Coping with Large Traffic Volumes in Schedule-Driven Traffic Signal Control

Abstract

Recent work in decentralized, schedule-driven traffic control has demonstrated the ability to significantly improve traffic flow efficiency in complex urban road networks. However, in situations where vehicle volumes increase to the point that the physical capacity of a road network reaches or exceeds saturation, it has been observed that the effectiveness of a schedule-driven approach begins to degrade, leading to progressively higher network congestion. In essence, the traffic control problem becomes less of a scheduling problem and more of a queue management problem in this circumstance. In this paper we propose a composite approach to real-time traffic control that uses sensed information on queue lengths to influence scheduling decisions and gracefully shift the signal control strategy to queue management in high volume/high congestion settings. Specifically, queue-length information is used to establish weights for the sensed vehicle clusters that must be scheduled through a given intersection at any point, and hence bias the wait time minimization calculation. To compute these weights, we develop a model in which successive movement phases are viewed as different states of an Ising model, and parameters quantify strength of interactions. To ensure scalability, queue information is only exchanged between direct neighbors and the asynchronous nature of local intersection scheduling is preserved. We demonstrate the potential of the approach through microscopic traffic simulation of a real-world road network, showing a 60% reduction in average wait times over the baseline schedule-driven approach in heavy traffic scenarios. We also report initial field test results, which show the ability to reduce queues during heavy traffic periods.

Smart Infrastructure for Future Urban Mobility

“…Work in recent years has focused on extension and refinement of the basic scheduledriven traffic con trol paradigm. One thread of research (Hu and Smith 2017a;2017b) has examined a problem that arises in circumstances when the volume of traffic on the road network approaches saturation. Consider an extreme situation where an intersection's approaching road seg ments are all filled to near capacity.…”

“…in simulation, the hybrid approach was shown to outperform the initial baseline Surtrac scheduling procedure and the backpressure algorithm alone by fifty percent and fifteen percent, respectively, in scenarios involving heavy traffic vol umes, while providing no performance advantage over baseline Surtrac in scenarios with low and medium traffic volumes. please refer to the articles by Hu and Smith (2017a;2017b) for details.…”

“…In essence, the problem is no longer a sequencing problem but a problem of deciding when to split clusters (or of managing queues). To address this issue, Hu and Smith (2017a, 2017b) have proposed a hybrid online planning procedure that combines schedule‐driven control with the backpressure algorithm, a state‐of‐the‐art approach to maximizing throughput from queuing theory. Using queue length, both locally and from downstream neighbors, as a basis for weighting clusters associated with a given signal phase, a softmax function is specified that increasingly biases intersection scheduling decisions toward managing queues as traffic congestion increases, and extends the schedule‐driven approach to incorporate the basic guarantee of stability provided by queuing theory.…”

Approximate Gradient Descent Convergence Dynamics for Adaptive Control on Heterogeneous Networks

“…In the context of intelligent transport systems, significant research efforts have been dedicated to extensions of the backpressure algorithm in recent years, in particular to address the specifics of traffic light scheduling on road networks (Varaiya 2009). The case of unknown routing rates was also investigated (Gregoire et al 2014), as well as the case of queues with finite capacity (Gregoire et al 2015), see also (Hu and Smith 2017a) and (Hu and Smith 2017b).…”