Developing an eScience Transportation Platform for Freeway Performance Analysis.

摘要

While the exponential growth of data brings us tremendous opportunities of research, it also creates key challenges that will need to be tackled. As of 2012, we create approximately 2.5 exabytes of information each day, which equals the total amount of data stored on magnetic tape in 2001. The way people create, store, maintain, access, share, and utilize the data leads to a brand new outlook called big data. It motivates and inspires scientists and researchers to develop new infrastructure for better exploiting and exploring huge amount of multidisciplinary data. In 1999, Jon Taylor, the Director General of Research Councils in the UK, first introduced the term "eScience", which defines the novel generation of infrastructure that enables researchers from multidisciplinary areas collaborate with each other to achieve better, faster, and diverse research capabilities.;Inspired by the concept of eScience, the on-line transportation platform Digital Roadway Interactive Visualization and Evaluation Network (DRIVENet) is developed aimed at transportation data sharing, integration, visualization, and analysis. The major research goals for the DRIVENet system can be summarized in threefold. First, it provides the repository service to facilitate data sharing and integration. Second, one of the primary purposes DRIVENet serve is to visualize the large sets of transportation data, helping users to perceive and understand the data. Third, the interactive and computational functions built in the DRIVENet system allow users to perform a variety of statistical analysis on multiple data sources, assisting users to draw meaningful inferences and make informed decisions. This research thus attempts to propose an innovative system architecture to address the aforementioned challenges, and develop an eScience approach to effectively utilize the existing data resources for transportation applications. Specially, a new approach that automates real-time freeway performance measurement is developed and implemented on DRIVENet, which further demonstrates the capability of DRIVENet in solving transportation problems. The new approach also provides quantitative evaluation of network-wide freeway performance to facilitate decision making in transportation operations and management.