Mobility-Aware Edge Caching for Minimizing Latency in Vehicular Networks

Abstract

This work proposes novel proactive caching schemes for minimizing the communication latency in Vehicular Ad Hoc Networks (VANETs) under freeway and city mobility models. The main philosophy that underlies these schemes is to exploit information that may be available a priori for vehicles' demands and mobility patterns. We consider two paradigms: cooperative, wherein multiple Roadside Units (RSUs) collaborate to expedite the transfer of information to the intended user, and non-cooperative, wherein each RSU operates independently of other RSUs in the network. To develop the proposed schemes, for each of the considered models we formulate optimization problems that expose the impact of velocity and demand profile of the vehicle on the optimal caching decision. Unfortunately, the developed formulations are NP-hard, and hence difficult to solve for moderate-to-large problems. To circumvent this difficulty, we use the insight developed through these formulations to develop practical caching algorithms based on the knapsack problem and suboptimal relaxations. These algorithms are shown to yield close-to-optimal solutions at much lower computation costs than the corresponding exhaustive search. Our numerical investigations suggest that the proposed proactive caching schemes yield substantial gains over the traditional caching policy, and their respective reactive baselines with no caching. Furthermore, the cooperative schemes are significantly more advantageous than their non-cooperative counterparts.