Dynamic Traffic Management System Research Articles

Reinforcement Learning-Based Adaptive Optimal Control Model for Signal Light in Intelligent Transportation Systems

Day-to-day mobility among the population has increased with economic growth. Smart cities are renovated with advanced technologies to admire modern life in which intelligent transportation becomes highly focused. Because the traffic signal control systems are fixed at a constant time. They split the traffic signal into predetermined intervals and function inefficiently; they result in long wait times, waste fuel and increased carbon emissions. This research study introduces a novel technique for traffic light management to reduce the uncertainties in the system. A dynamic and intelligent traffic light adaptive optimal management system (DITLAOCS) is implemented in this research. It does this by modifying the traffic signal duration in run time and using real-time traffic data as input. Furthermore, the proposed DITLAOCS executes based on three modes: fairness mode (FM), priority mode (PM) and emergent mode (EM). In fairness mode (FM), all vehicles are prioritized equally, while vehicles in different categories receive varying priority levels. Emergency vehicles, on the other hand, receive the highest priority. Furthermore, a fuzzy inference method based on traffic data is shown to choose one mode out of three (FM, PM and EM). This model uses deep reinforcement learning to switch traffic lights in three different phases (red, green and yellow). We evaluated and accurately simulated DITLAOCS on the Shaanxi city map in China using Simulation of Urban MObility (SUMO), an open-source simulator. The simulation results illustrate the efficiency of DITLAOCS when compared to other cutting-edge algorithms on several performance measures.

THE ROLE OF A COMPREHENSIVE APPROACH IN BUILDING AN EFFECTIVE INTELLIGENT TRAFFIC FLOW MANAGEMENT SYSTEM

The continuous growth of population in large cities, the intensive development of the economy, and the rising number of vehicles on the roads lead to the overload of transportation networks, resulting in traffic congestion. These congestions cause significant delays in movement, increase time and fuel consumption, and also have a negative impact on the environment. To address this problem in large cities, it is worthwhile to implement intelligent traffic flow management systems. The variability of methodologies underlying these systems significantly differs depending on their initial purpose. However, the resources of such individual methodologies deplete over time, necessitating the search for and implementation of new ones. The rapid loss of efficiency in such systems is rooted in the absence of a centralized node facilitating communication between systems and managing them. In other words, combining intelligent methodologies into a unified system can be useful in the creation of efficient and dynamic traffic flow management systems with significantly greater re-sources. Such an approach to organizing an intelligent traffic flow management system for the city’s transpor-tation network has been considered in this work. During the research, a brief overview of approaches to improv-ing the efficiency of the city’s transportation network along key directions was conducted. The structure, princi-ples, and ways of forming a robust integrated system for managing the traffic flow were outlined. This system consists of subsystems based on effective optimization and organization methodologies for traffic processes. The effectiveness of tested methodologies that meet the needs of such an integrated system was also discussed and evaluated. Keywords: intelligent transportation systems, traffic congestion, comprehensive approach, adaptive traffic light control, traffic prediction, Internet of things.

A scalable, dynamic, and secure traffic management system for vehicular named data networking applications

Several intelligent transport systems in vehicular networks (VANETs) rely on IP-based models for inter-vehicle communication. However, many approaches for Cooperative Intelligent Transport Systems and distributed systems are not secure and appropriate for VANETs, using specific technologies, centralized network architectures, or limited communication models. In addition, many applications are forced to deal with complex services that the network layer does not provide. This paper proposes NDN-Waze, a comprehensive distributed and lightweight system for vehicular traffic management using Named Data Networking as the main underlying communication protocol. NDN-Waze is a proof-of-concept design that has applications in vehicular route guidance, traffic and mobility monitoring, as well as roadside units as a service in urban areas. We use the NDN-Waze route guidance module to compare the VANET model via Named Data Networking (NDN) and Internet Protocol (IP). Our study employs traditional network metrics to support the hypothesis that the communication architecture has a direct impact on both efficiency and the quality of service operations. The simulation results demonstrate that NDN properties can override traditional IP-based forwarding proposals in VANET.

