文献类型：期刊文献

英文题名：Intelligent Resource Allocation for V2V Communication with Spectrum-Energy Efficiency Maximization

作者：Xu, Chunning[1];Wang, Shumo[2];Song, Ping[2];Li, Ke[3];Song, Tiecheng[2,4]

第一作者：Xu, Chunning

通讯作者：Song, TC[1];Song, TC[2]

机构：[1]Southest Univ, Urban Planning & Design Inst, Sch Architecture, Nanjing 210096, Peoples R China;[2]Southeast Univ, Sch Informat Sci & Engn, Nanjing 210096, Peoples R China;[3]Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China;[4]Southeast Univ, Shenzhen Res Inst, Shenzhen 518057, Peoples R China

第一机构：Southest Univ, Urban Planning & Design Inst, Sch Architecture, Nanjing 210096, Peoples R China

通讯机构：[1]corresponding author), Southeast Univ, Sch Informat Sci & Engn, Nanjing 210096, Peoples R China;[2]corresponding author), Southeast Univ, Shenzhen Res Inst, Shenzhen 518057, Peoples R China.

年份：2023

卷号：23

期号：15

外文期刊名：SENSORS

收录：;EI(收录号：20233314573244);Scopus(收录号：2-s2.0-85167759963);WOS:【SCI-EXPANDED(收录号:WOS:001045769000001)】；

基金：This work was supported by the Key Research and Development Program of Jiangsu Province (No. BE2020084-2), the National Key Research and Development Program of China (No. 2020YFB1600104), and the Central Guidance on Local Science and Technology Development Fund of Shenzhen (No. 2021Szvup026).

语种：英文

外文关键词：vehicular networking; resource allocation; 5G network slicing; multi-agent deep Q learning

摘要：Aiming to address the limitations of traditional resource allocation algorithms in the Internet of Vehicles (IoV), whereby they cannot meet the stringent demands for ultra-low latency and high reliability in vehicle-to-vehicle (V2V) communication, this paper proposes a wireless resource allocation algorithm for V2V communication based on the multi-agent deep Q-network (MDQN). The system model utilizes 5G network slicing technology as its fundamental feature and maximizes the weighted spectrum-energy efficiency (SEE) while satisfying reliability and latency constraints. In this approach, each V2V link is treated as an agent, and the state space, action, and reward function of MDQN are specifically designed. Through centralized training, the neural network parameters of MDQN are determined, and the optimal resource allocation strategy is achieved through distributed execution. Simulation results demonstrate the effectiveness of the proposed scheme in significantly improving the SEE of the network while maintaining a certain success rate for V2V link load transmission.