Multi-objective traffic signal optimization using 3D mesoscopic simulation and evolutionary algorithms

Mihăiţă, Adriana-Simona; Dupont, Laurent; Camargo, Mauricio

doi:10.1016/j.simpat.2018.05.005

Cited by 18 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jin et al, introduced an intelligent control system called Fuzzy Intelligent Traffic Signal (FITS) to control the cycle time of traffic signals. They also developed a computational framework to evaluate the FITS system using microscopic traffic simulation [14]. Computer simulation is a widely used tool to represent traffic systems.…”

Section: Related Workmentioning

confidence: 99%

“…This is mainly affected by the distance between a firefly and the brighter firefly ( , * ). Therefore, a solution can be modified according to equation (14), where ( , * ) is the attractiveness factor and it depends on the distance ( , * ) according to equation (15), where ( ) is the light absorption factor. = + , * ( * − ) (…”

Section: ) Solution Improvement Using the Attractiveness Effectmentioning

confidence: 99%

See 1 more Smart Citation

A Mathematical Programming Model and a Firefly-Based Heuristic for Real-Time Traffic Signal Scheduling With Physical Constraints

2021

View full text Add to dashboard Cite

Traffic congestion is one of the challenges that face urban cities' planners. It affects the environment as it increases the emissions of CO2 and affects the logistics systems as it may increase the travel time of different vehicles. Scheduling traffic signals is one of the ways to solve this problem. In the urban traffic signal scheduling problem, it is desired to get the optimum schedule for each considered traffic signal to maximize or minimize a specific objective function(s); these schedules determine the active and inactive traffic phases during each cycle time. In this paper, a mathematical programming model for solving the urban traffic signal scheduling problem is presented, the proposed mathematical model captures the physical constraints of the problem. Furthermore, a firefly-based rolling horizon approach is proposed to solve the problem. Both methods are used to solve a traffic-responsive system, which is considered the future of traffic control systems. The performance of both methods has been simulated using the SUMO traffic simulator to verify the solutions. The performance of the solutions was measured using the average queue length of the roads, the average waiting time, and the average travel time. The proposed methods have been applied to a real case study, and the results were remarkable.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: ) Solution Improvement Using the Attractiveness Effectmentioning

confidence: 99%

A Mathematical Programming Model and a Firefly-Based Heuristic for Real-Time Traffic Signal Scheduling With Physical Constraints

2021

View full text Add to dashboard Cite

show abstract

“…In recent years, a variety of machine learning methods are used for the control of urban traffic signal, such as fuzzy logic [3]- [6], neural networks [7]- [9], evolutionary algorithms [10]- [13] and dynamic programming [14]. Yang et al [5] developed two adaptive two-stage fuzzy controllers for traffic signals under different traffic density at an isolated intersection.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Deep Q-Learning With Q-Value Transfer for Multi-Intersection Signal Control

Song

et al. 2019

IEEE Access

111

View full text Add to dashboard Cite

The problem of adaptive traffic signal control in the multi-intersection system has attracted the attention of researchers. Among the existing methods, reinforcement learning has shown to be effective. However, the complex intersection features, heterogeneous intersection structures, and dynamic coordination for multiple intersections pose challenges for reinforcement learning-based algorithms. This paper proposes a cooperative deep Q-network with Q-value transfer (QT-CDQN) for adaptive multi-intersection signal control. In QT-CDQN, a multi-intersection traffic network in a region is modeled as a multi-agent reinforcement learning system. Each agent searches the optimal strategy to control an intersection by a deep Q-network that takes the discrete state encoding of traffic information as the network inputs. To work cooperatively, the agent considers the influence of the latest actions of its adjacencies in the process of policy learning. Especially, the optimal Q-values of the neighbor agents at the latest time step are transferred to the loss function of the Q-network. Moreover, the strategy of the target network and the mechanism of experience replay are used to improve the stability of the algorithm. The advantages of QT-CDQN lie not only in the effectiveness and scalability for the multi-intersection system but also in the versatility to deal with the heterogeneous intersection structures. The experimental studies under different road structures show that the QT-CDQN is competitive in terms of average queue length, average speed, and average waiting time when compared with the state-of-the-art algorithms. Furthermore, the experiments of recurring congestion and occasional congestion validate the adaptability of the QT-CDQN to dynamic traffic environments.INDEX TERMS Deep reinforcement learning, multi-intersection signal control, Q-learning, Q-value transfer, cooperative.

show abstract

“…Jauhar and Pant [19] and Lee [20] note that despite the invention of numerous modern soft computing techniques, GAs are still widely used by scientists in optimization problems. Besides industrial applications, many organizational challenges might be addressed using GAs, e.g., traffic flow control [21]. These real-life problems require a different implementation and tuning philosophy of GAs compared to the benchmark ones due to the substantial computational investment in assessing the population fitness [18].…”

Section: Introductionmentioning

confidence: 99%

Continuous Genetic Algorithms in the Optimization of Logistic Networks: Applicability Assessment and Tuning

Ignaciuk

Wieczorek

2020

Applied Sciences

View full text Add to dashboard Cite

Globalization opens up new perspectives for handling goods distribution in logistic networks. However, establishing an efficient inventory policy is challenging by virtue of the analytical and computational complexity. In this study, the goods distribution process that was governed by the order-up-to policy, implemented in either a distributed or centralized way, was investigated in the logistic systems with complex interconnection topologies. Uncertain demand may be imposed at any node, not just at conveniently chosen contact points, with a lost-sales assumption that introduces a non-linearity into the node dynamics. In order to adjust the policy parameters, the continuous genetic algorithm (CGA) was applied, with the fitness function incorporating both the operational costs and customer satisfaction level. This study investigated how to select the parameters of the popular inventory management policy when operating in the non-trivial networked structures. Moreover, precise guidelines for the CGA tuning in the considered class of problems were provided and evaluated in extensive numerical experiments.

show abstract

Multi-objective traffic signal optimization using 3D mesoscopic simulation and evolutionary algorithms

Cited by 18 publications

References 32 publications

A Mathematical Programming Model and a Firefly-Based Heuristic for Real-Time Traffic Signal Scheduling With Physical Constraints

A Mathematical Programming Model and a Firefly-Based Heuristic for Real-Time Traffic Signal Scheduling With Physical Constraints

Cooperative Deep Q-Learning With Q-Value Transfer for Multi-Intersection Signal Control

Continuous Genetic Algorithms in the Optimization of Logistic Networks: Applicability Assessment and Tuning

Contact Info

Product

Resources

About