Study On Optical Communications, Volume. 49, Issue 3, 71(2023)
Spectrum Resourse Management Method of V2X based on Deep Reinforcement Learning
Figures & Tables(11)
Fig. 3. The efficiency of V2I linkη1 on different transmission load K
Fig. 4. The efficiency of V2V linkη2 on different transmission load K
Fig. 5. The efficiency of V2X communication networkη3 on different transmission load K
Fig. 6. The V2I link efficiency η1 of three algorithms at different speeds
Fig. 7. The V2V link efficiency η2 of three algorithms at different speeds
Fig. 8. The V2X communication network efficiency η3 of three algorithms at different speeds
Table 1. Vehicle environment simulation parameters
View tableView in ArticleTable 1. Vehicle environment simulation parameters
参数类型 数值 V2I链路数量 4 V2V链路数量 1 载波频率/GHz 2 总带宽W/MHz 10 V2I功率等级/dBm 23 V2V功率等级/dBm [25,15,10,0] 电路损耗pc/dBm 16 基站天线增益/dBi 8 车辆天线增益/dBi 3 噪声功率σ2/dBm -114 传输负载K/Bytes 2×1 060 车辆速度V/km/h 30
Table 2. Channel model parameters of V2I link and V2V link
View tableView in ArticleTable 2. Channel model parameters of V2I link and V2V link
参数 V2I链路 V2V链路 路径损耗模型 128.1+37.6 log10d LOSin WINNER+B1 Manhattan 阴影分布 对数正态分布 对数正态分布 阴影标准差/dB 8 3 去相关距离/m 50 10 路径损耗和阴影更新/ms 100 100 快速衰落 瑞利衰落 瑞利衰落 快速衰落更新/ms 1 1
Table 3. The hyperparameters of Dueling-DQN
View tableView in ArticleTable 3. The hyperparameters of Dueling-DQN
参数类型 数值 隐藏层数量 3 学习率 0.001 优化器 RMSProp 更新步数 100 激活函数 ReLu 小批样本数 2 000 折扣因子 0.5
Tools
Get Citation
Copy Citation Text
Ming-hu WU, Bo JIN, Nan ZHAO, Ru WANG. Spectrum Resourse Management Method of V2X based on Deep Reinforcement Learning[J]. Study On Optical Communications, 2023, 49(3): 71
Paper Information
Category: Research Articles
Received: Jun. 21, 2022
Accepted: --
Published Online: Jun. 12, 2023
The Author Email: Nan ZHAO (nzhao@mail.hbut.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20