FAQ: A Fuzzy-Logic-Assisted <i>Q</i>-Learning Model for Resource Allocation in 6G V2X

Zhang, Minglong; Dou, Yi; Marojevic, Vuk; Chong, J. Michael; Chan, Henry C. B.

doi:10.1109/jiot.2023.3294279

Cited by 3 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, future 6G V2X sidelink systems can leverage machine learning-based resource allocation algorithms, particularly reinforcement learning (RL) [110][21] [111], which optimize performance through environmental learning. Studies have indicated that a mixed approach with RL can also benefit resource allocation, becoming a mandate in future sidelink scenarios [112]. RL-based resource allocation involves an agent making decisions based on the system state and received rewards.…”

Section: E Machine Learning(ml)-aided Resource Allocation For V2x Sid...mentioning

confidence: 99%

Towards 6G V2X Sidelink: Survey of Resource Allocation—Mathematical Formulations, Challenges, and Proposed Solutions

Annu,

Rajalakshmi

2024

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

The advent of 6G marks a transformative phase in wireless communication, ushering in a hyperconnected experience. This paper explores optimizing sidelink technologies in Vehicle-to-Everything (V2X) communication through integrating 6G capabilities. Emphasizing challenges in sidelink resource allocation, the study introduces mathematical solutions. The survey further investigates the evolution of Cellular-V2X (C-V2X) and sidelink standardization within the 6G V2X Sidelink context, highlighting key features and applications. Additionally, it examines inter-UE coordination, resource re-evaluation, and pre-emption operations in 5G-V2X Sidelink, addressing associated challenges and mathematical formulations. The paper focuses on power-based resource allocation in 5G-V2X, addressing challenges and proposing solutions for the 6G V2X Sidelink landscape. Encompassing direct communication, collision issues, spectrum compliance, resource fairness, uncertainty, and interference management, the survey comprehensively explores challenges and solutions in current sidelink resource allocation. It evaluates traditional and emerging techniques, such as cognitive radio, cooperative communication, power control, dynamic spectrum access, ML-aided allocation, blockchain-enabled allocation, and edge computing-driven allocation. The resource allocation requirements for diverse V2X services in 6G V2X Sidelink are outlined, explicitly focusing on Vehicular to Vehicular (V2V), Vehicular to Infrastructure (V2I), Vehicular to Pedestrian (V2P), and other V2X services, addressing their specific needs.

show abstract

Section: E Machine Learning(ml)-aided Resource Allocation For V2x Sid...mentioning

confidence: 99%

Towards 6G V2X Sidelink: Survey of Resource Allocation—Mathematical Formulations, Challenges, and Proposed Solutions

Annu,

Rajalakshmi

2024

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…These methods aim to optimize resource allocation decisions while considering computation offloading. Additionally, in [ 20 ], a novel fuzzy-logic-assisted Q-learning model (FAQ) is proposed, leveraging the advantages of the centralized allocation mode. The FAQ model aims to maximize network throughput while minimizing interference caused by concurrent transmissions during resource allocation.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Resource Allocation for V2V Communication with Spectrum–Energy Efficiency Maximization

Xu,

Wang,

Song

et al. 2023

Sensors

View full text Add to dashboard Cite

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.

show abstract