Simulation Of Urban Mobility Research Articles

Performance Evaluation of DSRC-Zigbee Heterogeneous Network for Intelligent Transportation System

Transportation is one of the primary needs of human beings that cannot be avoided, with the increasing vehicle can lead to a congested road situation which can lead to less safe road safety. An Intelligent Transportation System (ITS) can be used to increase road safety. This system uses a Dedicated Short-Range Communication (DSRC) protocol for network access due to its low latency transmission time. Unfortunately, there is research shows that DSRC has a performance issue in a dense area or increased network load. This problem is mostly solved with a heterogeneous network DSRC-LTE but utilizes mobile phone networks that dynamically change can lead to inconsistent and unpredictable network performance. There is some research about ZigBee for ITS shows that it is decent enough for non-critical applications. Thus, the authors try to utilize Zigbee to create the DSRC-Zigbee heterogeneous network so that the network is independent for the ITS application. The proposed heterogeneous network is a fixed model due to its simple architecture. OMNeT++ and Simulation of Urban Mobility (SUMO) are used to evaluate the performance of the network in an urban area with various scenarios. The simulation result shows that the proposed heterogeneous network is capable to improve the messages dissemination rate by 15.78% and 1.22% in a certain scenario compared to the homogeneous network DSRC only.

Ant colony optimization-based traffic routing with intersection negotiation for connected vehicles

This study presents a decentralized traffic management system that integrates dynamic traffic routing and signal-free intersection traffic control for connected vehicles (CV). In particular, we apply the ant colony optimization algorithm and the proposed concept of colored CV to solve the dynamic traffic routing problem with multi-source multi-destination traffic flows. Each CV, modeled as an ant, deposits pheromones on its path, while road sensors aggregate the pheromone information representing traffic conditions and transfer the information to the incoming CV to perform routing. Using the colored CV concept, the CV with the same destination deposit the corresponding pheromone called colored pheromone, and only these CV can interact with that pheromone. Thus, we can distinguish multi-source multi-destination traffic flows in the routing process. For implementing signal-free intersection traffic control, we propose a decentralized intersection negotiation protocol that allows the CV to pass the intersections by exchanging their trajectory information, thereby significantly reducing the time required by CV to pass the intersections. We performed extensive simulations to evaluate our system using Simulation of Urban Mobility, a microscopic traffic simulator. The results show improvement of our proposed system over the conventional traffic management systems in terms of the mean trip time and the number of running vehicles.

Traffic Congestion Prediction using Deep Reinforcement Learning in Vehicular Ad-Hoc Networks (VANETS)

In recent years, a new wireless network called vehicular ad-hoc network (VANET), has become a popular research topic. VANET allows communication among vehicles and with roadside units by providing information to each other, such as vehicle velocity, location and direction. In general, when many vehicles likely to use the common route to proceed to the same destination, it can lead to a congested route that should be avoided. It may be better if vehicles are able to predict accurately the traffic congestion and then avoid it. Therefore, in this work, the deep reinforcement learning in VANET to enhance the ability to predict traffic congestion on the roads is proposed. Furthermore, different types of neural networks namely Convolutional Neural Network (CNN), Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) are investigated and compared in this deep reinforcement learning model to discover the most effective one. Our proposed method is tested by simulation. The traffic scenarios are created using traffic simulator called Simulation of Urban Mobility (SUMO) before integrating with deep reinforcement learning model. The simulation procedures, as well as the programming used, are described in detail. The performance of our proposed method is evaluated using two metrics; the average travelling time delay and average waiting time delay of vehicles. According to the simulation results, the average travelling time delay and average waiting time delay are gradually improved over the multiple runs, since our proposed method receives feedback from the environment. In addition, the results without and with three different deep learning algorithms, i.e., CNN, MLP and LSTM are compared. It is obvious that the deep reinforcement learning model works effectively when traffic density is neither too high nor too low. In addition, it can be concluded that the effective algorithms for traffic congestion prediction models in descending order are MLP, CNN, and LSTM, respectively.

