A SUMO Based Simulation Framework for Intelligent Traffic Management System

Akhter, Shamim; System, Applied Intelligent; Ahsan, Md. Nurul; Quaderi, Shah Jafor Sadeek; Forhad, Md. Abdullah Al; Sumit, Sakhawat Hosain; Rahman, Md. Rahatur

doi:10.18178/jtle.8.1.1-5

Cited by 21 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, several works [10], [19], [25] including this one, require more realistic road networks. Therefore, it is necessary to import a digital road map, called Open Street Map (OSM), before using "netconvert" to convert it into SUMO-XML file [1], [21], which is the real-world road networks, as shown in figure 3.…”

Section: Traffic Simulatormentioning

confidence: 99%

See 1 more Smart Citation

Untitled

2021

IJCNC

View full text Add to dashboard Cite

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.

show abstract

Section: Traffic Simulatormentioning

confidence: 99%

“…If traffic simulation contains a few vehicles in a small area [1], [11], [23], the vehicle's route and vehicle's properties can be set manually. In contrast, the traffic simulation of a large city, e.g.…”

Section: Traffic Simulatormentioning

confidence: 99%

Untitled

2021

IJCNC

View full text Add to dashboard Cite

show abstract

“…Thus, it is common that road traffic-related data are stored in a cloudbased server or multiple computers-based data centers. We have already implemented our low-cost flexible and reliable ITMS [1][2][3][4][5] into public cloud-based architecture in [6]. However, to include the public services or provide the Open Data framework needs private storage facilities like a data center with limited budget commodity hardware.…”

Section: Related Workmentioning

confidence: 99%

“…ITMS takes weather, road, and vehicle-related data from a road segment on an hourly basis and dynamically calculates the weight of this road segment using the Deep-Neuro-Fuzzy model [3]. Besides, the Deep-Neuro-Fuzzy model was implemented by a simulation-based environment with the SUMO tool [4] [5] and proved the workability of the model. The next step is to implement the ITMS in a real testbed with real traffic scenarios.…”

Section: Introductionmentioning

confidence: 99%

Design and Development of An ASP.NET Based ITM Data Center To Support Open Data

Rahman

Forhad

Ahmed

et al. 2021

2021 International Conference on Information Technology (ICIT)

Self Cite

View full text Add to dashboard Cite

Intelligent Traffic Management (ITM) helps to solve real-time traffic problems and guides efficient and effective routes to reach a destination. It aggregates information from various sensors located in different places of roads and in vehicles to collect different kinds of data about vehicles, weather, roads, and traffic, etc. These data are filtered and processed to generate results from which ITM generates appropriate communication-related decisions. The full ITM must be able to cooperate by allowing communication with and among vehicles and/or IoT devices. It creates pressure on the network, requiring high data transmission bandwidth, and demands short response time and latency for our time-sensitive traffic applications. Besides these, massive amounts of data also demand faster processing and secure storage. In this context, a data center is deemed an ideal companion for ITM which will be used for storage, processing, and transmission of data and results back to different clients. In this article, we are going to present a data center that is specially built for ITM. Our designed data center uses WebSocket-based bi-directional communication, load balance, fault tolerable module, data replicability, and provides road-vehicle-traffic-related web services and distributes Open Data with API supports.

show abstract

“…There are also widely used traffic simulators in an urban environment, such as e.g., SUMO, MATSim [23,24]. SUMO-Simulation of Urban Mobility is a helpful and widely used simulation program in the urban environment [25][26][27][28][29]. Modifying a SUMO query is very prone to errors or mistakes because the query data should be modified in its XML file.…”

Section: Introductionmentioning

confidence: 99%

Use of Universal Simulation Software Tools for Optimization of Signal Plans at Urban Intersections

et al. 2022

View full text Add to dashboard Cite

Intersections in cities are important transport hubs, where traffic flows from all roads meet, connect, disconnect or intersect. This research is dedicated to the creation of simulation models of intersections and is based on real observations of two crossroads in a city. The principle is based on observing traffic flows using real traffic counting at peak times. The aim is to reduce traffic congestion by adjusting signal plans on the monitored section using computer simulation and modelling in ExtendSim8 software, which is a universal tool allowing the user to simulate any system or process by creating a logical representation in an easy-to-use format. According to our preliminary literature research, the ExtendSim software has never before been used before to create an intersection simulation to optimize the signal plan. There are several specialized software products for simulating traffic and intersections, but not everyone has access to these, or else they require lengthy user training. Therefore, it is very advantageous to use a universal simulation tool that is not used for traffic simulation at intersections in the city. The article points out that a universal simulation program such as ExtendSim can also be used in the design or assessment of signal plans at intersections.

show abstract

A SUMO Based Simulation Framework for Intelligent Traffic Management System

Cited by 21 publications

References 13 publications

Untitled

Untitled

Design and Development of An ASP.NET Based ITM Data Center To Support Open Data

Use of Universal Simulation Software Tools for Optimization of Signal Plans at Urban Intersections

Contact Info

Product

Resources

About