No abstract

Rational traffic flow forecasting is essential to the development of advanced intelligent transportation systems. Most existing research focuses on methodologies to improve prediction accuracy. However, applications of different forecast models have not been adequately studied yet. This research compares the performance of three representative prediction models with real-life data in Beijing. They are autoregressive integrated moving average, neutral network, and nonparametric regression. The results suggest that nonparametric regression significantly outperforms the other models. With Wilcoxon signed-rank test, the root mean square errors and the error distribution reveal that the nonparametric regression model experiences superior accuracy. In addition, the nonparametric regression model exhibits the best spatial-transferred application effect.

The unique valley geographical environment and the congestion-prone road landscape make valley city traffic jammed easily. In this paper, under the background of “open blocks”, two open patterns, which correspond to two different road landscapes ("ideal grid opening" and "open under realistic conditions"), are proposed. Taking Lanzhou city as an example, six basic statistical characteristics are used to compare and analyze the changes of road network topology in blocks to find out which open pattern is more suitable for valley cities. The results show that the pattern "open under realistic conditions" has a significant effect on the improvement of network performance and capacity. Specifically, breaking the "large blocks" and developing the small-scale blocks help to alleviate the traffic pressure. Besides, the opening of blocks located along river valley has a more positive effect on improving road network performance than the blocks sited in the inner area of cities.

Urban public transport is an effective way to solve urban traffic problems and promote sustainable development of urban traffic. A scientific operation scheduling system has an important guiding significance for optimizing the configuration of urban public transport capacity resources, improving the level of operation organization and management, and providing for the sustainability of the transportation system. According to the inhomogeneous distribution of passenger flow along transit lines, this study develops a combinational scheduling model in which the enterprise supplies zonal service based on regular service. The objective function minimizes the sum of passenger travel cost and operation cost, and the simulated annealing algorithm is designed to solve the optimization model. This paper abstracts an ideal example by taking a real-world case of Bus Line 131 in Lanzhou, China. The numerical example is used to verify the validity of the model and algorithm. Results show that the combinational operation scheme can effectively satisfy passengers’ demand and reduce the total cost by 7.03% in comparison with the regular operation system. The optimal combinational system with the lowest total cost can increase the vehicle load factor and improve the utilization ratio.

No abstract