Enhanced Deep Cooperative Q-Learning for Optimized Vehicle-to-Vehicle Communication in 5G/6G Networks


Ahmed, Tahir H. and Mahmud, Azwan and Abd. Aziz, Azlan and Yaacob, Syamsuri (2023) Enhanced Deep Cooperative Q-Learning for Optimized Vehicle-to-Vehicle Communication in 5G/6G Networks. In: 2023 14th International Conference on Information and Communication Technology Convergence (ICTC), 11-13 October 2023, Jeju Island, Korea, Republic of.

[img] Text
19.pdf - Published Version
Restricted to Repository staff only

Download (1MB)


In the era of 5G and forthcoming 6G, effective Vehicle-to-Vehicle (V2V) communication is crucial for many applications like autonomous driving, real-time traffic information sharing, and others. This work proposes a novel Enhanced Deep Cooperative Q-Learning (DCO-DQN) model to optimize V2V communication considering the volatile nature of wireless channels, device parameters, vehicular mobility, and history of interactions. The model is equipped with an advanced reward function to reflect multiple performance metrics, which is a clear distinction from existing methods. The comprehensive system model, implementation details, and results clearly show superior performance over traditional methods across various metrics and scenarios. A detailed comparison and analysis strengthen the case for adopting our method for future V2V communication in 5G/6G

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Wireless communication, 5G, V2V , Deep Q-Learning , AI/ML
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Engineering (FOE)
Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 21 Feb 2024 06:13
Last Modified: 21 Feb 2024 06:13
URII: http://shdl.mmu.edu.my/id/eprint/12098


Downloads per month over past year

View ItemEdit (login required)