Traffic Simulation Technology Research Articles

Enhancing parameter calibration for micro-simulation models: Investigating improvement methods

Calibrating microscopic traffic simulation models is a prerequisite for simulation applications. This study proposes three novel methods to improve the accuracy and interpretability of the calibration model. The proposed approach involves selecting the calibration parameter, refining the model parameter system, and optimizing the calibration results. The first method expands the single-point mean into a multi-point distribution. The cumulative distribution curve of delay was selected as the calibration parameter. The second method divides the parameter system into global and local parameters. Global parameters were calibrated using NGSIM measured data, and local parameters were calibrated through intelligent algorithms. The third method proposes a methodology of parameter clustering recursion based on the genetic algorithm results, with information entropy selected as the analysis index. To evaluate the effectiveness of the proposed optimization methods, this study used NGSIM trajectory data as a case study. Eight simulation schemes based on the three optimization methods were designed, and simulation experiments were conducted using the VISSIM platform. The results show that the accuracy of the multi-point distribution calibration and parameter value optimization method is significantly higher than the default method. Additionally, the optimization method with calibration of both global and local parameters was more consistent with actual driving characteristics. This study provides a theoretical foundation for improving the practical application of traffic simulation technology, which has significant implications for transportation planning and management.

Modelling and simulation of urban traffic systems: present and future

The conflict of supply and demand in urban traffic system causes serious problems nowadays owing to rapid urbanisation worldwide, including traffic congestion, air pollution, etc. In this paper, the recent development of modelling and simulation of urban traffic systems is briefly overviewed, where the macro-, micro- and meso-scopic simulation models, especially the micro-scopic models are discussed. Three widely used microscopic traffic simulation models are analysed and the new generation traffic simulation technologies for Intelligent Transportation Systems (ITS) are discussed from the perspectives of software technology, hardware technology, and methodologies. The existing problems and challenges in modelling and simulation of urban traffic systems are evaluated and the latest trends and the potential solutions are suggested.

Development of people mass movement simulation framework based on reinforcement learning

Understanding individual and crowd dynamics in urban environments is critical for numerous applications, such as urban planning, traffic forecasting, and location-based services. However, researchers have developed travel demand models to accomplish this task with survey data that are expensive and acquired at low frequencies. In contrast, emerging data collection methods have enabled researchers to leverage machine learning techniques with a tremendous amount of mobility data for analyzing and forecasting people’s behaviors. In this study, we developed a reinforcement learning-based approach for modeling and simulation of people mass movement using the global positioning system (GPS) data. Unlike traditional travel demand modeling approaches, our method focuses on the problem of inferring the spatio-temporal preferences of individuals from the observed trajectories, and is based on inverse reinforcement learning (IRL) techniques. We applied the model to the data collected from a smartphone application and attempted to replicate a large amount of the population’s daily movement by incorporating with agent-based multi-modal traffic simulation technologies. The simulation results indicate that agents can successfully learn and generate human-like travel activities. Furthermore, the proposed model performance significantly outperforms the existing methods in synthetic urban dynamics.

Case Study: Optimization of Underground Car Park Design and Safety Assessment

The development of underground space is a very complicated process, and the traditional 2D-based approach in engineering is not enough to solve the problems encountered. The 3D visualization brought by BIM technology greatly improves the accuracy of design and construction. This paper’s case is the underground parking lot development project of Shanghai International Shipping Service Center. The underground parking lot design and optimization is based on the Building Information Modeling (BIM)+ traffic simulation technology. And according to the actual condition of the parking lot, we established a safety evaluation index system, and constructed a micro-simulation road network through VISSIM, so that we can determine potential safety conflict points on each floor and make recommendations. Finally, based on fuzzy evaluation theory and analytic hierarchy process, we evaluated the safety level of the underground parking lot. The safety evaluation result shows that the junction of the passageway from the B2 to B1 is the main point of security conflict, and it is necessary to set up corresponding warning signs and guidance measures at these locations. The BIM + traffic simulation technology adopted in this paper is a new model, and this research has reference value for the development of urban underground parking systems

Study on Parameters Calibration in Traffic Simulation Technology

Traffic simulation technology is used to simulate traffic situation, and provide data base for selection and comparison of different proposals, whose most important problem to be solved is that simulation data can match with the actual situation. To ensure the realistic of the simulation data, we use the method which is the organic combination between GA and SPSA to calibrate the simulation model. At last, it seems that the technology is applicable from the result.

Estimating the Cruising Range of Electric Vehicle Based on Instantaneous Speed and Acceleration

In contrast to fuel vehicles, the wide-spread use of electric vehicles (EVs) is still hindered by limited battery capacity and cruising range. It is important to forecast the EVs cruising range accurately before departure and reduce the risk of running out of electricity before arriving at the destination or charging station. In this article, through analyzing the variation characteristics of energy consumption rate with instantaneous speed and acceleration, a series of EV energy consumption rate models are established according to different operation modes. Further, a novel cruising range estimation method is proposed based on the presented EV energy consumption rate models, which is characterized by fully considering the impacts of instantaneous speed and acceleration. Finally, using the simulation data of a road in Beijing, the model presented in this article is utilized in conjunction with microscopic traffic simulation technologies to demonstrate its application in estimating the EVs cruising range under different traffic volumes.

The Study of Traffic Simulation System Based on B/S Pattern

Traffic simulation is now widely accepted as one of the most appropriate analytical methods for understanding traffic capacity and for assessing the effectiveness of traffic amends. This paper studied the architecture of several pieces of popular simulation software, compared the stand-alone pattern with B/S (Browser/Server) pattern, analysed the increasing need to improve traffic simulation software by changing the stand-alone pattern, then presented a suitable architecture to realize B/S pattern for traffic simulation software, and had successfully built the Traffic Simulation WebGIS System which was based on WebGIS technology and .Net Framework. This system makes full use of WebGIS and traffic simulation technologies which can best meet traffic management needs. Users can visit the system and use the traffic simulation functions offered by remote servers through the Internet by browsers anywhere without having to install any special software on their compter or mobile machines.