Distributed data-driven engine framework facing CPS brain-inspired intelligent transportation

Single data source, isolated data islands and low information utilization in intelligent transportation lead to the poor inversion of the cyber space to the physical space including Incomplete data integration, high interdependency of systems and poor anti-control ability. In this paper the data-driven method is adopted to optimize the W parameter in Webster method to reduce the waiting time of vehicles to realize the traffic congestion. In particular, a multi-source heterogeneous data processing method and a unified modeling of the multi-dimensional and multi-layer networks have been introduced. By data-driven engine, we have implemented both massive storage and fast processing system. We have also build a service system which can rapidly realize data integration and services delivery as well as be directly called by researchers from the database through network requests to reduce the data reprocessing. This paper also produces the data interaction process of the data engine framework in traffic management and control, and proposes a solution for the use of massive city data.