Adaptive Traffic Light Control Research Articles

An Adaptive Traffic Light Control Scheme and its Implementationin WSN-Based ITS

Abstract We investigate the problem of adaptive control of traffic lights using real-time traffic information collected by a wireless sensor network (WSN). Previous studies mainly focused on optimizing the intervals of green lights in a fixed sequence of traffic lights, and ignored some traffic flow’s characteristics and special traffic circumstances. In this paper, an adaptive traffic light control scheme has been proposed, in which the sequence of traffic lights can be adjusted dynamically in accordance with the real time traffic detected, including traffic volume, waiting time and vehicle density. Subsequently, the optimal traffic light length can be determined according to the local traffic and predicted traffic data. Simulation results demonstrate that the proposed scheme can achieve much higher performance, in terms of throughput and average waiting time. We also implement proposed scheme into our WSN-based ITS project, iSensNet, and the result shows that our scheme is effective and practical.

Threshold Tuning Using Stochastic Optimization for Graded Signal Control

Adaptive control of traffic lights is a key component of any intelligent transportation system. Many real-time traffic light control (TLC) algorithms are based on graded thresholds, because precise information about the traffic congestion in the road network is hard to obtain in practice. For example, using thresholds <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{1}$</tex></formula> and <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{2}$</tex> </formula> , we could mark the congestion level on a particular lane as “low,” “medium,” or “high” based on whether the queue length on the lane is below <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{1}$ </tex></formula> , between <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{1}$</tex></formula> and <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{2}$</tex></formula> , or above <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$L_{2}$</tex> </formula> , respectively. However, the TLC algorithms that were proposed in the literature incorporate fixed values for the thresholds, which, in general, are not optimal for all traffic conditions. In this paper, we present an algorithm based on stochastic optimization to tune the thresholds that are associated with a TLC algorithm for optimal performance. We also propose the following three novel TLC algorithms: 1) a full-state Q-learning algorithm with state aggregation, 2) a Q-learning algorithm with function approximation that involves an enhanced feature selection scheme, and 3) a priority-based TLC scheme. All these algorithms are threshold based. Next, we combine the threshold-tuning algorithm with the three aforementioned algorithms. Such a combination results in several interesting consequences. For example, in the case of Q-learning with full-state representation, our threshold-tuning algorithm suggests an optimal way of clustering states to reduce the cardinality of the state space, and in the case of the Q-learning algorithm with function approximation, our (threshold-tuning) algorithm provides a novel feature adaptation scheme to obtain an “optimal” selection of features. Our tuning algorithm is an incremental-update online scheme with proven convergence to the optimal values of thresholds. Moreover, the additional computational effort that is required because of the integration of the tuning scheme in any of the graded-threshold-based TLC algorithms is minimal. Simulation results show a significant gain in performance when our threshold-tuning algorithm is used in conjunction with various TLC algorithms compared to the original TLC algorithms without tuning and with fixed thresholds.

Honeybee Social Foraging for Urban Traffic Control

Green time allocation scheduling for a single road traffic intersection is a dynamic resource allocation problem. In nature, a similar problem is found when animals need to allocate themselves across habitats. For instance, honeybees allocate more animals where there are more resources, when they are foraging for food. Based on these foraging ideas, we introduce a novel adaptive traffic light control strategy. The analogies between the two problems are discussed, and the proposed algorithm is compared with an optimal fixed-time controller. This bioinspired algorithm solves the green time allocation problem without the use of traffic models. This makes the solution feasible for a large-scale network. We also show on simulations, how an equilibrium state is reached under saturation and no saturation conditions.

Passage-detector-based traffic queue estimation in Intelligent Transportation Systems: A computational study of competing algorithms

We present here the results of a comprehensive computational study of competing algorithms for traffic queue estimation. These estimators can be used in conjunction with adaptive feedback traffic light control schemes in Intelligent Transportation Systems. Dynamic queue length estimators proposed by Baras, Levine and Lin are shown to be significantly superior to other methods proposed in the literature.

NEURAL NETWORK MODELS FOR TRAFFIC CONTROL AND CONGESTION PREDICTION

Advance Traffic Management Systems (ATMS) must be able to respond to existing and predicted traffic conditions if they are to address the demands or the 1990's. Artificial intelligence and neural network are promising technologies that provide intelligent, adaptive performance in a variety of application domains. This paper describes two separate neural network systems that have been developed for integration into a ATMS blackboard architecture. The first system is an adaptive traffic signal light controller based upon the Hopfield neural network model, while the second system is a backpropagation model trained to predict urban traffic congestion. Each of these models are presented in detail with results attained utilizing a discrete traffic simulation shown to illustrate their performance.