TY - GEN
T1 - Collaborative Multi-Agent Resource Allocation in C-V2X Mode 4
AU - Saad, Malik Muhammad
AU - Islam, Md Mahmudul
AU - Tariq, Muhammad Ashar
AU - Khan, Muhammad Toaha Raza
AU - Kim, Dongkyun
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/8/17
Y1 - 2021/8/17
N2 - Intelligent Transport System (ITS) provides an efficient solution to road safety traffic. To support safety applications, cellular vehicle-to-everything (C-V2X) is developed by third generation partnership project (3GPP). C-V2X support two modes of communication as mode 3 and mode 4. In mode 4, vehicles reserve the resources based on their local observations using semi-persistent scheduling (SPS). If two vehicles, simultaneously select the same resources, it will lead to resource contention. This arises the consensus problem. To overcome this, in this paper we proposed the multi agent collaborative deep reinforcement learning based scheme. A single deep Q network (DQN) is trained for each zone. Each zone is preconfigured with resources which constitute a resource pool. A reward function is shared between the vehicles that belong to the same pool. This approach makes the vehicles to collaborate rather than compete in selecting the resources for their transmission. The proposed scheme is compared with the random resource allocation in C-V2X. The results show that the proposed scheme outperforms even in dense vehicular environment.
AB - Intelligent Transport System (ITS) provides an efficient solution to road safety traffic. To support safety applications, cellular vehicle-to-everything (C-V2X) is developed by third generation partnership project (3GPP). C-V2X support two modes of communication as mode 3 and mode 4. In mode 4, vehicles reserve the resources based on their local observations using semi-persistent scheduling (SPS). If two vehicles, simultaneously select the same resources, it will lead to resource contention. This arises the consensus problem. To overcome this, in this paper we proposed the multi agent collaborative deep reinforcement learning based scheme. A single deep Q network (DQN) is trained for each zone. Each zone is preconfigured with resources which constitute a resource pool. A reward function is shared between the vehicles that belong to the same pool. This approach makes the vehicles to collaborate rather than compete in selecting the resources for their transmission. The proposed scheme is compared with the random resource allocation in C-V2X. The results show that the proposed scheme outperforms even in dense vehicular environment.
KW - Cellular vehicle-to-everything (C-V2X)
KW - Deep reinforcement Learning
KW - Distributed Resource Allocation
KW - Semi-Persistent Scheduling (SPS)
UR - http://www.scopus.com/inward/record.url?scp=85115604047&partnerID=8YFLogxK
U2 - 10.1109/ICUFN49451.2021.9528717
DO - 10.1109/ICUFN49451.2021.9528717
M3 - Conference contribution
AN - SCOPUS:85115604047
T3 - International Conference on Ubiquitous and Future Networks, ICUFN
SP - 7
EP - 10
BT - ICUFN 2021 - 2021 12th International Conference on Ubiquitous and Future Networks
PB - IEEE Computer Society
T2 - 12th International Conference on Ubiquitous and Future Networks, ICUFN 2021
Y2 - 17 August 2021 through 20 August 2021
ER -