Demand Forecasting Model for Park-and-Ride Lots in King County, Washington

Author(s):  
Susan Hendricks ◽  
Maren Outwater

As the demand for using park-and-ride lots grows, the need to accurately forecast these trips also grows. Initially, demand for park-and-ride lots was forecast using a technique that identified the draw area for each lot and estimated demand without regard to capacity. These were simplifying assumptions that are no longer appropriate with respect to current demand for park-and-ride lots. In King County, Washington, the 12 largest park-and-ride lots are currently operating at 95 percent utilization. According to a recent park-and-ride lot survey in King County, there is significant latent demand for using lots that are full. The analysis of demand for parking in park-and-ride lots in King County was developed as part of the Washington State Department of Transportation Public/Private Partnership Program for the Park-and-Ride Capacity Enhancement Project. There were 17 park-and-ride lots considered for capacity enhancement. The approach to evaluate park-and-ride lot demand uses a technique to identify intermediate stop choices, such as park-and-ride lots, as part of the overall modal choice. User and nonuser surveys were evaluated to identify the importance of specific variables, such as security or amenities. A combination of the survey results and an application of the demand forecasting model were used to estimate shifts in demand for parking from increased capacity and user fees. Several different user fees were tested and compared with stated preference results from the user and nonuser surveys. The project resulted in significantly different demand for park and ride than previous modeling efforts because of the impact of lot capacity and effects of user fees.

2013 ◽  
Vol 392 ◽  
pp. 618-621
Author(s):  
Zhi Gang Wang ◽  
Qing Jie Zhou ◽  
Xing Hua Zhou

A combined power demand forecasting model with variable weight considering both of the impact of the macroeconomic situation and the internal development trend is proposed. The proposed model consists of regression analysis models and the trend extrapolation models. The variable weight is determined by the difference of the prediction results between the two kinds of models . Beijing's power demand forecasting illustrates the usefulness and reliability of the combined model.


2020 ◽  
pp. 1-11
Author(s):  
Hongjiang Ma ◽  
Xu Luo

The irrationality between the procurement and distribution of the logistics system increases unnecessary circulation links and greatly reduces logistics efficiency, which not only causes a waste of transportation resources, but also increases logistics costs. In order to improve the operation efficiency of the logistics system, based on the improved neural network algorithm, this paper combines the logistic regression algorithm to construct a logistics demand forecasting model based on the improved neural network algorithm. Moreover, according to the characteristics of the complexity of the data in the data mining task itself, this article optimizes the ladder network structure, and combines its supervisory decision-making part with the shallow network to make the model more suitable for logistics demand forecasting. In addition, this paper analyzes the performance of the model based on examples and uses the grey relational analysis method to give the degree of correlation between each influencing factor and logistics demand. The research results show that the model constructed in this paper is reasonable and can be analyzed from a practical perspective.


Sign in / Sign up

Export Citation Format

Share Document