Genetic Algorithm-Based Joint Task Offloading and Resource Allocation in UAV-Enabled Vehicular Edge Computing

Integrating Unmanned Aerial Vehicles (UAVs) into Vehicular Edge Computing (VEC) establishes UAV-enabled VEC, effectively addressing potential degradation of offloading per-formance caused by overloaded edge servers in urban aggregation areas. However, the limited dimensions of UAV s impose constraints on their onboard energy and computational capa-bilities, thereby presenting significant challenges in achieving efficient task offloading. Motivated by this, this work studies task offloading and resource allocation in UAV-enabled VEC for enhancing the offloading performance. Specifically, we propose a task offloading framework in UAV-enabled VEC that per-forms task offloading for vehicles. Based on this framework, we formulate a novel problem called Task Offloading and Resource Allocation (TORA), aiming to minimize the weighted sum of completion time and energy consumption for processing computational tasks. Furthermore, due to the non-convex nature of the TORA problem, we propose a genetic algorithm-based joint task offloading and resource allocation scheme to effectively solve the TORA problem. This scheme comprises a chromosome representation for encoding solutions and a set of reproduction operators (i.e., selection, crossover, and mutation) for solution evolution. Finally, the proposed scheme is evaluated through a constructed simulation model, and the experimental results substantiate its effectiveness.