Edge Caching and Computation Management for Real-Time Internet of Vehicles: An Online and Distributed Approach

Vehicular Edge Computing (VEC) is expected to be an effective solution to meet the ultra-low delay requirements of many emerging Internet of Vehicles (IoV) services by shifting the service caching and the computation capacities to the network edge. However, due to the constraints of the multidimensional (storage-computing-communication) resources capacities and the cost budgets of vehicles, there are two main issues need to be addressed: 1) How to collaboratively optimize the service caching decision among edge nodes to better reap the benefits of the storage resource and save the time-correlated service reconfiguration cost? 2) How to allocate resources among various vehicles and where vehicular requests are scheduled to improve the efficiency of the computing and communication resources utilization? In this paper, we formulate an edge caching and computation management problem that jointly optimizes the service caching, the request scheduling, and the resource allocation strategies. Our focus is to minimize the time-average service response delay of the random arriving service requests in a cost-efficient way. To cope with the dynamic and unpredictable challenges of IoVs, we leverage the combined power of Lyapunov optimization, matching theory, and consensus alternating direction method of multipliers to solve the problem in an online and distributed manner. Theoretical analysis shows that the developed approach achieves a close-to-optimal delay performance without relying on any prior knowledge of the future network information. Moreover, simulation results validate the theoretical analysis and demonstrate that our algorithm outperforms the baselines substantially.

Automated summary

Vehicular Edge Computing (VEC) is proposed as a solution to meet the low latency requirements of Internet of Vehicles (IoV) services, addressing the optimization of service caching and resource allocation to minimize service response delay.