Performance Evaluation of Microservices Centric In-network Computations for Internet of Vehicles

This paper presents the design and implementation of a multilayered microservices-centric in-network computation framework tailored for the Internet of Vehicular Networks. The proposed framework integrates a vehicular network layer, Edge computing layer, and Cloud to enhance network efficiency and minimize latency for time-critical vehicular applications. In the proposed work, modifications were made to the NDNsim codebase, integrating the C++ Boost Asio library to facilitate NDNsim-Edge communication for designated microservice computation. in additions, a microservice-centric driver assistance application is also emulated in Dotnet core with microservices deployed on various Edge and cloud servers. Moreover, Restful APIs have been developed, allowing the NDNsim layer, physical Edge layer, and Cloud stations to offload a microservice-centric computation request and retrieve the corresponding compute outcomes. Furthermore, the Entity framework is utilized to ensure proper tracking and management of the requests while an HTML-based user interface is developed for a visual representation of the request pattern. Extensive testbed experimentation revealed that the proposed framework highly optimized bandwidth consumption, reduces latency and amplifies the computed results delivery ratio compared with the conventional monolithic system.