Freeway ramp control using fuzzy set theory for inexact reasoning

This paper presents a fuzzy controller for freeway ramp metering, which uses rules of the form: IF ‘freeway condition’ THEN ‘control action.’ The controller has been designed to consider varied levels of congestion, a downstream control area, changing occupancy levels, upstream flows, and a distributed detector array in its rule base. Through fuzzy implication, the inference of each rule is used to the degree to which the condition is true. Using a dynamic simulation model of conditions at the San Francisco-Oakland Bay Bridge, the action of the fuzzy controller is compared to the existing ‘crisp’ control scheme, and an idealized controller. Tests under a variety of scenarios with different incident locations and capacity reductions show that the fuzzy controller is able to exact 40 to 100% of the possible savings in passenger-hours. In general, the fuzzy algorithm displays smooth and rapid response to incidents, and significantly reduces the minute-miles of congestion.