SAV Operations on a Bus Line Corridor: Travel Demand, Service Frequency, and Vehicle Size

Before shared automated vehicles (SAVs) can be widely adopted, they are anticipated to be implemented commercially in confined regions or fixed routes where the benefits of automation can be realized. SAVs have the potential to operate in a traditional transit corridor, replacing conventional transit vehicles, and have frequent interactions with riders and other vehicles sharing the same right of way. This paper microsimulates SAVs’ operation on a 6.5-mile corridor to understand how vehicle size and attributes of such SAV-based transit affect traffic, transit riders, and system costs. The SUMO (Simulation of Urban MObility) platform is employed to model microscopic interactions among SAVs, transit passengers, and other traffic. Results show that the use of smaller, but more frequent, SAVs leads to reduced passenger waiting times but increased vehicle travel times. More frequent services of smaller SAVs do not, in general, significantly affect general traffic due to shorter dwell times. Overall, using smaller SAVs instead of the large 40-seat SAVs can reduce system costs by up to 4% while also reducing passenger waiting times, under various demand levels and passenger loading factors. However, the use of 5-seat SAVs does not always have the lowest system costs.

A Study on Autonomous Intersection Management: Planning-Based Strategy Improved by Convolutional Neural Network

The development and application of autonomous vehicles bring great changes to urban traffic management and control. As one of the bottlenecks to improve transportation efficiency, intersection management plays an important role in the urban city. When the dynamic control method in different cases is determined, the key of autonomous intersection management problem is to search the passing orders for approaching connected and automated vehicles (CAVs). The paper proposed a framework based on convolutional neural network to predict different passing orders’ total time consumption. Thus, the best passing order with the lowest time consume can be chosen as the optimal solution. Then continuous-time optimal control can be carried out on CAVs. Meanwhile, sequential model-based algorithm configuration technique is used for neural network training. Simulation results exported from Simulation of Urban Mobility (SUMO) indicate that the proposed method outperforms actuated signal control and first come first serve strategy. The average delay of the proposed method can decrease by 42.40%–73.05% compared with actuated signal control and 2.95%–55.29% compared to first come first serve strategy. Moreover, it can increase average speed by more than 20% compared with the other two methods. The proposed method can significantly reduce the computation time comparing with the original planning-based strategy. At last, the framework can be applied to other regression tasks like vehicle emissions, then different optimization targets can be estimated to get better solutions faster.

Cluster Routing-Based Data Packet Backhaul Prediction Method in Vehicular Named Data Networking

Vehicular named data networking (V-NDN) is a network architecture that combines named data networking (NDN) and vehicular ad hoc networks (VANETs). Due to the high-speed mobility of the on-board unit (OBU) in V-NDNs, topological changes may cause the problem of reverse path breaking for data packets, thus impacting the communication quality of service (QoS) among vehicles. To address this issue, a data packet backhaul prediction method (DBPM) based on cluster routing in the V-NDN is proposed in this paper. The DBPM uses GPS and a convex programming location algorithm (CPLA) at roadside units (RSUs) to obtain the positioning information of vehicle in the clusters, and uses two positioning data items to predict the location of the vehicle's future access point (AP) for the cluster by using the Kalman filtering model. Then, the DBPM forwards the returned data packets to the vehicle by the cluster. Simulation experiments are performed by using the simulators Simulation of Urban Mobility (SUMO) and VanetMobiSim. Results show that the proposed DBPM can effectively reduce the average delay and packet loss ratio in the vehicle-to-infrastructure (V2I) communication in urban scenes, thus enhancing the robustness of data transmission and effectively supporting the data communication's QoS of V-NDN.