Dynamic Management of Urban Coastal Traffic and Port Access Control

Urban traffic congestion and vehicle/passenger port recurring delays are major obstacles of coastal urban area sustainability. Most research in coastal urban road management has focused on congestion detection without the effective integration of the dynamic interactions with port queueing systems. For securing coastal city environmental, social and economic efficiency, this paper develops and tests a dynamic urban coastal traffic and port management system. The integrated system controls traffic and port gates’ operations based on ITS/C-ITS methodologies. The system integrates dynamic models for congestion detection, using ANN and a parameterized model, on a coastal urban road network that leads to a city port and identifies optimal solutions for road traffic and port queuing gate control. The system communicates with users via connected vehicles and VMS. The system was tested in a coastal urban road leading to Patras Southern Port, Greece, and at port control gates. Field and simulation data were used to assess system performance and social–environmental impacts. The results reveal that the system’s application offers benefits to the individual driver moving towards the Port to board a ship (gaining at least 7 min and consuming 0.306 L less fuel) as well as to society (39.72% increase in traffic safety) and environment (1,445,132 g CO2 emission reduction).

Traffic Prediction and Signal Controlling Using Mode-search Optimization Based Deep Long Short Term Memory Classifier

Aim: The research aims at developing a traffic prediction and signal controlling model based on deep learning technique in order to provide congestion-free transportation in Intelligent Transport System (ITS). Need for the Research: Recent technical advancements in the ITS, industrialization, and urbanization increase traffic congestion, which leads to high fuel consumption and health issues. This signifies the need for a dynamic traffic management system to handle the traffic congestion issues that negatively affect the transportation service. Methods: For promoting congestion-free transportation in the ITS, this research aims to devise a traffic prediction and control system based on deep learning techniques that effectively controls the traffic during peak hours. The proposed mode-search optimization effectively clusters the vehicles based on the necessity. In addition, the mode-search optimization tunes the optimal hyperparameters of the deep Long Short Term Memory classifier, which minimizes the training loss. Further, the traffic signal control system is developed through the mode-search-based deep LSTM classifier for predicting the path of the vehicles by analyzing the attributes, such as velocity, acceleration, jitter, and priority of the vehicles. Result: The experimental results evaluate the efficacy of the traffic prediction model in terms of quadratic mean of acceleration (QMA), jitter, standard deviation of travel time (SDTT), and throughput, for which the values are found to be 37.43, 0.23, 8.75, and 100 respectively. Achievements: The proposed method attains the performance improvement of 5% to 42% when compared with the conventional methods.

The development of a smarter mode of transportation using ai to reduce travel and waiting times

Smarter mode of transportation (SMT) rely heavily on real-time traffic management. Safety on the roads is only one of many benefits brought forth by advancements in dynamic traffic management systems for congested metropolitan areas. In this study, we present the design and implementation of a Bayesian Belief Networks (BBN) traffic control system that is both flexible and reliable. The use of knowledge-based systems as a framework for making decisions in real-time has gained widespread acceptance. Since traditional dynamic controllers relied on sensors with their own set of drawbacks, we may employ vision sensors (such as cameras) to get around these problems. Computing based on images and videos is very useful for gauging traffic volumes. The present traffic management system at the road junction was found wanting, thus a new system was developed and put into place to alleviate the congestion. Lab VIEW and MATLAB are used to measure how well the suggested framework works. Extensive simulations utilizing the suggested method show that it reduces waiting time and speeds up movement on average compared to controllers employing traditional sensors.

Artificial neural network based load balancing scheme for top of rack switches in optical data centers

Abstract Data centers serve as dedicated facilities for housing computer systems and their related components, including telecommunications and storage systems. They typically have high levels of security and environmental controls to ensure that the equipment housed within them functions optimally. Data center networks (DCNs) often employ load balancing algorithms to handle large volumes of traffic and ensure that all servers and switches are utilized equally, keeping the network running smoothly. However, as load on the server varies, therefore dynamic traffic management systems that can adjust traffic flow in real-time based on the current traffic state is required. This study presents an artificial neural network-based load balancing method. By training a feed-forward artificial neural network (ANN) using a back propagation (BP) learning algorithm, it evenly distributes workload over all of the nodes. Simulation results are also presented to prove the usefulness of the proposed load balancing mechanism. It is found that the load balancing scheme can reduce the packet blocking probability (PBP) by 10 folds and delay by about nearly 11 percent.

Analysis of the Traffic Parameters on a Section in the City of the National Road during Several Years of Operation

The study carried out an analysis of the vehicle traffic parameters on a national road in 2011-2016. The variability and uncertainty of results were evaluated. An analysis of traffic data recorded on the city's entry and exit lanes was carried out. The variations in traffic volume are of interest e.g. in dynamic traffic management systems and navigation services, examining the benefits of flexible work time and places and assessing the environmental effects of traffic congestion. Research has shown that the assumption that lanes perform equally is not always true. Traffic volume models should be periodically calibrated taking into account the shape of the daily profile, which may, for example, allow public transport timetables to be more responsive to the needs of travelers.

