Joint Sensing, Communication, and Computation Resource Allocation for Cooperative Perception in Fog-Based Vehicular Networks

Abstract

To enlarge the perception range and reliability of individual autonomous\nvehicles, cooperative perception has been received much attention. However,\nconsidering the high volume of shared messages, limited bandwidth and\ncomputation resources in vehicular networks become bottlenecks. In this paper,\nwe investigate how to balance the volume of shared messages and constrained\nresources in fog-based vehicular networks. To this end, we first characterize\nsum satisfaction of cooperative perception taking account of its\nspatial-temporal value and latency performance. Next, the sensing block\nmessage, communication resource block, and computation resource are jointly\nallocated to maximize the sum satisfaction of cooperative perception, while\nsatisfying the maximum latency and sojourn time constraints of vehicles. Owing\nto its non-convexity, we decouple the original problem into two separate\nsub-problems and devise corresponding solutions. Simulation results demonstrate\nthat our proposed scheme can effectively boost the sum satisfaction of\ncooperative perception compared with existing baselines.\n