摘要
为解决无人机通信网络中数据调度行为中断概率过大的问题,实现对通信资源的合理分配,提出基于改进机器学习的无人机中继通信数据调度控制方法;设计基本网络架构,联合BMRC协议,设置URLLC数据链路单元,联合相关通信数据样本,求解通信中断概率的具体数值,实现对无人机中继通信网络资源的联合优化处理;分别计算时隙分配参量与带宽分配参量,并以此为基础,确定无人机中继位置,实现对中继通信资源的调度;按照机器学习算法标准,定义PCA改进特征,从而完善改进机器学习算法,再联合最优控制器闭环,实现对通信数据调度行为的控制;实验结果表明,改进机器学习算法作用下,随着中继数据累积量的增大,无人机通信网络中数据调度行为中断概率的最大值只能达到7.3%,有效降低了中断概率,符合合理分配通信资源的实际应用需求。
To solve the high interruption probability of data scheduling behavior in unmanned aerial vehicle(UAV)communication networks and achieve the reasonable allocation of communication resources,a data scheduling control method for UAV relay communication based on improved machine learning is proposed.The BMRC protocol is combined to design the basic network architecture,and set the URLLC data link unit,the relevant communication data samples are combined to solve specific values of communication interruption probability,and achieve the joint optimization processing of drone relay communication network resources.The time slot allocation parameters and bandwidth allocation parameters are separately calculated,and based on this,the drone relay location is determined to achieve the scheduling of relay communication resources.According to the machine learning algorithm,the PCA improvement features are defined to improve the machine learning algorithm,and then combine with the optimal controller closed-loop to achieve the control of communication data scheduling behavior.The experimental results show that under the effect of improved machine learning algorithm,with the increase of relay data,the maximum outage probability of data scheduling behavior in the UAV communication network only reaches by 7.3%,which effectively reduces the outage probability and meets actual application requirements of reasonable allocation communication resources.
作者
苏彩玉
万海斌
SU Caiyu;WAN Haibin(Guangxi Vocational&Technical Institute of Industry,Baise 530001,China;School of Computer and Electronic Information,Guangxi University,Yulin 530004,China)
出处
《计算机测量与控制》
2024年第5期109-114,136,共7页
Computer Measurement &Control
基金
广西高校中青年教师科研基础能力提升项目(2022KY1296)。
关键词
改进机器学习
中继通信
数据调度
数据链路单元
BMRC协议
时隙带宽
最优控制器
中断概率
improving machine learning
relay communication
data scheduling
data link unit
BMRC protocol
time slot bandwidth
optimal controller
interruption probability
