Compressible access control method based on Q learning in large-scale Internet of Things

The invention relates to a compressible access control method based on Q learning in a large-scale Internet of Things, a user maintains a two-dimensional Q table, time slots and measurement vectors are selected through Q learning, problems caused by randomness of time slot and measurement vector selection by the user are effectively reduced, and the resource utilization rate is improved; through an odd-even frame access scheme, it is guaranteed that receiving of feedback information is matched with the large time delay problem of a satellite network; the problems of low utilization rate of system resources and poor flexibility are solved by combining adaptive frame length adjustment control of two-dimensional Q learning and compressed sensing. 本申请涉及一种大规模物联网中基于Q学习的可压缩接入控制方法，用户维护一个二维Q表，通过Q学习进行时隙与测量向量的选择，有效降低用户选择时隙与测量向量随机性带来的问题，提高资源利用率；通过奇偶帧接入方案保证反馈信息的接收匹配卫星网络的大时延问题；结合二维Q学习和压缩感知的自适应帧长调整控制，解决系统资源利用率低和灵活性差的问题。