Intelligent traffic rerouting with dynamic vehicle selection for congestion mitigation

Traffic congestion is an inevitable issue faced by urban cities due to the high population density and transportation requirements. Although public transport and infrastructure improvements can alleviate congestion, spatial limitations restrict these solutions. Therefore, an additional system is necessary to mitigate traffic congestion on existing, overburdened networks. Currently, researchers are primarily investigating traffic rerouting systems integrated with artificial intelligence to distribute vehicles and optimize road usage with minimal costs. Likewise, this paper proposed a dynamic rerouting system integrated with simple artificial intelligence that consists of near-future traffic flow prediction while also introducing a Key Performance Index (KPI) to accurately measure congestion levels and effectively select vehicles for rerouting with minimum cost. The proposed system first aggregates various traffic data to serve as the input of a Support Vector Machine (SVM) traffic flow prediction model, which estimates near-future traffic conditions. These conditions are then measured using a self-proposed KPI to label the congestion level of each road. A vehicle filtration process then selects the vehicles for rerouting based on the congestion level and the travel cost between the origin and destination. Finally, an alternative route is computed via a k Shortest Path (kSP) model by minimizing the travel time. Simulation results indicate that the proposed vehicle rerouting system is capable of reducing the total travel time of a given traffic network by an astonishing 33.1 %. • Proposed a near real-time rerouting system with the aim of reducing the total travel time of a traffic network. • Introduced an innovative Key Performance Index system that accurately assesses the congestion level for the rerouting system. • Minimizing the cost of rerouting via a vehicle filtration process to minimize the number of rerouted vehicles. • Applied Support Vector Machine to perform near-future traffic flow prediction to achieve proactive rerouting. • Investigated the effects of rerouting intervals, traffic levels and Key Performance Index weightages on the proposed system.