An efficient authentication scheme with strong privacy preservation for fog-assisted vehicular ad hoc networks based on blockchain and neuro-fuzzy

Privacy, security and efficiency are important performance issues in vehicular ad hoc network (VANET), which researchers have tried to address in recent years. This research article proposes a lightweight and privacy-preserving certificateless authentication scheme in fog-assisted VANET using blockchain technology and neuro-fuzzy machine learning technique. A new authentication scheme is designed using certificateless signature based on elliptic curve cryptography (ECC) and hash function operation. The scheme utilizes two blockchains to achieve decentralized and transparent transactions and revocation process. In order to prevent denial-of-service attack, in which a roadside unit (RSU) is flooded with a massive amount of fake authentication requests so as to prevent legitimate nodes from being authenticated, a neuro-fuzzy algorithm is implemented to proactively detect and discard any anomalous requests prior to an authentication process. Moreover, the scheme is demonstrated to be semantically secure in the random oracle model (ROM) based on the intractability of the discrete logarithm problem (DLP). A panoptic analysis shows that the scheme possesses outstanding attributes required for a secure vehicular communication system. The experimental simulation is conducted using simulation of urban mobility (SUMO) and the broadly-accepted network simulator NS-3. The results indicate that the proposed scheme has a high efficiency in terms of transmission delay and message delivery rate. The comparative analysis with the state-of-the-art schemes reveals that the proposed scheme has an improvement of 50%–90.5% in computation cost and 38.46%–69.6% in communication overhead. The simulation result of the neuro-fuzzy gives an accuracy of 91.5% and further analysis shows that it significantly reduces the computation burden on the RSU proportionately with increase in the number of malicious messages.

VC 3: A Novel Vehicular Compatibility-Based Cooperative Communication in 5G Networks

This letter explores the challenges of high mobility networks in 5G communications and introduces a novel and efficient clustering scheme. We propose VC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> : vehicular compatibility-based cooperative communications to form clusters having longer and stable connections, which reduces coverage holes and extends the network access. Our exhaustive simulations in real OpenStreetMap traffic traces in the simulation for urban mobility (SUMO) and the network simulator (NS3) with LENA module demonstrate exceptional results of having more than 80% packet delivery ratio and 70%~90% success probability with only 1 s delay. Moreover, the proposed VC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> outperforms two existing solutions (MMZ and Two-Way clustering) and achieves 2~4 Mbps higher throughput.

NC–MAC: A Distributed MAC Protocol for Reliable Beacon Broadcasting in V2X

Beacon broadcasting is of great importance in improving road safety and avoiding dangerous situations in vehicular ad hoc networks (VANETs). In order to support emerging vehicular applications such as autonomous driving, the reliability of beacon broadcasting becomes an indispensable issue which is also difficult given the highly dynamic topology and vehicle density. For the territories which are not covered with communication infrastructure, controlling and scheduling in a centralized way may not be applicable. Therefore, vehicle-to-vehicle (V2V) ad hoc communication is promising to address the ubiquitousness coverage concern. In this paper, a distributed network coding-based medium access control protocol (NC-MAC) is proposed to support V2V beacon broadcasting. We combine the preamble-based feedback mechanism, retransmissions, and network coding together to enhance broadcasting reliability. Extensive simulations are given to show the performance gain of NC-MAC protocol compared to the existing 5 G cellular vehicle-to-everything (C-V2X) MAC protocol in a wide range of scenarios including highway and urban vehicle traces generated by simulation of urban mobility (SUMO). The results show that the proposed protocol can improve the communication reliability as well as scalability.

Analysis of Pollutant Emissions on City Arteries—Aspects of Transport Management

The aim of the study is to present a methodology for analyzing pollution emissions in a medium-sized city using modern traffic simulations in the aspect of minimizing exhaust emissions. The scope of the research and the methods of analysis used differ from those applied in big cities projects that can be found in the literature, Therefore the progressive elaboration model has been applied methodically to formulate and carry out the feasibility study. To perform microscopic traffic simulations, the software Simulation of Urban Mobility (SUMO—German Aerospace Center (DLR), Berlin, Germany) was applied. Thanks to the simulations, changes in traffic organization were accurately identified in the context of pollution emissions before they were implemented. The proposed approach allows a smooth flow of vehicles and a reduction of exhaust emissions. The experiments, supported by visual modelling of traffic with respect to pollution emissions, were performed on one of the main arteries of the city of Czestochowa (Poland). The results were used to explain the benefits of planned roadworks and convince the city government of the necessity to modernize the communication network.

