Distributed processing for automotive data stream management system on mixed single- and multi-core processors

Modern automotive systems incorporate a range of data from on-board sensors and outside the vehicle. This results in complex data processing and rising software development costs. To address these issues, we investigated the adaptation of a general-purpose data stream management system (DSMS) use in automotive applications. Existing DSMSs cannot be applied directly in automotive systems, since they are not designed for stream processing in a distributed environment with an architecture of mixed single- and multi-core processors. This makes it difficult to optimize the placement of communicating entities on multiple processors when the parallel processing of massive amounts of streamed data is required. In this study, we investigated distributed and parallel stream processing on mixed single- and multi-core processors for an automotive DSMS. To extend the automotive DSMS in a distributed environment and facilitate the testing of the real-time constraints of stream processing on the various placements of entities, we designed a framework to automatically generate execution files on multiple processors. Our experimental results validated an architecture of mixed single- and multi-core processors and demonstrated the effectiveness of the framework.