Joint mode selection and resource allocation for cellular V2X communication using distributed deep reinforcement learning under 5G and beyond networks

被引:3
作者
Yadav, Shalini [1 ]
Rishi, Rahul [1 ]
机构
[1] Maharshi Dayanand Univ, Comp Sci & Engn, UIET, Rohtak, Haryana, India
关键词
V2X; V2V; V2R; MDP; DDQN; DRL; QoS; MANAGEMENT; LATENCY; SCHEME; SPECTRUM;
D O I
10.1016/j.comcom.2024.04.015
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Vehicle -to -everything (V2X) communication via cellular networks is a promising technique for 5G and beyond networks. The cars interact directly with one another, as well as with the infrastructure and various vehicles on the road, in this mode. It enables the interchange of time -sensitive and safety -critical data. Despite these benefits, unstable vehicle -to -vehicle (V2V) communications, insufficient channel status information, high transmission overhead, and the considerable communication cost of centralized resource allocation systems all pose challenges for defense applications. To address these difficulties, this study proposes a combined mode selection and resource allocation system based on distributed deep reinforcement learning (DRL) to optimize the overall network sum rate while maintaining the reliability and latency requirements of V2V pairs and the data rate of V2R connections. Because the optimization issue is non -convex and NP -hard, it cannot be solved directly. To tackle this problem, the defined problem is first translated into machine learning form using the Markov decision process (MDP) to construct the reward function and decide whether agent would conduct the action. Following that, the distributed coordinated duelling deep Q -network (DDQN) method based on prioritized sampling is employed to improve mode selection and resource allocation. This approach learns the action -value distribution by estimating both the state -value and action advantage functions using duelling deep networks. The results of the simulation show that the suggested scheme outperforms state-of-the-art decentralized systems in terms of sum rate and QoS satisfaction probability.
引用
收藏
页码:54 / 65
页数:12
相关论文
共 38 条
[1]   Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles [J].
Aradi, Szilard .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (02) :740-759
[2]  
Ashraf MI, 2017, EUR CONF NETW COMMUN
[3]   Scheduling the Operation of a Connected Vehicular Network Using Deep Reinforcement Learning [J].
Atallah, Ribal F. ;
Assi, Chadi M. ;
Khabbaz, Maurice J. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2019, 20 (05) :1669-1682
[4]   CONNECTED ROADS OF THE FUTURE Use Cases, Requirements, and Design Considerations for Vehicle-to-Everything Communications [J].
Boban, Mate ;
Kousaridas, Apostolos ;
Manolakis, Konstantinos ;
Eichinger, Josef ;
Xu, Wen .
IEEE VEHICULAR TECHNOLOGY MAGAZINE, 2018, 13 (03) :110-123
[5]   Latency-Energy Tradeoff in Connected Autonomous Vehicles: A Deep Reinforcement Learning Scheme [J].
Budhiraja, Ishan ;
Kumar, Neeraj ;
Sharma, Himanshu ;
Elhoseny, Mohamed ;
Lakys, Yahya ;
Rodrigues, Joel J. P. C. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (11) :13296-13308
[6]   Energy-Delay Tradeoff Scheme for NOMA-Based D2D Groups With WPCNs [J].
Budhiraja, Ishan ;
Kumar, Neeraj ;
Tyagi, Sudhanshu .
IEEE SYSTEMS JOURNAL, 2021, 15 (04) :4768-4779
[7]   ISHU: Interference Reduction Scheme for D2D Mobile Groups Using Uplink NOMA [J].
Budhiraja, Ishan ;
Kumar, Neeraj ;
Tyagi, Sudhanshu .
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (09) :3208-3224
[8]   Deep-Reinforcement-Learning-Based Proportional Fair Scheduling Control Scheme for Underlay D2D Communication [J].
Budhiraja, Ishan ;
Kumar, Neeraj ;
Tyagi, Sudhanshu .
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (05) :3143-3156
[9]  
Budhiraja I, 2020, IEEE CONF COMPUT, P877, DOI 10.1109/INFOCOMWKSHPS50562.2020.9162839
[10]   LTE-V: A TD-LTE-Based V2X Solution for Future Vehicular Network [J].
Chen, Shanzhi ;
Hu, Jinling ;
Shi, Yan ;
Zhao, Li .
IEEE INTERNET OF THINGS JOURNAL, 2016, 3 (06) :997-1005