that our method can obtain the higher network utility and system capacity than other optimization methods in multi-UAV networks with lower computational complexity.