| 彭 艺,张 申,朱 豪,李启骞.联合机器学习的D2D通信多中继选择机制[J].电子测量与仪器学报,2020,34(3):149-154 |
| 联合机器学习的D2D通信多中继选择机制 |
| D2D communication multiple relay selection mechanism for joint machine learning |
| |
| DOI： |
| 中文关键词: D2D通信 多中继选择 Q-learning |
| 英文关键词:D2D communication multi relay selection Q-learning |
| 基金项目:国家自然科学基金（61761025）资助项目 |
|
|
|
|
| 摘要点击次数: 412 |
| 全文下载次数: 961 |
| 中文摘要: |
| 在D2D通信中，当源节点与目的节点间的距离过大时，可以通过引入中继节点来改善通信质量。当通信衰落严重时，单中继无法有效改善通信质量，此时可以引入多中继参与通信。针对D2D网络多中继通信，提出一种基于机器学习中Q learning算法的多中继选择机制。首先，判断源节点与目的节点之间通信是否需要合作中继;其次，通过考虑D2D网络中通信能量消耗来对Q learning算法中的Q函数的回报值进行定义;最后，通过计算D2D通信传输距离和通信接收端信噪比得出满意度函数。综合考虑回报值和满意度，获得协作中继集。仿真结果表明，基于Q learning算法的多中继协作可以显著减少传输延迟，平衡网络负载。 |
| 英文摘要: |
| In device to device(D2D) communication, when the distance between source node and destination node is too large, relay node can be introduced to improve the communication quality. When the communication decline is serious and single relay cannot improve the communication quality effectively, multi relay communication needs to be introduced. Aiming at multi relay communication in D2D communication, this paper proposes a multi relay selective communication mechanism based on Q learning in machine learning. First, determine whether cooperative relay is needed for communication between source node and destination node. Secondly, the return value of Q function in q learning algorithm is defined by considering the communication energy consumption in D2D network. Finally, the satisfaction function is obtained by calculating the transmission distance of D2D communication and the signal to noise ratio of the communication receiver. Considering the return value and satisfaction, a cooperative relay set is obtained. Simulation results show that multi relay cooperation based on Q learning algorithm can significantly reduce transmission delay and balance network load. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