IoT based monitoring of air quality and traffic using regression analysis

Dynamic traffic management (DTM) systems are used to reduce the negative externalities of traffic congestion, such as air pollution in urban areas. They require traffic and environmental monitoring infrastructures. In this paper we present a prototype of a low-cost Internet of Things (IoT) system for monitoring traffic flow and the Air Quality Index (AQI). The computation of the traffic flows is based on processing video in the compressed domain. Only using motion vectors as input, traffic flow is computed in real-time over an embedded architecture. An estimation of the AQI is supported by machine learning regression techniques, using different feature data obtained from the IoT device. These automatic learning techniques overcome the need for complex calibration and other limitations of embedded devices in making the needed measurements of the pollutant gases for the computation of the actual AQI. The experimentation with the data obtained from different cities representing different scenarios with a variety of climate and traffic conditions, allows validating the proposed architecture. As regressors, Linear Regression (LR), Gaussian Process Regression (GPR) and Random Forest (RF) are compared using the performance metrics R2, MSE, MAE and MRE resulting in a relevant improvement of the AQI estimations of our proposal.

A framework for dynamic smart traffic light management system

A framework for dynamic smart traffic light management system

Vehicle Classification Based on CCTV Video Recording Using Histogram of Oriented Gradients, Local Binary Patterns, and Hierarchical Multi-SVM

Vehicle classification is a crucial element in a dynamic traffic management system. The system is needed since the number of vehicles gradually increase every year. There are many methods for vehicle classification, one of those is the use of CCTV camera. As it is multifunction and cheaper than other types of camera, the government tend to use the CCTV camera as monitoring equipment of vehicles on the road. Hence, an accurate vehicle classification system from CCTV records is needed for traffic management system as well as other systems. In this study, the method contains four steps: object detection using Gaussian Mixture Model, features extraction using Histogram of Oriented Gradients and Local Binary Patterns, model training and classification using Hierarchical Multi-SVM. The experimental results show that our proposed method works well with the accuracy of 80.28%, precision of 94.27%, recall of 73.79%, and F-measure of 82.76%.

Design and analysis of control strategies for pedestrian flows

Exploiting the full potential of pedestrian infrastructure is becoming critical in many environments which cannot be easily expanded to cope with the increasing pedestrian demand. This is particularly true for train stations as in many dense cities space is limited and expansion is difficult and very costly. In this paper, we investigate how to improve the level-of-service experienced by pedestrians by regulating and controlling their movements with a dynamic traffic management system. Although dynamic traffic management systems have been widely investigated in the last two decades to mitigate vehicular traffic congestion, little attention has been given in the literature to dynamic traffic management systems for pedestrian flows. The objective of this paper is to develop the concept of a dynamic traffic management system for pedestrian flows by building on the experience acquired from vehicular traffic management systems. We first propose a general framework for dynamic traffic management systems which takes into account the specificities of pedestrian traffic. The specificities of pedestrian traffic are discussed and emphasized. Then we illustrate the framework by using a control strategy designed for pedestrian flows that mitigates the issues induced by bidirectional flows. We show the effectiveness of this strategy by simulating a subpart of the train station in Lausanne (Switzerland). The results show a substantial improvement despite the relative simplicity of the method. These results emphasize the under-explored potential of pedestrian control and guidance when integrated into a dynamic pedestrian management system.

Investigating the Relationship between Controller Locations and Dynamic Traffic Control in Generic Transportation Networks

Traffic control policies aim at reducing the negative externalities that ever-growing demand is causing on transportation networks, such as congestion and pollutant emissions. To achieve these goals, strategies coordinating and aligning the effects of several individual traffic controllers have received increasing attention in research and development in the past decades. However, a considerable gap still exists between the desired and experienced performance of advanced dynamic traffic management systems, resulting in failure to completely prevent the increasing peak-hour congestion in main urban areas worldwide. In this work we contribute to assessing whether this gap might be tied to inefficient network design, rather than algorithmic prowess. Based upon our earlier work, we investigate whether a trend can be found between determining locations of controllers in a network following control theoretical insights, and try to confirm our earlier intuitions when dealing with dynamic traffic assignment, featuring accurate propagation and spillback dynamics. To achieve these goals, we extend an existing synthetic network generation tool to allow us to test this hypothesis on real-life-like road networks, and extend our previously developed algorithms for the controller location problems allowing for sufficient generalization. Test results are presented on a simpler deterministic scenario and on 240 randomly generated networks, showcasing that placing controllers following controllability-based principles is advantageous from the perspective of model-based dynamic traffic management applications.