A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles

Intelligent decision control is one key issue of automated vehicles. Complex dynamic traffic flow and multi-requirement of passengers including vehicle safety, comfort, vehicle efficiency bring about tremendous challenges to vehicle decision making. Overtaking maneuver is a demanding task due to its large potential of traffic collision. Therefore, this paper proposes a fuzzy-inference-based reinforcement learning (FIRL) approach of autonomous overtaking decision making. Firstly, the problem of overtaking is formulated as a multi-objective Markov decision process (MDP) considering vehicle safety, driving comfort, and vehicle efficiency. Secondly, a temporal difference learning based on dynamic fuzzy (DF-TDL) is presented to learn optimized policies for autonomous overtaking decision making. Fuzzy inference is introduced to deal with continuous states and boost learning process. The RL algorithm decides whether to overtake or not based on the learned policies. Then, the automated vehicle executes local path planning and tracking. Furthermore, a simulation platform based on simulation of urban mobility (SUMO) is established to generate the random training data, that is, various traffic flows for algorithm iterative learning and validate the proposed method, extensive test results demonstrate the effectiveness of the overtaking decision-making method.

Energy saving performance improvement of intelligent connected PHEVs via NN-based lane change decision

Plug-in hybrid electric vehicles (PHEVs) unite the advantages of the engine and electric motor which could provide great potential in saving energy. However, the fuel economy performance of the PHEVs is highly associated with the driving condition, especially for parallel PHEVs because they could not decouple the engine work status from the driving condition. Meanwhile, fuel economy performance is not only a longitudinal issue but also related to lane selection. Lane selection is an important driving behavior and the algorithm of lane selection is necessary for the development progress of intelligent connected vehicles. Energy consumption cost is an important part of the vehicle’s using consumption cost. Therefore, lane selection strategies must consider this point. With the development of intelligent connected vehicle technology, such as V2X (Vehicle to Everything), the potential of energy consumption performance of intelligent connected PHEVs could be improved by taking environment information from V2X and smart sensors into lane selection. In this paper, a neural network (NN) based method is proposed to predict the future status of the local vehicle using the information from V2X, and then another network is used to estimate the future energy consumption of each lane. The lane selection is decided on energy consumption estimation. Lastly, the effectiveness of the method is validated by simulation using Matlab combined with SUMO (Simulation of Urban MObility).

Traffic flow and emissions improvement via Vehicle‐to‐vehicle and vehicle‐to‐infrastructure communication for an intelligent intersection

AbstractAs transportation becomes more demanding in modern communities, the challenges involved such as congestion and emissions grow more concerns. Intelligent transportation system (ITS) is one of the most recognizable solution to resolve the problem. One of the components of an ITS is intelligent intersections that use vehicle‐to‐vehicle (V2V) and vehicle‐to‐infrastructure (V2I) communications to reduce the waiting time and consequently the idling time and emission of the vehicles. To implement different control strategies to reach the aforementioned objectives, a validated platform is required to simulate the real‐world traffic flow. To this end, Simulation of Urban Mobility (SUMO) software along with real data are utilized for developing two control strategies: Single Vehicle Speed Advisory Algorithm (SVSAA) and Platoon Speed Advisory Algorithm (PSAA). The results of real‐world simulation demonstrate that the proposed schemes are able to reduce the waiting time, fuel consumption, and emissions significantly compared with the baseline strategy. Moreover, it turns out that PSAA scheme implementation via model predictive controller may totally eliminate the congestion at the intersection.

