Optimization of traffic signals on urban arteries through a platoon-based simulation model (original) (raw)
Related papers
Synchronization of traffic signals through a heuristic-modified genetic algorithm with GLTM
Proceedings of XIII Meeting of the Euro Working …, 2009
Urban signal timing is a non-convex NLP problem. Finding an optimal solution on not very small and simple networks may take long time, wherever possible. The present paper focuses on signal synchronization, thus creating fast-flow corridors on one or more network road arterials. To do this, a genetic-like algorithm is applied, in which new solutions generation follows heuristic conceptions. This can be carried out thanks to the specific formulation adopted, suitable for synchronization problems. The objective function is evaluated by the General Link Transmission Model, a very fast macroscopic dynamic simulator referring to the kinematic waves theory. Through this, queues dynamic evolution, spillback phenomenon and vehicles travel times are explicitly taken into account.
Multiple Traffic Signal Control Using A Genetic Algorithm
Artificial Neural Nets and Genetic Algorithms, 1999
Optimising traffic signal timings for a multiple-junction road network is a difficult but important problem. The essential difficulty of this problem is that the traffic signals need to coordinate their behaviours to achieve the common goal of optimising overall network delay. This paper discusses a novel approach towards the generation of optimal signalling strategies, based on the use of a genetic algorithm (GA). This GA optimises the set of signal timings for all junctions in network. The different efficient red and green times for all the signals are determined by genetic algorithm as well as the offset time for each junction. Previous attempts to do this rely on a fixed cycle time, whereas the algorithm described here attempts to optimise cycle time for each junction as well as proportion of green times. The fitness function is a measure of the overall delay of the network. The resulting optimised signalling strategies were compared against a well-known civil engineering technique, and conclusions drawn.
Research on Timing Optimization of Regional Traffic Signals based on Improved Genetic Algorithm
Proceedings of the 2018 3rd International Workshop on Materials Engineering and Computer Sciences (IWMECS 2018), 2018
Aiming at the problem that the signal timing schemes of the current intersections are isolated from each other and the optimization of the regional traffic control can not be effectively achieved, an optimal timing model for multi-intersection signal control schemes is proposed. The paper analyzes the characteristics of traffic flow at multiple intersections and simulates the controlled traffic flow between multiple intersections by using the cellular transmission model as a basic model. According to the characteristics of controlled parameters that affect traffic volume in multi-intersection road network and the analysis of traffic signal control accuracy and real-time requirements, an improved genetic algorithm is proposed. Combined with DISCO intersection numerical simulation software, the model in this paper is numerically simulated. The numerical simulation results show that the model can adapt to the change of traffic flow between intersections through time adjustment, and the average delay time of road vehicles is smaller than that of other schemes, which is an optimization model that can be adopted by real time controllers.
Traffic signal timing optimisation based on genetic algorithm approach, including drivers’ routing
Transportation Research Part B: Methodological, 2004
The genetic algorithm approach to solve traffic signal control and traffic assignment problem is used to tackle the optimisation of signal timings with stochastic user equilibrium link flows. Signal timing is defined by the common network cycle time, the green time for each signal stage, and the offsets between the junctions. The system performance index is defined as the sum of a weighted linear combination of delay and number of stops per unit time for all traffic streams, which is evaluated by the traffic model of TRANSYT [User guide to TRANSYT, version 8, TRRL Report LR888, Transport and Road Research Laboratory, Crowthorne, 1980]. Stochastic user equilibrium assignment is formulated as an equivalent minimisation problem and solved by way of the Path Flow Estimator (PFE). The objective function adopted is the network performance index (PI) and its use for the Genetic Algorithm (GA) is the inversion of the network PI, called the fitness function. By integrating the genetic algorithms, traffic assignment and traffic control, the GATRANSPFE (Genetic Algorithm, TRANSYT and the PFE), solves the equilibrium network design problem. The performance of the GATRANSPFE is illustrated and compared with mutually consistent (MC) solution using numerical example. The computation results show that the GA approach is efficient and much simpler than previous heuristic algorithm. Furthermore, results from the test road network have shown that the values of the performance index were significantly improved relative to the MC.
