“…Recently, the in-vehicle communication device has been evolving as an integrated device. In the in-vehicle communication, there is a problem that the complexity of the electronic control units (ECU) increases to about 150 per vehicle depending on the type and level of advanced driver assistance systems technology, so the need for an integrated ECU is emerging [15][16][17][18][19][20]. Even in V2X communication, if different devices are composed according to the service application, the physical configuration and interworking can be complicated.…”
We propose a thread-based modeling and analysis method for a vehicle-to-everything (V2X) communication device, according to the performance requirements of the V2X application. For a developer to develop a V2X device or application, its performance requirements must first be determined. Furthermore, the developer selects the hardware system to enable the service to function while satisfying the performance requirements. Through this process, the developer designs and creates the program in a manner that considers thread configuration and core mapping with the given hardware resources. Then, the performance evaluation of a system is tested via instruction-level program analysis with executable programs. This process is an essential procedure for developing a program that satisfies the performance requirements. However, the debugging procedure repeated through program development, performance analysis, and program modification requires significant time and is costly. Hence, to reduce the time and cost of unnecessary work, we propose a thread-level modeling and analysis method using a queueing theory for a V2X communication device that can be applied at the design level. First, we propose a thread-level performance modeling and analysis method based on queuing theory in a multi-core-based vehicle service system. Furthermore, we analyze the performance of a multi-core-based vehicle service system utilizing the proposed method.
“…Recently, the in-vehicle communication device has been evolving as an integrated device. In the in-vehicle communication, there is a problem that the complexity of the electronic control units (ECU) increases to about 150 per vehicle depending on the type and level of advanced driver assistance systems technology, so the need for an integrated ECU is emerging [15][16][17][18][19][20]. Even in V2X communication, if different devices are composed according to the service application, the physical configuration and interworking can be complicated.…”
We propose a thread-based modeling and analysis method for a vehicle-to-everything (V2X) communication device, according to the performance requirements of the V2X application. For a developer to develop a V2X device or application, its performance requirements must first be determined. Furthermore, the developer selects the hardware system to enable the service to function while satisfying the performance requirements. Through this process, the developer designs and creates the program in a manner that considers thread configuration and core mapping with the given hardware resources. Then, the performance evaluation of a system is tested via instruction-level program analysis with executable programs. This process is an essential procedure for developing a program that satisfies the performance requirements. However, the debugging procedure repeated through program development, performance analysis, and program modification requires significant time and is costly. Hence, to reduce the time and cost of unnecessary work, we propose a thread-level modeling and analysis method using a queueing theory for a V2X communication device that can be applied at the design level. First, we propose a thread-level performance modeling and analysis method based on queuing theory in a multi-core-based vehicle service system. Furthermore, we analyze the performance of a multi-core-based vehicle service system utilizing the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.