A Novel, Three-Stage Intelligent Fuzzy Traffic Signal Control System

Abstract

Traffic congestion is a serious issue for cities and urban areas, owing to the increasing usage of vehicles. This phenomenon results in several negative consequences, such as high fuel consumption and loss of time. To address this problem, several countries have implemented optimal traffic signal control systems. However, these systems have some drawbacks, such as the need for expensive hardware and maintenance difficulties. Because the sensors are buried under the road surface, the system often cannot account for the full length of the vehicular queue. This, among several issues, inhibits the full potential of the technology’s effectiveness and sustainability. In addition, there is much uncertainty in traffic conditions, which points to the need for a model that includes vagueness in the control system. This study proposes a novel hierarchical structure for a three-stage fuzzy traffic control system. This new system assesses the vehicle queue, identifies heavy traffic, detects emergency cars, and adjusts the duration of traffic lights according to the traffic flow and waiting times of vehicles using fuzzy inference rules. This controller was evaluated and validated using a micro-simulation model of an isolated intersection. The obtained results revealed the increased adaptability and flexibility of the proposed system owing to its potential to differentiate a random number of traffic directions. It is also able to handle emergency vehicles and can decrease waiting times, stalling fewer cars, if there is a high traffic flow in the conflicting direction(s) and is a robust and scalable system with lower computational costs.