An Integrated Knowledge-base/simulation System for Real- Time Incident Management

This paper presents a real-time incident management system that integrates the knowledge base with a microscopic traffic simulation model. The system consists of five modules: input module, knowledge-based module, prediction module, simulation module, and output module. The knowledge base is used to inventory the operational experience and traffic impact information associated with all recorded incidents. The prediction module is developed to predict the information of maximum queue length and incident duration predictions. The simulation module, developed with design plans for construction, contains traffic volumes and all detailed geometric features for both mainline segments and interchanges. The proposed system will enable traffic control operators during the incident management period to perform two critical functions: (1) having an immediate estimate of the traffic impacts such as the queue length, average speed due to the detected incident; and (2) performing a subsequent detailed real-time analysis of network traffic conditions under various candidate incident management and/or control strategies with the simulation module. The simulation results also offer the information between departure time and estimated travel time during the period of incident management. Furthermore, the system can also connects to the on-line detectors so that the real-time information can be used in the prediction and update of the simulation module. To minimize both the learning and executing efforts of our target users, the integrated simulator is given a GIS-type of map features, allowing the operators to perform the input and output tasks through a user-friendly graphical interface.