Task Offloading and Resource Allocation in Mobile Edge Computing Assisted Vehicular Networks Across Multiple Regions

The widespread adoption of Autonomous Vehicles (AVs) necessitates Mobile Edge Computing (MEC) to offload computation-intensive tasks, thereby minimising energy consumption while maintaining real-time responsiveness for critical operations such as obstacle avoidance, lane keeping, adaptive cruise control, and intersection management. However, optimising task offloading and resource allocation poses significant challenges due to the AVs' constrained battery life and limited processing capacity. To tackle this, we propose a unified framework integrating Optimal Stopping Theory (OST), Deep Reinforcement Learning (DDPG), and a Genetic Algorithm (GA). OST determines the optimal offloading checkpoint, while DDPG dynamically optimises resource allocation to minimise energy consumption and ensure rapid responsiveness for realtime autonomous operations. Additionally, GA enhances MEC efficiency by optimising the execution order in scenarios where multiple tasks need to be offloaded. Simulation results show that OST improves offloading performance by at least 9.4% compared to conventional strategies. The DDPG-based approach reduces vehicle energy consumption by at least 24.7%, while the GA method decreases queue waiting times by 67.6% and reduces failed offloading tasks by 20%. This framework effectively balances energy efficiency and task latency while ensuring reliable and responsive AV operations in the MEC-assisted vehicular network.