Predictive Wireless Based Status Update for Communication-Agnostic Sampling

In a wireless network that conveys status updates from sources (i.e., sensors) to destinations, one of the key issues studied by existing literature is how to design an optimal source sampling strategy on account of the communication constraints which are often modeled as queues. In this paper, an alternative perspective is presented—a novel status-aware communication scheme, namely parallel communications , is proposed which allows sensors to be communication-agnostic. Specifically, the proposed scheme can determine, based on an online prediction functionality, whether a status packet is worth transmitting considering both the network condition and status prediction, such that sensors can generate status packets without communication constraints. We evaluate the proposed scheme on a Software-Defined-Radio (SDR) test platform, which is integrated with a collaborative autonomous driving simulator, i.e., Simulation-of-Urban-Mobility (SUMO), to produce realistic vehicle control models and road conditions. The results show that with online status predictions, the channel occupancy is significantly reduced, while guaranteeing low status recovery error. Then the framework is applied to two scenarios: a multi-density platooning scenario, and a flight formation control scenario. Simulation results show that the scheme achieves better performance on the network level, in terms of keeping the minimum safe distance in both vehicle platooning and flight control.

An Incentive Based Dynamic Ride-Sharing System for Smart Cities

Connected and automated vehicle (CAV) technology, along with advanced traffic control systems, cannot ensure congestion-free traffic when the number of vehicles exceeds the road capacity. To address this problem, in this paper, we propose a dynamic ride-sharing system based on incentives (for both passengers and drivers) that incorporates travelers of similar routes and time schedules on short notice. The objective is to reduce the number of private vehicles on urban roads by utilizing the available seats properly. We develop a mobile-cloud architecture-based system that enables real-time ride-sharing. The effectiveness of the proposed system is evaluated through microscopic traffic simulation using Simulation of Urban Mobility (SUMO) considering the traffic flow behavior of a real smart city. Moreover, we develop a lab-scale experimental prototype in the form of Internet of Things (IoT) network. The simulation results show that the proposed system reduces fuel consumption, CO2 and CO emissions, and average waiting time of vehicles significantly, while increasing the vehicle’s average speed. Remarkably, it is found that only 2–10% ride-sharing can improve the overall traffic performance.

An Efficient Context-Aware Vehicle Incidents Route Service Management for Intelligent Transport System

The continuous urbanization with extensive dynamic situations on evolving cities, urban, and suburban areas, it is not feasible to categorize the navigation as fastest route, toll-free, and other variants. Metropolitan areas are more prone to traffic congestion, lane blocking, accidents, etc., due to the overcrowding and dynamic change of commuters&#x2019; arrival rates. In the metropolitan areas, most of the commuters&#x2019; use Google map to reach their desired destinations. It is quite often that route specified by navigation will not be reliable because sometimes due to the inability to update the sudden occurrence of incidents on the routes. Currently, Google map and GPS provide the time required to cover the distance and shortest route to reach the destination. The main issues with the existing Google map are it does not considers the impact of sudden occurrence of incidents, does not show the type of incidents that occurred, clearance time, and optimal routes. These issues are solved by designing an efficient context-aware vehicle incidents route service management for an intelligent transport system. The proposed system takes the context information of incidents, vehicles, weather conditions, roadside units, roads, and so on. This context information will be collected and shared with the nearby vehicles and roadside units using both mobile agents and dedicated short-range communication protocols. The proposed system suggests alternative routes with minimal delay and traffic clearance time and severity of incidents to the commuters. Also, it provides the incident information to the neighborhood vehicles, roadside units, nearby hospitals, ambulance, and members of the victims. The proposed system is exhaustively simulated in objective modular network testbed in C++, simulation of urban mobility, and Veins with different simulation parameters. The proposed system&#x2019;s simulation results reduce the travel time (7 min) compared to the without the context information system (25 min), least collision rate (0.785&#x0025;) compared to the existing system, minimizes the traffic clearance time in the incident zone, and uniform distribution of vehicle traffic on the estimated routes.

