I. Introduction

Networking between electronic control units (ECUs) is critical for the proper functioning of modern vehicle features. Ever since the drive-by-wire concept became popular in the automotive industry, multiple ECUs have been designed to cooperate via in-vehicle networks (IVNs). Among the several networking protocols, the controller area network (CAN) currently dominates the market share of in-vehicle networking because it supports the critical requirements of vehicular applications [1]. These requirements include message prioritization, time synchronization, multicasting, and some hardware aspects such as being lightweight and noise-tolerant. More recently, connected and autonomous vehicles (CAVs) have emerged that rely on high-bandwidth sensors such as those capable of light detection and ranging, radio detection and ranging, and cameras. However, considering the fact that the CAN supports a limited throughput Mb/s, the CAN is no longer a promising protocol for CAVs. Although the conventional Ethernet and transmission control protocol (TCP)/Internet protocol (IP) stacks have been empirically verified in Internet and local area networks (LANs), they cannot replace the CAN because they do not satisfy all the requirements of vehicles. For example, a broadcasted packet is not time synchronized; a conventional switch does not respect the packet priority; a vehicle might be adversely affected by unexpected delay due to congestion control. These downsides of best-effort delivery should be addressed in real-time systems such as vehicles.