Enabling Efficient Emulation of Internet-of-Vehicles on a Single Machine: Practices and Lessons.

The rise of Intelligent Vehicles and next-generation networks accelerates the advent of Internet-of-Vehicles (IoV), where each vehicle acts as a node and interconnects with other nodes for data sharing and processing. The primary challenges for evaluating Human-Vehicle Interactions (HVI) designs in the context of IoV are (1) computation on limited on-vehicle hardware resources; and (2) varied network connectivity in different settings. Moreover, existing emulators are highly customized for specific scenarios, which can limit the comprehensiveness of evaluations for IoV. To this end, we present a relatively general and portable emulation platform, that is designed for evaluating a variety of novel HVI designs under different IoV settings. Our emulation platform consists of two key components: 1) an automatic extractor to extract workload patterns in different IoV topologies and 2) configurable network settings to examine different HVI designs in various network conditions. We then characterize two IoV applications to examine the feasibility of our proposed emulation platform.