Traffic Signal Control Using Hybrid Action Space Deep Reinforcement Learning.

Recent research works on intelligent traffic signal control (TSC) have been mainly focused on leveraging deep reinforcement learning (DRL) due to its proven capability and performance. DRL-based traffic signal control frameworks belong to either discrete or continuous controls. In discrete control, the DRL agent selects the appropriate traffic light phase from a finite set of phases. Whereas in continuous control approach, the agent decides the appropriate duration for each signal phase within a predetermined sequence of phases. Among the existing works, there are no prior approaches that propose a flexible framework combining both discrete and continuous DRL approaches in controlling traffic signal. Thus, our ultimate objective in this paper is to propose an approach capable of deciding simultaneously the proper phase and its associated duration. Our contribution resides in adapting a hybrid Deep Reinforcement Learning that considers at the same time discrete and continuous decisions. Precisely, we customize a Parameterized Deep Q-Networks (P-DQN) architecture that permits a hierarchical decision-making process that primarily decides the traffic light next phases and secondly specifies its the associated timing. The evaluation results of our approach using Simulation of Urban MObility (SUMO) shows its out-performance over the benchmarks. The proposed framework is able to reduce the average queue length of vehicles and the average travel time by 22.20% and 5.78%, respectively, over the alternative DRL-based TSC systems.

Coordinated ramp signal optimization framework based on time series flux-correlation analysis.

Urban expressways provide an effective solution to traffic congestion, and ramp signal optimization can ensure the efficiency of expressway traffic. The existing methods are mainly based on the static spatial distance between mainline and ramp to achieve multi-ramp coordinated signal optimization, which lacks the consideration of the dynamic traffic flow and lead to the long time-lag, thus affecting the efficiency. This article develops a coordinated ramp signal optimization framework based on mainline traffic states. The main contribution was traffic flow-series flux-correlation analysis based on cross-correlation, and development of a novel multifactorial matric that combines flow-correlation to assign the excess demand for mainline traffic. Besides, we used the GRU neural network for traffic flow prediction to ensure real-time optimization. To obtain a more accurate correlation between ramps and congested sections, we used gray correlation analysis to determine the percentage of each factor. We used the Simulation of Urban Mobility simulation platform to evaluate the performance of the proposed method under different traffic demand conditions, and the experimental results show that the proposed method can reduce the density of mainline bottlenecks and improve the efficiency of mainline traffic.

Evaluation of Accuracy of Traffic Flow Generation in SUMO

A traffic simulation of the Jianghan Zone in Wuhan, China was carried out. In order to simulate genuine traffic flow without traditional hard-to-implement data collection methods, geographic population distribution data were gathered from the public information and traffic flow was generated by ActivityGen in SUMO (Simulation of Urban Mobility). For the sake of discovering the accuracy of the simulated traffic, real-time road condition and traffic prediction based on previous data on same time of each road in this area was compared. The results show that traffic flow generated from geographic population distribution data has referential meanings and with more detailed model classification, simulated traffic data can be closer to real conditions. This may offer a new way to generate traffic flow for researchers working in traffic simulation area. Further improvement of the accuracy in traffic flow generation by geographic population needs to pay more attention on special places like hospital and train stations.

Solution of Problems to Ensure Road Safety by Means of Intelligent Transport Systems

The article is devoted to intelligent transport systems based on short-range radio technology (DSRC). The main feature of this type of system is the ability to provide communication between vehicles without the direct involvement of drivers and without access to the global network. This allows to solve a number of problems related mainly to road safety. This article is about collision prediction and the detection of dangerous driving elements. For these problems, mathematical models of their solution are given, a description of the basic terms of the proposed algorithms, and the results of simulation experiments delivered using the traffic simulator Simulation of Urban Mobility are presented. The model for prediction of vehicle collisions is based on methods for approximating vehicle trajectories and their pairwise comparison. The detection of dangerous driving elements is based on the statistical processing of a number of vehicle motion parameters in the visibility range of the such DSRC device.