Structure and effectiveness analysis of an integrated traffic supervisory system

This paper addresses the problem of integrating Advanced Traveller Information Systems (ATIS) and Advanced Traffic Management Systems (ATMS). A framework that allows the integration of existing successful control implementations is reviewed. This framework is utilized to integrate the ATISIATMS control decisions of two operational schemes; ATIS stand-alone system (dynamic route guidance), and ATMS stand-alone control system (responsive signal control), and to form a dual non-cooperative supervisory traffic control system. The two operational schemes are formulated as bi-level optimization problems. Approximate simulation-based optimization algorithms are devised as representations of the existing control logic operating these schemes. These operational schemes are then integrated via as fuzzy-logc supervisory control system. Neural nets are utilized to develop the knowledge base of the fuzzy system and to calibrate the fuzzy set parameters. The neurofuzzy algorithm is tested on a simplified urban network.