Fuzzy Q-Learning-Based Opportunistic Communication for MEC-Enhanced Vehicular Crowdsensing
Trung Thanh Nguyen, Truong Thao Nguyen, Thanh Hung Nguyen, Phi Le Nguyen
TL;DR
This work addresses the OCVC problem in MEC‑enhanced vehicle crowdsensing, aiming to minimize 4G transmission cost while keeping data latency below a threshold $δ$. It introduces a distributed Fuzzy Q‑learning offloading strategy that leverages three transmission modes (4G, RSU via Wi‑Fi, and neighbor relays) and uses fuzzy logic to adapt the reward parameter $\theta$ to changing network conditions. The approach achieves a 30–40% reduction in 4G usage while ensuring 99% of packets meet the latency requirement, as demonstrated by a Python-based simulator using real urban mobility data. The results support practical deployment of cost- and energy-efficient, latency-aware MEC‑enabled vehicular crowdsensing in urban environments.
Abstract
This study focuses on MEC-enhanced, vehicle-based crowdsensing systems that rely on devices installed on automobiles. We investigate an opportunistic communication paradigm in which devices can transmit measured data directly to a crowdsensing server over a 4G communication channel or to nearby devices or so-called Road Side Units positioned along the road via Wi-Fi. We tackle a new problem that is how to reduce the cost of 4G while preserving the latency. We propose an offloading strategy that combines a reinforcement learning technique known as Q-learning with Fuzzy logic to accomplish the purpose. Q-learning assists devices in learning to decide the communication channel. Meanwhile, Fuzzy logic is used to optimize the reward function in Q-learning. The experiment results show that our offloading method significantly cuts down around 30-40% of the 4G communication cost while keeping the latency of 99% packets below the required threshold.