Agent-based Intelligent KPIs Optimization of Public Transit Control System

Public transit has a wide variety of resources. There is an infrastructure including stations and routes with multiple trips provided by different modes of transportation (metro, subway, bus). These resources must be well exploited to ensure good quality of service to passengers and especially against perturbations that may occur during the day. The contribution of this work is to model and implement a transit control system that detects perturbations and finds, through optimization, the best regulation action while respecting the constraints of the traffic situation. This system combines various measures of Key Performance Indicators (KPIs) into a single performance value, covering several dimensions depending on the type of service quality to be guaranteed. To take into account the complex and dynamic nature of transportation systems, a multi-agent approach is adopted in the modelling of our system. The validation is based on real traffic data. The results show better performance of our system compared to the current resolution.