A stochastic optimization framework for road traffic controls based on evolutionary algorithms and traffic simulation

Abstract

A stochastic optimization framework for road traffic controls based on evolutionary algorithms and traffic simulation. Advances in Engineering SoftwareAccess to the published version may require subscription. N.B. When citing this work, cite the original published paper. AbstractTraffic flow is considered as a stochastic process in road traffic modeling. Computer simulation is a widely used tool to represent traffic system in engineering applications. The increased traffic congestion in urban areas and their impacts require more efficient controls and management. While the effectiveness of control schemes highly depends on accurate traffic model and appropriate control settings, optimization techniques play a central role for determining the control parameters in traffic planning and management applications. However, there is still a lack of research effort on the scientific computing framework for optimizing traffic control and operations and facilitating real planning and management applications. To this end, the present study proposes a model-based optimization framework to integrate essential components for solving road traffic control problems in general. In particular, the framework is based on traffic simulation models, while the solution needs extensive computation during the engineering optimization process. In this study, an advanced genetic algorithm, extended by an external archive for storing globally elite genes, governs the computing framework, and it shows superior performance than the ordinary genetic algorithm because of the reduced number of fitness function evaluations in engineering applications. To evaluate the optimization algorithm and validate the whole software framework, this paper illustrates a detailed application for optimization of traffic light controls. The study optimizes a simple road network of two intersections in Stockholm to demonstrate the model-based optimization processes as well as to evaluate the presented algorithm and software performance.

A non-parametric Bayesian framework for traffic-state estimation at signalized intersections

“…While many studies in literature were devoted to link-based TSE with regards to intersections controlled by fixedtime traffic signal, group-based and lane-based control approaches provided benefits due to more flexible phase structures and sequences for both conventional traffic signal systems [e.g., 9,15] and adaptive signal systems [8]. Lanebased traffic states are one of the most important inputs for enabling the functionalities of group-based and lane-based controllers.…”

“…In particular, if a loop detector is occupied by vehicle, the connected signal controller would receive a signal of a digital pulse, being 1, and the digital signal returned to 0 as soon as the vehicle has passed through the detector. The timing logic applied is a gap-seeking algorithm for green time extension, as described in Jin et al [9].…”

“…According to the applied intersection layout, a traffic model was built in an open-source microscopic simulator, SUMO 0.19.0 [11]. A self-developed software program for the signal controller was implemented to connect the SUMO simulator so that the traffic lights in the simulation were governed by the stage-based vehicle-actuated control [9]. To generate the state, control and measurement data, SUMO simultaneously recorded the detection information and the number of vehicles on each lane via a provided application programming interface, callded TraCI .…”

Hierarchical multi-agent control of traffic lights based on collective learning

“…The phase sequence of each intersection agent is predetermined in these studies. Group-based phasing approaches have proved their utilities by dynamically generating phase structures and sequences with respect to traffic detected at intersection (e.g., Wong and Wong, 2003;Jin et al, 2017b). A previous study by the same authors proposed an RL-based adaptive TLC system suitable for group-based phasing strategies (Jin and Ma, 2017).…”

“…The optimal signal control parameters are generated using a genetic algorithm based optimization framework. The descriptions of VA timing and the optimization framework can be found in Jin et al (2017b). In addition to comparing with the optimized TMBVA system, the analysis examines the performance of the proposed system without using FA.…”