Satisfaction-driven services caching and resource allocation for UAV mobile edge computing

With the booming development of the Internet of Things, mobile edge computing of UAVs, as an emerging computing paradigm, offloads intensive tasks to network edge servers, thereby improving user data processing capacity. This paper designs a service caching and resource allocation algorithm that combines the quantum genetic algorithm and the traditional algorithm to address the needs of diversified and different prioritized user application services. Taking into account storage, computation, and energy constraints, the maximum user satisfaction and minimum service placement cost are achieved by jointly optimizing service caching, user offloading policy, time slot allocation, computational resource allocation, and flight trajectory. Specifically, the original problem is decomposed into three subproblems. First, the subproblem of service caching and user offloading is solved based on the quantum genetic algorithm. Second, the closed-form optimal solution for computational resource allocation is obtained based on the Lagrangian duality function. Then, the subproblem of time slot allocation and UAV trajectory optimization is solved using the successive convex approximation technique. Finally, the three subproblems are iterated several times to obtain their optimal solutions. The simulation results show that the algorithm can satisfy the diversified needs of users well, and can also have low services caching.