Activity-Based Travel Demand Forecasting Using Micro-Simulation

2014 ◽  
pp. 167-181
Author(s):  
Qiong Bao ◽  
Bruno Kochan ◽  
Tom Bellemans ◽  
Davy Janssens ◽  
Geert Wets
Keyword(s):  
Travel Demand ◽  
Demand Forecasting ◽  
Daily Number ◽  
Average Value ◽  
Stochastic Error ◽  
Micro Simulation ◽  
Geographical Scale ◽  
Block Level ◽  
Random Components ◽  
Minimum Number

Activity-based models of travel demand employ in most cases a micro-simulation approach, thereby inevitably including a stochastic error that is caused by the statistical distributions of random components. As a result, running a transport micro-simulation model several times with the same input will generate different outputs. In order to take the variation of outputs in each model run into account, a common approach is to run the model multiple times and to use the average value of the results. The question then becomes: What is the minimum number of model runs required to reach a stable result? In this chapter, systematic experiments are carried out by using the FEATHERS, an activity-based micro-simulation modeling framework currently implemented for Flanders (Belgium). Six levels of geographic detail are taken into account, which are building block level, subzone level, zone level, superzone level, province level, and the whole Flanders. Three travel indices (i.e., the average daily number of activities per person, the average daily number of trips per person, and the average daily distance travelled per person), as well as their corresponding segmentations with respect to socio-demographic variables, transport mode alternatives, and activity types are calculated by running the model 100 times. The results show that application of the FEATHERS at a highly aggregated level only requires limited model runs. However, when a more disaggregated level is considered (the degree of the aggregation here not only refers to the size of the geographical scale, but also to the detailed extent of the index), a larger number of model runs is needed to ensure confidence of a certain percentile of zones at this level to be stable. The values listed in this chapter can be consulted as a reference for those who plan to use the FEATHERS framework, while for the other activity-based models the methodology proposed in this chapter can be repeated.

scholarly journals Study on coloring method of airport flight-gate allocation problem

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Hongyan Li ◽  
Xianfeng Ding ◽  
Jiang Lin ◽  
Jingyu Zhou
Keyword(s):  
Graph Coloring ◽  
Programming Model ◽  
Weight Vector ◽  
Multi Objective ◽  
Average Value ◽  
Two Factors ◽  
Minimum Number ◽  
First Come First Serve ◽  
Airport Terminals ◽  
Single Objective

Abstract With the development of economy, more and more people travel by plane. Many airports have added satellite halls to relieve the pressure of insufficient boarding gates in airport terminals. However, the addition of satellite halls will have a certain impact on connecting flights of transit passengers and increase the difficulty of reasonable allocation of flight and gate in airports. Based on the requirements and data of question F of the 2018 postgraduate mathematical contest in modeling, this paper studies the flight-gate allocation of additional satellite halls at airports. Firstly, match the seven types of flights with the ten types of gates. Secondly, considering the number of gates used and the least number of flights not allocated to the gate, and adding the two factors of the overall tension of passengers and the minimum number of passengers who failed to transfer, the multi-objective 0–1 programming model was established. Determine the weight vector $w=(0.112,0.097,0.496,0.395)$ w = ( 0.112 , 0.097 , 0.496 , 0.395 ) of objective function by entropy value method based on personal preference, then the multi-objective 0–1 programming model is transformed into single-objective 0–1 programming model. Finally, a graph coloring algorithm based on parameter adjustment is used to solve the transformed model. The concept of time slice was used to determine the set of time conflicts of flight slots, and the vertex sequences were colored by applying the principle of “first come first serve”. Applying the model and algorithm proposed in this paper, it can be obtained that the average value of the overall tension degree of passengers minimized in question F is 35.179%, the number of flights successfully allocated to the gate maximized is 262, and the number of gates used is minimized to be 60. The corresponding flight-gate difficulty allocation weight is $\alpha =0.32$ α = 0.32 and $\beta =0.40$ β = 0.40 , and the proportion of flights successfully assigned to the gate is 86.469%. The number of passengers who failed to transfer was 642, with a failure rate of 23.337%.

Estimating Household Travel Energy Consumption in Conjunction with a Travel Demand Forecasting Model

2017 ◽  
Vol 2668 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Venu M. Garikapati ◽  
Daehyun You ◽  
Wenwen Zhang ◽  
Ram M. Pendyala ◽  
Subhrajit Guhathakurta ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Urban Form ◽  
Travel Demand ◽  
Demand Forecasting ◽  
The United States ◽  
Metropolitan Region ◽  
Demand Model ◽  
Awareness Campaigns ◽  
Energy Footprint ◽  
Household Travel

This paper presents a methodology for the calculation of the consumption of household travel energy at the level of the traffic analysis zone (TAZ) in conjunction with information that is readily available from a standard four-step travel demand model system. This methodology embeds two algorithms. The first provides a means of allocating non-home-based trips to residential zones that are the source of such trips, whereas the second provides a mechanism for incorporating the effects of household vehicle fleet composition on fuel consumption. The methodology is applied to the greater Atlanta, Georgia, metropolitan region in the United States and is found to offer a robust mechanism for calculating the footprint of household travel energy at the level of the individual TAZ; this mechanism makes possible the study of variations in the energy footprint across space. The travel energy footprint is strongly correlated with the density of the built environment, although socioeconomic differences across TAZs also likely contribute to differences in travel energy footprints. The TAZ-level calculator of the footprint of household travel energy can be used to analyze alternative futures and relate differences in the energy footprint to differences in a number of contributing factors and thus enables the design of urban form, formulation of policy interventions, and implementation of awareness campaigns that may produce more-sustainable patterns of energy consumption.

scholarly journals Multi-Regional Online Car-Hailing Order Quantity Forecasting Based on the Convolutional Neural Network

Information ◽  
2019 ◽  
Vol 10 (6) ◽  
pp. 193 ◽  
Author(s):  
Zihao Huang ◽  
Gang Huang ◽  
Zhijun Chen ◽  
Chaozhong Wu ◽  
Xiaofeng Ma ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Travel Demand ◽  
Short Term Memory ◽  
Demand Forecasting ◽  
Image Feature ◽  
Support Vector ◽  
Data Set ◽  
Demand Distribution ◽  
Demand Forecasting Model

With the development of online cars, the demand for travel prediction is increasing in order to reduce the information asymmetry between passengers and drivers of online car-hailing. This paper proposes a travel demand forecasting model named OC-CNN based on the convolutional neural network to forecast the travel demand. In order to make full use of the spatial characteristics of the travel demand distribution, this paper meshes the prediction area and creates a travel demand data set of the graphical structure to preserve its spatial properties. Taking advantage of the convolutional neural network in image feature extraction, the historical demand data of the first twenty-five minutes of the entire region are used as a model input to predict the travel demand for the next five minutes. In order to verify the performance of the proposed method, one-month data from online car-hailing of the Chengdu Fourth Ring Road are used. The results show that the model successfully extracts the spatiotemporal features of the data, and the prediction accuracies of the proposed method are superior to those of the representative methods, including the Bayesian Ridge Model, Linear Regression, Support Vector Regression, and Long Short-Term Memory networks.

Sign in / Sign up

Export Citation Format

Share Document