Service Experience Oriented Cooperative Computing in Cache-Enabled UAVs Assisted MEC Networks

The unmanned aerial vehicle (UAV)-enabled multi-access edge computing (MEC) technology is opening up new opportunities in the integrated space-air-ground in the 5 G era and beyond. However, providing low-latency services solely from an overall perspective cannot ensure a high quality of experience (QoE) for user equipments (UEs). Therefore, we propose a service experience-oriented cooperative caching framework, where the UAVs can effectively serve each UE by providing communication and computing resources. A novel metric called service experience ratio is defined to reflect the experience at the UEs. Under the constraints of UAV's energy budget and delay requirements, we consider jointly optimizing task offloading, resource allocation, trajectory planning, and service caching placement to maximize the service experience ratio. Since the original problem is a mixed- integer non-convex programming problem with a fractional structure, it is challenging to be solved in polynomial time. Based on Dinkelbach's method and convex optimization theory, we simplify the problem model and propose a four-stage alternating iterative service ratio maximization algorithm to solve this problem. Besides, we also analyze the convergence and complexity of our proposed algorithm. Numerical results demonstrate that the service experience ratio achieved by the proposed algorithm is 19%-34% higher than the comparative works.