Non-orthogonal access uplink transmission time optimization method based on deep reinforcement learning

Abstract

The invention relates to a non-orthogonal access uplink transmission time optimization method based on deep reinforcement learning, which comprises the following steps: (1) there are I mobile users intotal under the coverage of a base station; while a service quality that satisfies a mobile user is proposed, the uplink transmission time of the mobile user and the total energy consumption of all users are minimized in the situation that the uploading amount formula of the mobile user is given; (2) the ORRCM problem is to find the optimal overall radio resource consumption in the case that theuploading amount formula of the mobile user is given; the ORRCM problem is observed, and it is learned that the objective function thereof has only one variable t; (3) the optimal uplink transmissiontime t* is obtained through a reinforcement learning algorithm, so that the optimal overall radio resource consumption is obtained; (4) the iterative process is repeated until the optimal uplink transmission time t* is obtained, so as to obtain the optimal overall radio resource consumption.

Description

technical field [0001] The invention belongs to the communication field, and relates to a non-orthogonal access uplink transmission time optimization method based on deep reinforcement learning. Background technique [0002] The rapid development of mobile Internet services has caused enormous traffic pressure on the cellular wireless access network. Due to limited wireless resources, using non-orthogonal access technology to allow mobile users to share the same channel at the same time provides an effective method for wireless access to achieve ultra-high throughput and large-scale connections in the future 5G network. Contents of the invention [0003] In order to overcome the disadvantages of long uplink transmission time and high total energy consumption of all mobile users in the prior art, the present invention provides a non-orthogonal interface based on deep reinforcement learning that minimizes uplink transmission time and total energy consumption of all mobile us...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the disadvantages of long uplink transmission time and high total energy consumption of all mobile users in the prior art, the present invention provides a non-orthogonal interface based on deep reinforcement learning that minimizes uplink transmission time and total energy consumption of all mobile users. In order to optimize the uplink transmission time, the present invention aims at the difficulty that the uplink transmission time is too large, mainly considers the use of non-orthogonal access technology to transmit data, and studies a non-orthogonal access uplink transmission time based on deep reinforcement learning Optimization

Images