基于上下文学习的电力物联网接入控制方法

Context-aware learning-based access control method for power IoT

针对6G时代电力物联网海量终端接入冲突严重、队列积压大、能量效率低等问题,提出了一种基于上下文学习的接入控制算法。所提算法基于强化学习和快速上行链路授权技术,考虑终端活跃与休眠2种状态,优化目标为在终端接入服务质量需求的长期约束下最大化网络总能量效率。利用李雅普诺夫优化对长期优化目标与约束进行解耦,将长期优化问题转化为单时隙独立的确定性子问题,并利用基于终端状态感知的上置信界算法进行求解。仿真结果表明,所提算法能够在满足终端接入服务质量需求的同时,有效提高网络总能量效率。相较于传统快速上行链路授权算法,所提算法可提高平均能量效率48.11%,提高满足接入服务质量需求的终端比例54.95%,降低平均队列积压83.83%。

In view of the problems of severe access conflicts,high queue backlog,and low energy efficiency in the massive terminal access scenario of the power Internet of things(power IoT)in 6G era,a context-aware learning-based access control(CLAC)algorithm was proposed.The proposed algorithm was based on reinforcement learning and fast uplink grant technology,considering active state and dormant state of terminals,and the optimization objective was to maximize the total network energy efficiency under the long-term constraint of terminal access service quality requirements.Lyapunov optimization was used to decouple the long-term optimization objective and constraint,and the long-term optimization problem was transformed into a series of single time-slot independent deterministic sub-problems,which could be solved by the terminal state-aware upper confidence bound algorithm.The simulation results show that CLAC can improve the network energy efficiency while meeting the terminal access service quality requirements.Compared with the traditional fast uplink grant,CLAC can improve the average energy efficiency by 48.11%,increase the proportion of terminals meeting access service quality requirements by 54.95%,and reduce the average queue backlog by 83.83%.