An emission and weight of vehicles-based road traffic congestion pricing system and control with consideration of investment worthiness

This work presents a knowledge-based approach to traffic congestion pricing system and control. The road traffic congestion has attracted different intelligent contributions which have addressed many real-time traffic scenarios at a toll point unlike the flat toll system that renders parallel toll for every traffic condition. However, existing works on dynamic traffic congestion pricing systems focus entirely on the traffic parameters without taking cognizance of the impacts of the weight of vehicles on the road. More so, despite the numerous health hazards associated with air pollution from vehicle exhaust during traffic peak hour, effects of emission have not been conceived as pivotal input to be circumvented in road toll design. Therefore, a fuzzy logic-based approach to dynamic traffic congestion pricing problems in a 1*2 traffic scenario comprising of a fast lane and a slow lane, is presented. The inputs to the fuzzy inference system are the weights of vehicles, the rate of carbon dioxide emission, and the traffic density on the toll lane; while the output is the congestion price. Simulations results indicate the qualitative robustness of this approach in handling the inherent nonlinear nature of road pricing problems. Investors and traffic management systems can rely on the simplicity, reduced computation cost, reduced health hazards and the justified investment worthiness on road and toll facilities.