Traffic signal timing optimisation based on genetic algorithm approach, including driversÕ routing
The genetic algorithm approach to solve traffic signal control and traffic assignment problem is used to tackle the optimisation of signal timings with stochastic user equilibrium link flows. Signal timing is defined by the common network cycle time, the green time for each signal stage, and the offsets between the junctions. The system performance index is defined as the sum of a weighted linear combination of delay and number of stops per unit time for all traffic streams, which is evaluated by the traffic model of TRANSYT [User guide to TRANSYT, version 8, TRRL Report LR888, Transport and Road Research Laboratory, Crowthorne, 1980]. Stochastic user equilibrium assignment is formulated as an equivalent minimisation problem and solved by way of the Path Flow Estimator (PFE). The objective function adopted is the network performance index (PI) and its use for the Genetic Algorithm (GA) is the inversion of the network PI, called the fitness function. By integrating the genetic algorithms, traffic assignment and traffic control, the GATRANSPFE (Genetic Algorithm, TRANSYT and the PFE), solves the equilibrium network design problem. The performance of the GATRANSPFE is illustrated and compared with mutually consistent (MC) solution using numerical example. The computation results show that the GA approach is efficient and much simpler than previous heuristic algorithm. Furthermore, results from the test road network have shown that the values of the performance index were significantly improved relative to the MC.
A Genetic Algorithm Approach for Optimizing Traffic Control Signals Considering Routing
Computer-aided Civil and Infrastructure Engineering, 2007
It is well-known that coordinated , area-wide traffic signal control provides great potential for improvements in delays, safety and environmental measures. However, an aspect of this problem that is commonly neglected in practice is the potentially confounding effect of drivers rerouting in response to changes in travel times on competing routes, brought about by the changes to the signal timings. This paper considers the problem of optimising signal green and cycle timings over an urban network, in such a way that the optimisation anticipates the impact on traffic routing patterns. This is achieved by including a network equilibrium model as a constraint to the optimisation. A Genetic Algorithm (GA) is devised for solving the resulting problem, using total travel time across the network as an illustrative fitness function, and with a widely-used traffic simulation-assignment model providing the equilibrium flows. The procedure is applied to a case-study of the city of Chester in the UK, and the performance of the algorithms is analysed with respect to the parameters of the GA method. The results show a better performance of the signal-timing as optimised by the GA method as compared to the other method which does not consider rerouting. This improvement is found to be more significant with a more congested network whereas under a relatively mild congestion situation the improvement is not very clear.
Optimization Using Simulation of Traffic Light Signal Timings
Traffic congestion has become a great challenge and a large burden on both the governments and the citizens in vastly populated cities. The main problem, originally initiated by several factors, continues to threaten the stability of modern cities and the livelihood of its habitants. Hence, improving the control strategies that govern the traffic operations is a powerful solution that can solve the congestion problem. These improvements can be achieved by enhancing the traffic control performance through adjusting the traffic signal timings. This paper focuses on finding various solutions for the addressed problem through the optimization using simulation of traffic signal timings under oversaturated conditions. The system under study is an actual road network in Alexandria, Egypt; where, numerous data have been collected in different time intervals. A series of computer simulation models to represent the actual system as well as proposed solutions have been developed using the ExtendSim simulation environment. Furthermore, an evolutionary optimizer is utilized to attain a set of optimum/near-optimum signal timings to minimize the total time in system of the vehicles, resulting in an improved performance of the road network. Analysis of experimentation results shows that the adopted methodology optimizes the vehicular flow in a multiple-junction urban traffic network.
Development of a Stochastic Genetic Algorithm for Traffic Signal Timings Optimization
Traffic Management of over-saturated urban networks is a great challenge in large metropolitan areas. Over-saturation is a severe traffic condition when excessive unbalance between the vehicular demand and the road network's capacity takes place, generating serious inflation of queuing lengths, waiting times, spillbacks and risk of accidents. Other environmental, psychological and economic aspects could also be related to the problem. However, adequate traffic management can successfully handle the demand in both space and time, and overcome the arising congestion dilemma. A mathematical model representing the traffic control stochastic environment has been developed. The optimum/nearoptimum traffic signal timing values have been determined through the application of a genetic algorithm that feeds these values into a developed simulation model to obtain the corresponding queuing parameters. The generated signal timings significantly enhance the traffic performance and alleviate the choke points over a multiple-junction urban network. The developed approach has been applied on a network consisting of two consecutive junctions in Alexandria, Egypt using actual field data. Although the solution has not been implemented in reality; nevertheless, optimization results are very promising and show that the proposed model can drastically improve the queuing parameters of the vehicular flow.
Intelligent Traffic Light Management: Arterial Simulation & Optimization
2008
Abstract The signal controllers of heavy-traffic arteries are subject to optimization to best accomodate the movement of the large traffic volumes. The DOGS system for arterial optimization works by adjusting the common cycle time according to detected traffic conditions and was tested in the vissim microsimulator for a section of the Danish ringroad 3.
The paper presents results of our research on application of genetic algorithms to the problem of finding good configurations of traffic signals offsets in a road network (Traffic Signal Setting problem). We tested algorithms on a large road network-realistic map of Warsaw acquired from the OpenStreetMap project. The main research tool was the software Traffic Simulation Framework developed by the first author. To speed up experiments we employed a high-performance computing cluster at the University of Rzeszów-sessions of experiments were supervised by the second author.