UAV as Auxiliary Base Station uses Deep Learning to Conduct Research on Network Resource Allocation

With the development of UAV technology, using UAV as a base station in the air can quickly restore vehicle communications after disasters. In order to reduce the delay and maximize the rational use of bandwidth and power, this paper applies TDMA technology to UAV communication network, and proposes a joint optimization allocation strategy of bandwidth and power. First of all, a deep learning network needs to be trained. The use of deep learning can improve the accuracy of prediction. The reward mechanism is set through the change of delay. The purpose of training is to enable the UAV to choose the optimal bandwidth allocation coefficient under the dynamic change of the environment. Then, a joint optimization strategy is proposed to set the SNR threshold to ensure the communication quality. The user's transmission rate is calculated according to the Shannon formula, Finally, the scheme with minimum delay is selected as the final bandwidth and power allocation value. In the simulation experiment, compared with the previous traditional algorithm, the network performance has been further improved in terms of reducing delay and energy consumption, and what needs to be improved may be the problem of computation.