A Concurrent Message Processing Mechanism for Internet of Vehicles
Chang Liu, Ping Wang · 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · 2021
With the rapid development of the intelligent networked automobile industry, the current OBU (on-board-unit) and RSU (roadside-unit) have been installed on high-performance multi-core chips. The latest related technologies can already support 5th Generation (5G) communication. Therefore, how the upper-level application should adapt to the exponential growth trend of data volume has become an urgent problem in the industry. Aiming at the above problems, this paper proposes a multi-thread synchronization mechanism based on atomic operands and a blocking scheme based on condition variables. In the producer-consumer model, the message production process is optimized for the five types of messages in the Internet of Vehicles, and a more lightweight message queue with higher resource utilization is provided to users. Various parameters involved in this method have been tested in multiple scenarios. The experimental results show that in non-extreme scenarios, this method can maintain a good performance and smoothly complete the work of message production, consumption and analysis. A flexible configuration interface for users also provided to quickly adapt to different device platforms, ensuring the flexibility of functional software.