Privacy-Preserving Task Offloading in Vehicular Edge Computing

With the development of mobile edge computing (MEC), MEC-based task offloading of vehicle edge computing (VEC) has become popular due to its low delay. However, when vehicle users (VUs) offload data to the edge servers (ESs), user privacy may be leaked. In addition, communication among ESs can also threaten the privacy of VUs. Therefore, a five-objective optimization model including time delay of VLCU, time delay of ES, energy consumption, load balancing, and privacy protection degree is constructed. To solve the above model, an improved CMA-ES algorithm based on triple analysis decision variable grouping strategy (TADG-CMA-ES) is proposed. To improve the dimension reduction performance of the algorithm, the variables in divided subgroups are further grouped according to the convergence relevance degrees (CRD) of the variables.