Study On Adaptive Type-2 Fuzzy Traffic Signal Control

Traffic jam has become more and more serious due to the rapid growth of vehicle ownership in the cities, particularly in the rush hours. As a result, journey time, energy consumption, traffic accident, noise and environmental pollution seriously deteriorate. Obviously, the optimal regulation of traffic signal control has great signification for easing the traffic pressure and improving the efficiency of transportation. Transportation system is a large complex nonlinear dynamic system. Traditional controllers are usually restricted due to the influence cause by traffic environment, weather, driver selection, accident and so on. Typical type-1 fuzzy traffic signal control system improves the traffic efficiency to some extent, but the ability to deal with complicated traffic system is reduced due to the weakness of handling fuzzy uncertainty. However, type-2 fuzzy system is a kind of nonlinear control system based on type-2 fuzzy set theory, and its own characteristic of three-dimensional fuzzy set provides a new degree of freedom to describe the uncertain behavior of system, which make it more suitable for research of traffic signal control system.Based on the analysis of the problems of typical fuzzy traffic signal control, this thesis concentrates on single intersection, arterial traffic and area traffic network, employs type-2 fuzzy control system, and studies two key problems:traffic model and traffic signal control strategy. The main research results include the following aspects:(1) Single intersection type-2 fuzzy traffic signal control. In order to achieve the effective control of single intersection, a four-phase intersection is studied. The corresponding queue length model and vehicle delay model are established. Aiming at the dynamic uncertainty problem in single intersection, a single intersection type-2 fuzzy controller is designed. The green time of each phase is dynamically decided according to the real-time traffic information in order to achieve the smallest average vehicle delay, so as to enhance the traffic efficiency in the intersection. The excellent performance of the designed controller is confirmed through experiments under different conditions. Finally, in view of the difficulty of parameter settings in type-2 fuzzy controller, DNA evolutionary algorithm is applied to online optimize and adjust the parameters of membership function. The results indicate that the optimized type-2 fuzzy traffic control system has better effect.(2) Arterial type-2 fuzzy traffic signal coordination control. In order to alleviate its traffic pressure effectively, arterial traffic flow model and evaluation index model are set up firstly. Each intersection adopts three-phase control and multi-lane pattern. Moreover, the right-turning traffic flow is also taken into account. Aiming at the coordination and dynamic uncertainty problem in arterial traffic, a kind of arterial traffic type-2 fuzzy coordination control method is put forwarded based on the established arterial traffic model, which contains two layer type-2 fuzzy controller, the basic control layer and the coordination layer. The former allocates green time according to the traffic situation of each intersection, while the latter adjusts each intersection’s green time on the basis of the vehicles between this intersection and the downstream intersections for the purpose of maximum green wave band control. In order to further improve the effectiveness of the controller, besides optimizing the parameters of membership function, the rules of the two controllers also need to be adjusted. In view of more parameters are optimized caused by higher complexity in arterial traffic, gravitational search algorithm (GSA) is adopted to the optimization of the two controllers’parameters alternately. The simulation test takes arterial traffic contained five intersections as example. The experimental results show the effectiveness of the proposed method from several aspects.(3) Area type-2 fuzzy traffic signal control. An area traffic network is studied. The corresponding traffic flow model and evaluation index model are established, and a multi-agent area traffic type-2 fuzzy signal control method is provided. Aiming at the topology of traffic network, multi-agent system is utilized to implement intersection’s phase sequence transformation and collaborative control due to its characteristics of distributed processing and coordination technology. The intersection level type-2 fuzzy controller and the coordination level controller are included. Based on the created area traffic model, the former decides phase sequence change and each phase’s green time according to dynamic real-time traffic information, while the latter adjusts the adjacent intersections’signal control strategy when traffic congestion will be happened at an intersection, so as to ease traffic congestion. Because the scope of optimization is further expanded, differential evolution (DE) algorithm which has lower algorithm complexity is used to optimize the rule base and membership functions parameters of Type-2 fuzzy controller. Moreover, the rule base and membership functions are optimized by turns in order to reduce the computational complexity. The simulation test takes an eleven-intersection traffic network as example. The corresponding results demonstrate its superiority of the proposed method.