MIME: Mobility-Induced Dynamic Matching for Partial Offloading in Vehicular Edge Computing

Autonomous vehicles (AVs) execute compute-intensive control operations like adjusting speed and steering, causing significant energy dissipation and latency due to resource-limited onboard units (OBUs). Offloading these tasks to Roadside Units (RSUs) is a solution, but it faces challenges. First, the stringent latency requirements are impacted by the vehicle’s stochastic velocity. Second, allocating limited RSU resources to numerous vehicles within its coverage area is difficult. This paper proposes the MIME framework to address these issues. We use Discrete Fourier transform (DFT) that computes the average velocity over an aperiodic velocity signal extracted from a real-world dataset. For resource allocation, we model it as matching with externalities, using reactive preferences based on vehicle speed and location. We present an efficient, scalable, stable solution, showing a 24.61% and 11.2% reduction in offloading latency and energy for the inD dataset, and a 5.6% and 5.52% reduction for the SUMO dataset.