A link-to-link segment based metamodel for dynamic network loading

Abstract Dynamic network loading (DNL) is a core part of simulation-based dynamic traffic assignment (DTA) models, which describes how traffic propagates on a transportation network and usually maps a set of route departure rates to a set of route travel times. Due to the incorporation of different intra- and inter-link dynamics such as queuing, spillback, etc., DNL becomes complex, resulting in models with undesirable analytical properties (e.g., discontinuity, non-differentiability, and lack of closed-form) and requiring intensive computational efforts. Moreover, as DNL is applied repeatedly in simulation-based DTA algorithms, it often is the computational bottleneck of large-scale traffic assignment and related optimization problems. In this research, we address these problems by proposing a link-to-link segment-based Kriging metamodel for dynamic network loading. The proposed Kriging model calculates route travel time, link travel time, and link flow. It systematically approximates the traditional DNL model while being faster and maintaining some desirable analytical properties. Both temporal and spatial proximity information and the route segment incidence information are incorporated in the metamodel formulation. The models are trained using maximum likelihood estimation with different dataset sizes. In the experiments, the proposed Kriging metamodels performed better than a state-of-the-art neural network model, achieving an average error of 1.64% and 5.32% in the Nguyen Dupuis (ND) network and the Sioux Falls (SF) network, respectively, along with at least 43 times, sometimes as high as over 1300 times, improvement in computational speed. The results, however, suggest a tradeoff between efficiency and accuracy and the size of the training dataset. With balanced route demand, the model’s performance was reasonable even under congested traffic conditions. The MAPE values were at most 3% and 18% in the ND network and the SF network, respectively, for different level of congestion demonstrating the effectiveness of the proposed model.

[1]  Kay W. Axhausen,et al.  Predicting road system speeds using spatial structure variables and network characteristics , 2007, J. Geogr. Syst..

[2]  Nicholas B. Taylor.  The CONTRAM Dynamic Traffic Assignment Model , 2003 .

[3]  Lei Zhang,et al.  Surrogate‐Based Optimization of Expensive‐to‐Evaluate Objective for Optimal Highway Toll Charges in Transportation Network , 2014, Comput. Aided Civ. Infrastructure Eng..

[4]  Hong Kam Lo,et al.  An informed user equilibrium dynamic traffic assignment problem in a multiple origin-destination stochastic network , 2018, Transportation Research Part B: Methodological.

[5]  W. Y. Szeto,et al.  A CELL-BASED SIMULTANEOUS ROUTE AND DEPARTURE TIME CHOICE MODEL WITH ELASTIC DEMAND , 2004 .

[6]  Hong Kam Lo,et al.  Doubly Uncertain Transport Network: Degradable Link Capacity and Perception Variations in Traffic Conditions , 2006 .

[7]  Kay W. Axhausen,et al.  The Multi-Agent Transport Simulation , 2016 .

[8]  W. Y. Szeto,et al.  Dynamic traffic assignment: formulations, properties, and extensions , 2003 .

[9]  Steven Logghe,et al.  Multicommodity Link Transmission Model for Dynamic Network Loading , 2006 .

[10]  Carolina Osorio,et al.  Dynamic origin-destination matrix calibration for large-scale network simulators , 2019, Transportation Research Part C: Emerging Technologies.

[11]  W. Y. Szeto,et al.  DYNAMIC TRAFFIC ASSIGNMENT: PROPERTIES AND EXTENSIONS , 2006 .

[12]  Tao Yao,et al.  Existence of simultaneous route and departure choice dynamic user equilibrium , 2012, 1211.0898.

[13]  Xiaowei Zhang,et al.  Enhancing stochastic kriging for queueing simulation with stylized models , 2018, IISE Transactions.

[14]  Xiangyu Wang,et al.  Traffic Volume Prediction With Segment-Based Regression Kriging and its Implementation in Assessing the Impact of Heavy Vehicles , 2019, IEEE Transactions on Intelligent Transportation Systems.

[15]  Hong Kam Lo,et al.  Modeling competitive multi-modal transit services; a nested logit approach. , 2004 .

[16]  Terry L. Friesz,et al.  Statistical metamodeling of dynamic network loading , 2018, Transportation Research Part B: Methodological.

[17]  Yi-Chang Chiu,et al.  A Temporal Domain Decomposition Algorithmic Scheme for Large-Scale Dynamic Traffic Assignment , 2012 .

[18]  Tomaz Tollazzi,et al.  Calibration of microsimulation traffic model using neural network approach , 2013, Expert Syst. Appl..

[19]  W. Y. Szeto,et al.  A cell-based variational inequality formulation of the dynamic user optimal assignment problem , 2002 .

[20]  Runze Li,et al.  Design and Modeling for Computer Experiments , 2005 .

[21]  Carlos F. Daganzo,et al.  THE CELL TRANSMISSION MODEL, PART II: NETWORK TRAFFIC , 1995 .

[22]  Qingquan Li,et al.  An improved distance metric for the interpolation of link-based traffic data using kriging: a case study of a large-scale urban road network , 2012, Int. J. Geogr. Inf. Sci..

[23]  Terry L. Friesz,et al.  Continuity of the path delay operator for dynamic network loading with spillback , 2015, 1501.04241.

[24]  Chenfeng Xiong,et al.  Bayesian Stochastic Kriging Metamodel for Active Traffic Management of Corridors , 2014 .

[25]  Kara M. Kockelman,et al.  Spatial prediction of traffic levels in unmeasured locations: applications of universal kriging and geographically weighted regression , 2013 .

[26]  Hong K. Lo,et al.  Metamodel-based calibration of large-scale multimodal microscopic traffic simulation , 2021 .

[27]  Yuliant Sibaroni,et al.  Prediction of public transportation occupation based on several crowd spots using ordinary kriging method , 2016 .

[28]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[29]  Lorenzo Meschini,et al.  A sequential approach to time-dependent demand calibration: Application, validation and practical implications for large-scale networks , 2017, 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS).

[30]  Kara M. Kockelman,et al.  Spatial Prediction of AADT in Unmeasured Locations by Universal Kriging , 2011 .

[31]  W. Y. Szeto,et al.  Dynamic traffic assignment: A review of the methodological advances for environmentally sustainable road transportation applications , 2018 .

[32]  Thomas J. Santner,et al.  Design and analysis of computer experiments , 1998 .

[33]  Wei Huang,et al.  Transit interchange discount optimization using an agent-based simulation model , 2020, ANT/EDI40.

[34]  Michael G.H. Bell,et al.  An efficient and exact event-based algorithm for solving simplified first order dynamic network loading problems in continuous time , 2016 .

[35]  Hong Kam Lo,et al.  Modeling transfer and non-linear fare structure in multi-modal network , 2003 .

[36]  G. Matheron.  Principles of geostatistics , 1963 .

[37]  Marta Rojo,et al.  Evaluation of Traffic Assignment Models through Simulation , 2020, Sustainability.

[38]  G. Gary Wang,et al.  Review of Metamodeling Techniques in Support of Engineering Design Optimization , 2007, DAC 2006.

[39]  Biagio Ciuffo,et al.  A Sensitivity-Analysis-Based Approach for the Calibration of Traffic Simulation Models , 2014, IEEE Transactions on Intelligent Transportation Systems.

[40]  C. Daganzo.  On the traffic assignment problem with flow dependent costs—II , 1977 .

[41]  Raghavan Srinivasan,et al.  Efficient multi-objective calibration of a computationally intensive hydrologic model with parallel computing software in Python , 2013, Environ. Model. Softw..