Image Processing and IoT Based Dynamic Traffic Management System

Due to rise in number of vehicles the traffic management has become a major problem. Manual traffic system is not efficient. This paper presents adaptive traffic management system using Internet of Things (IoT) and Image processing. The proposed system has capability to analyze real time data using image processing. Using cameras, different lanes are monitored constantly. The data obtained from different lanes are examined. Detection and counting of number of vehicles in each lane is done by using image processing. The count from each lane is sent to the central processing unit. According to the count of vehicles algorithm calculates waiting time for each lane, then the signal lights will be decided. This system reduces the average waiting time and increases the efficiency of traffic clearance. The system also reduces the pollution due CO2 emission and useful in emergency situations, thus being adaptive traffic management using Internet of Things (IoT).

A Novel Self-Organizing Approach to Automatic Traffic Light Management System for Road Traffic Network

Traffic network is basically a “network of networks” consisting of mainly two types of networks: road network and a travel network. Due to drastic increase in population of vehicles, traffic congestion in metro cities of India is a severe problem. To resolve this use, we have proposed an approach to dynamic and automatic road traffic light management system. The approach is based on arithmetic mean theorem. The input to the control interface of traffic light of proposed approach are six different parameters : velocity of traffic units (v), queue length (l), inter-arrival time between vehicles (t), centrality measures value(c) and predicted value (prdt v) of traffic congestion by historical database and output is level of congestion. On the basis of congestion level, we build inference rules. The proposed approach automatically updates duration of green and red light as per the level of congestion at a particular junction. Proposed approach follows forward reasoning of If–Then rules. A study of this approach is done in this paper on various traffic situations of Delhi, India depending on queue length of vehicles.

An IoT-based dynamic traffic management system in perspective of Bangladesh

An IoT-based dynamic traffic management system in perspective of Bangladesh

An IoT-based dynamic traffic management system in perspective of Bangladesh

This article presents a traffic management system that dynamically micro-manages city traffic by keeping track of the precise number of stationary vehicles at every intersection. It can be implemented quickly at a relatively low cost. Through the use of localised computing, a trilateration system, integration of internet of things (IoT) and development of an algorithm which manages the green signal timing on a per lane basis we create a system which is not only cost effective, but also provides vehicle security and public notification of citywide traffic congestion. It is capable of working in conjunction with both human driven vehicles of today as well as the self-driving vehicles of tomorrow. We simulate overall effectiveness of the system in MATLAB for worst-case scenario and have nonetheless found favourable (5-10% improvement) results.

Dynamic Traffic Control and Management System for Smart Cities

Dynamic Traffic Control and Management System for Smart Cities

Assessment of Possibilities of On-Line Response Dynamic Traffic Management System Development in Medium Size Urban Areas

Assessment of Possibilities of On-Line Response Dynamic Traffic Management System Development in Medium Size Urban Areas

Anticipating emission-sensitive traffic management strategies for dynamic delivery routing

Traffic pollution is an increasing challenge for cities. Emissions such as nitrogen dioxides pose a major health threat to the city’s inhabitants. These emissions often accumulate to critical levels in local areas of the city. To react to these critical emission levels, cities start implementing dynamic traffic management systems (TMS). These systems dynamically redirect traffic flows away from critical areas. These measures impact the travel speeds within the city. This is of particular importance for parcel delivery companies. These companies deliver goods to customers in the city. To avoid long delivery times and higher costs, companies already adapt their routing with respect to changing traffic conditions. Still, a communication with the TMS may allow anticipatory planning to avoid potentially critical areas in the city. In this paper, we show how communication between TMS and delivery companies results in benefits for both parties. To exploit the provided information, we develop a dynamic routing policy anticipating potential future measures of the TMS. We analyze our algorithm in a comprehensive case study for the TMS of the city of Braunschweig, Germany, a city often used as reference for a typical European city layout. We show that for the delivery company, integrating the TMS’ information in their routing algorithms reduces the driving times significantly. For the TMS, providing the information results in less traffic in the polluted areas.